{
  "tasks": [
    {
      "key": "marker_d2",
      "title": "Insert marker",
      "points": [
        {
          "round": "R0",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 10,
          "value": 0.2,
          "lo": 0.1495631113084507,
          "hi": 0.26220159457390224,
          "throughput": 0.7274490785645005,
          "throughput_lo": 0.32846340878908004,
          "throughput_hi": 1.2295254970296179
        },
        {
          "round": "R0",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 13,
          "value": 0.26,
          "lo": 0.20310479187292155,
          "hi": 0.32630697283296084,
          "throughput": 0.8029647930821494,
          "throughput_lo": 0.43394033445834035,
          "throughput_hi": 1.2430009266744466
        },
        {
          "round": "R1",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 16,
          "value": 0.32,
          "lo": 0.2581144026760303,
          "hi": 0.3889444208533815,
          "throughput": 1.1045485924675922,
          "throughput_lo": 0.6549710239086702,
          "throughput_hi": 1.6189645675407252
        },
        {
          "round": "R1",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 19,
          "value": 0.38,
          "lo": 0.31434452864304074,
          "hi": 0.4503613537099005,
          "throughput": 1.589662545319327,
          "throughput_lo": 1.0385229895260073,
          "throughput_hi": 2.183043332464862
        },
        {
          "round": "R2",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 13,
          "value": 0.26,
          "lo": 0.20310479187292155,
          "hi": 0.32630697283296084,
          "throughput": 0.7155088062622309,
          "throughput_lo": 0.39350198657667823,
          "throughput_hi": 1.0718921865633875
        },
        {
          "round": "R2",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 100,
          "successes": 47,
          "value": 0.47,
          "lo": 0.42063391602382394,
          "hi": 0.5199601433821166,
          "throughput": 1.3689320388349513,
          "throughput_lo": 1.0675235097156826,
          "throughput_hi": 1.70484078778077
        },
        {
          "round": "R2",
          "arm": "final_marker_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 23,
          "value": 0.46,
          "lo": 0.3909903069389895,
          "hi": 0.5305783205119909,
          "throughput": 1.4932910113980666,
          "throughput_lo": 0.9960649286768323,
          "throughput_hi": 2.1053482253288847
        },
        {
          "round": "R3",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 20,
          "value": 0.4,
          "lo": 0.33333333333333337,
          "hi": 0.47058823529411764,
          "throughput": 0.8167339715958075,
          "throughput_lo": 0.5096901024728734,
          "throughput_hi": 1.1929331457963435
        },
        {
          "round": "R3",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 21,
          "value": 0.42,
          "lo": 0.35243881347527767,
          "hi": 0.4906984414266831,
          "throughput": 1.0677966101694916,
          "throughput_lo": 0.7004126202861147,
          "throughput_hi": 1.510653839662718
        },
        {
          "round": "R3",
          "arm": "final_marker_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 27,
          "value": 0.54,
          "lo": 0.46942167948800917,
          "hi": 0.6090096930610106,
          "throughput": 1.3763806287170772,
          "throughput_lo": 0.9295758283239327,
          "throughput_hi": 1.939667119045798
        },
        {
          "round": "R4",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 23,
          "value": 0.46,
          "lo": 0.3909903069389895,
          "hi": 0.5305783205119909,
          "throughput": 0.9719678828003944,
          "throughput_lo": 0.6062287027498217,
          "throughput_hi": 1.455110555550663
        },
        {
          "round": "R4",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 30,
          "value": 0.6,
          "lo": 0.5294117647058824,
          "hi": 0.6666666666666666,
          "throughput": 1.2683201803833146,
          "throughput_lo": 0.8894418332910555,
          "throughput_hi": 1.7403518583499045
        },
        {
          "round": "R4",
          "arm": "final_marker_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 29,
          "value": 0.58,
          "lo": 0.5093015585733168,
          "hi": 0.6475611865247223,
          "throughput": 1.4981058431867753,
          "throughput_lo": 1.0180916974582574,
          "throughput_hi": 2.1085052935837845
        },
        {
          "round": "R5",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 21,
          "value": 0.42,
          "lo": 0.35243881347527767,
          "hi": 0.4906984414266831,
          "throughput": 0.9260620314567103,
          "throughput_lo": 0.6005999743748419,
          "throughput_hi": 1.3210168519352554
        },
        {
          "round": "R5",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 32,
          "value": 0.64,
          "lo": 0.5699854243199669,
          "hi": 0.7045243796016016,
          "throughput": 1.4859147662779897,
          "throughput_lo": 1.095127798168367,
          "throughput_hi": 1.9558351285491844
        },
        {
          "round": "R5",
          "arm": "final_marker_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 38,
          "value": 0.76,
          "lo": 0.6948814593528864,
          "hi": 0.814922462215741,
          "throughput": 2.3367040174911176,
          "throughput_lo": 1.7304616609419265,
          "throughput_hi": 3.063095118390232
        }
      ],
      "rounds": {
        "R0": [
          {
            "label": "R0",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 218,
                  "ours_freecf": 176
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 3,
                  "ours_freecf": 2
                },
                "steps": {
                  "baseline": 72,
                  "ours_freecf": 158
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 72,
                  "ours_freecf": 300
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 6,
                  "ours_freecf": 7
                },
                "steps": {
                  "baseline": 223,
                  "ours_freecf": 91
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 8
                },
                "steps": {
                  "baseline": 319,
                  "ours_freecf": 400
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 11,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 317,
                  "ours_freecf": 133
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 13,
                  "ours_freecf": 12
                },
                "steps": {
                  "baseline": 361,
                  "ours_freecf": 58
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 15,
                  "ours_freecf": 14
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 328
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 17,
                  "ours_freecf": 16
                },
                "steps": {
                  "baseline": 177,
                  "ours_freecf": 400
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 18,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 80,
                  "ours_freecf": 400
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 293,
                  "ours_freecf": 161
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 23,
                  "ours_freecf": 22
                },
                "steps": {
                  "baseline": 286,
                  "ours_freecf": 156
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 24,
                  "ours_freecf": 25
                },
                "steps": {
                  "baseline": 77,
                  "ours_freecf": 163
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 27,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 198,
                  "ours_freecf": 251
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 29,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 157,
                  "ours_freecf": 320
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 31,
                  "ours_freecf": 30
                },
                "steps": {
                  "baseline": 319,
                  "ours_freecf": 400
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 33,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 56,
                  "ours_freecf": 35
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 34,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 396
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 37,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 383,
                  "ours_freecf": 400
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 130,
                  "ours_freecf": 400
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 41,
                  "ours_freecf": 40
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 400
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 42,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 156,
                  "ours_freecf": 185
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 44,
                  "ours_freecf": 45
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 400
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 46,
                  "ours_freecf": 47
                },
                "steps": {
                  "baseline": 146,
                  "ours_freecf": 305
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 49,
                  "ours_freecf": 48
                },
                "steps": {
                  "baseline": 458,
                  "ours_freecf": 256
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 50
                },
                "steps": {
                  "baseline": 54,
                  "ours_freecf": 347
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 52,
                  "ours_freecf": 53
                },
                "steps": {
                  "baseline": 186,
                  "ours_freecf": 483
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 54,
                  "ours_freecf": 55
                },
                "steps": {
                  "baseline": 640,
                  "ours_freecf": 54
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 56,
                  "ours_freecf": 57
                },
                "steps": {
                  "baseline": 52,
                  "ours_freecf": 219
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 58,
                  "ours_freecf": 59
                },
                "steps": {
                  "baseline": 602,
                  "ours_freecf": 372
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 61
                },
                "steps": {
                  "baseline": 61,
                  "ours_freecf": 535
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 63,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 147,
                  "ours_freecf": 172
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 601,
                  "ours_freecf": 572
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 66,
                  "ours_freecf": 67
                },
                "steps": {
                  "baseline": 56,
                  "ours_freecf": 193
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 544,
                  "ours_freecf": 139
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 70,
                  "ours_freecf": 71
                },
                "steps": {
                  "baseline": 310,
                  "ours_freecf": 616
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 72,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 65,
                  "ours_freecf": 480
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 75,
                  "ours_freecf": 74
                },
                "steps": {
                  "baseline": 424,
                  "ours_freecf": 551
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "baseline": 76,
                  "ours_freecf": 144
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 419,
                  "ours_freecf": 195
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 80,
                  "ours_freecf": 81
                },
                "steps": {
                  "baseline": 56,
                  "ours_freecf": 410
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 83,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 487,
                  "ours_freecf": 80
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 85,
                  "ours_freecf": 84
                },
                "steps": {
                  "baseline": 526,
                  "ours_freecf": 423
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 87,
                  "ours_freecf": 86
                },
                "steps": {
                  "baseline": 168,
                  "ours_freecf": 110
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 88,
                  "ours_freecf": 89
                },
                "steps": {
                  "baseline": 237,
                  "ours_freecf": 487
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 90,
                  "ours_freecf": 91
                },
                "steps": {
                  "baseline": 41,
                  "ours_freecf": 444
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 93,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 151,
                  "ours_freecf": 594
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 94,
                  "ours_freecf": 95
                },
                "steps": {
                  "baseline": 57,
                  "ours_freecf": 46
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 96
                },
                "steps": {
                  "baseline": 163,
                  "ours_freecf": 84
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 99,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 151,
                  "ours_freecf": 149
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/r0_baseline_vs_ours_heval_sobol50_final/paired_round_outcomes.csv"
          }
        ],
        "R1": [
          {
            "label": "R1",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 2
                },
                "steps": {
                  "baseline": 97,
                  "ours_freecf": 224
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 312,
                  "ours_freecf": 156
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 7,
                  "ours_freecf": 8
                },
                "steps": {
                  "baseline": 203,
                  "ours_freecf": 301
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 40,
                  "ours_freecf": 423
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 13,
                  "ours_freecf": 14
                },
                "steps": {
                  "baseline": 216,
                  "ours_freecf": 344
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 16,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 162,
                  "ours_freecf": 173
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 20,
                  "ours_freecf": 18
                },
                "steps": {
                  "baseline": 401,
                  "ours_freecf": 187
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 23,
                  "ours_freecf": 21
                },
                "steps": {
                  "baseline": 518,
                  "ours_freecf": 125
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 24,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 630,
                  "ours_freecf": 346
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 27,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 508,
                  "ours_freecf": 167
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 32,
                  "ours_freecf": 31
                },
                "steps": {
                  "baseline": 194,
                  "ours_freecf": 210
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 34,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 166,
                  "ours_freecf": 146
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 36,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 144,
                  "ours_freecf": 214
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 41,
                  "ours_freecf": 40
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 335
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 42,
                  "ours_freecf": 44
                },
                "steps": {
                  "baseline": 261,
                  "ours_freecf": 172
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 46,
                  "ours_freecf": 45
                },
                "steps": {
                  "baseline": 168,
                  "ours_freecf": 208
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 50,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 42,
                  "ours_freecf": 171
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 52,
                  "ours_freecf": 53
                },
                "steps": {
                  "baseline": 172,
                  "ours_freecf": 158
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 54,
                  "ours_freecf": 55
                },
                "steps": {
                  "baseline": 86,
                  "ours_freecf": 185
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 331,
                  "ours_freecf": 82
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 191,
                  "ours_freecf": 306
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 63,
                  "ours_freecf": 65
                },
                "steps": {
                  "baseline": 358,
                  "ours_freecf": 286
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 261,
                  "ours_freecf": 238
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 70,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 89,
                  "ours_freecf": 96
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 74,
                  "ours_freecf": 72
                },
                "steps": {
                  "baseline": 225,
                  "ours_freecf": 147
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "baseline": 391,
                  "ours_freecf": 321
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 79,
                  "ours_freecf": 80
                },
                "steps": {
                  "baseline": 119,
                  "ours_freecf": 90
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 83,
                  "ours_freecf": 81
                },
                "steps": {
                  "baseline": 229,
                  "ours_freecf": 237
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 100,
                  "ours_freecf": 268
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 87,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 69,
                  "ours_freecf": 236
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 92,
                  "ours_freecf": 91
                },
                "steps": {
                  "baseline": 515,
                  "ours_freecf": 257
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 95,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 449,
                  "ours_freecf": 238
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 98,
                  "ours_freecf": 97
                },
                "steps": {
                  "baseline": 181,
                  "ours_freecf": 151
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 100,
                  "ours_freecf": 101
                },
                "steps": {
                  "baseline": 230,
                  "ours_freecf": 177
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 104,
                  "ours_freecf": 103
                },
                "steps": {
                  "baseline": 269,
                  "ours_freecf": 425
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 106,
                  "ours_freecf": 105
                },
                "steps": {
                  "baseline": 386,
                  "ours_freecf": 134
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 108,
                  "ours_freecf": 109
                },
                "steps": {
                  "baseline": 48,
                  "ours_freecf": 57
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 113,
                  "ours_freecf": 112
                },
                "steps": {
                  "baseline": 236,
                  "ours_freecf": 181
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 116,
                  "ours_freecf": 114
                },
                "steps": {
                  "baseline": 597,
                  "ours_freecf": 209
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 119,
                  "ours_freecf": 117
                },
                "steps": {
                  "baseline": 307,
                  "ours_freecf": 66
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 122,
                  "ours_freecf": 121
                },
                "steps": {
                  "baseline": 225,
                  "ours_freecf": 209
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 123,
                  "ours_freecf": 125
                },
                "steps": {
                  "baseline": 525,
                  "ours_freecf": 271
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 128,
                  "ours_freecf": 126
                },
                "steps": {
                  "baseline": 162,
                  "ours_freecf": 138
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 131,
                  "ours_freecf": 130
                },
                "steps": {
                  "baseline": 207,
                  "ours_freecf": 219
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 134,
                  "ours_freecf": 132
                },
                "steps": {
                  "baseline": 518,
                  "ours_freecf": 136
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 135,
                  "ours_freecf": 136
                },
                "steps": {
                  "baseline": 247,
                  "ours_freecf": 470
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 139,
                  "ours_freecf": 140
                },
                "steps": {
                  "baseline": 321,
                  "ours_freecf": 87
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 141,
                  "ours_freecf": 143
                },
                "steps": {
                  "baseline": 282,
                  "ours_freecf": 334
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 145,
                  "ours_freecf": 146
                },
                "steps": {
                  "baseline": 203,
                  "ours_freecf": 375
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 149,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 244,
                  "ours_freecf": 71
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/r1_eval_checkpoint100000/paired_round_outcomes.csv"
          }
        ],
        "R2": [
          {
            "label": "R2",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 174,
                  "ours_freecf": 379
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 3,
                  "ours_freecf": 2
                },
                "steps": {
                  "baseline": 348,
                  "ours_freecf": 245
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 766,
                  "ours_freecf": 263
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 7,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 210,
                  "ours_freecf": 84
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 8
                },
                "steps": {
                  "baseline": 204,
                  "ours_freecf": 201
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 11,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 303,
                  "ours_freecf": 177
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 12,
                  "ours_freecf": 13
                },
                "steps": {
                  "baseline": 178,
                  "ours_freecf": 318
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 15,
                  "ours_freecf": 14
                },
                "steps": {
                  "baseline": 153,
                  "ours_freecf": 568
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 16,
                  "ours_freecf": 17
                },
                "steps": {
                  "baseline": 482,
                  "ours_freecf": 625
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 18,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 230,
                  "ours_freecf": 403
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 251,
                  "ours_freecf": 455
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 23,
                  "ours_freecf": 22
                },
                "steps": {
                  "baseline": 479,
                  "ours_freecf": 247
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 25,
                  "ours_freecf": 24
                },
                "steps": {
                  "baseline": 240,
                  "ours_freecf": 197
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 26,
                  "ours_freecf": 27
                },
                "steps": {
                  "baseline": 183,
                  "ours_freecf": 82
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 29,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 198,
                  "ours_freecf": 274
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 31,
                  "ours_freecf": 30
                },
                "steps": {
                  "baseline": 445,
                  "ours_freecf": 261
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 33,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 316,
                  "ours_freecf": 475
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 34,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 159,
                  "ours_freecf": 461
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 36,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 533,
                  "ours_freecf": 41
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 94,
                  "ours_freecf": 95
                },
                "steps": {
                  "baseline": 288,
                  "ours_freecf": 664
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 96
                },
                "steps": {
                  "baseline": 323,
                  "ours_freecf": 178
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 99,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 409,
                  "ours_freecf": 269
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 242,
                  "ours_freecf": 111
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 41,
                  "ours_freecf": 40
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 162
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 42,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 185,
                  "ours_freecf": 463
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 45,
                  "ours_freecf": 44
                },
                "steps": {
                  "baseline": 243,
                  "ours_freecf": 362
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 46,
                  "ours_freecf": 47
                },
                "steps": {
                  "baseline": 461,
                  "ours_freecf": 631
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 48,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 423,
                  "ours_freecf": 420
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 50,
                  "ours_freecf": 51
                },
                "steps": {
                  "baseline": 144,
                  "ours_freecf": 80
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 52,
                  "ours_freecf": 53
                },
                "steps": {
                  "baseline": 345,
                  "ours_freecf": 402
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 55,
                  "ours_freecf": 54
                },
                "steps": {
                  "baseline": 375,
                  "ours_freecf": 167
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 56,
                  "ours_freecf": 57
                },
                "steps": {
                  "baseline": 212,
                  "ours_freecf": 288
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 59,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 231,
                  "ours_freecf": 800
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 61
                },
                "steps": {
                  "baseline": 182,
                  "ours_freecf": 556
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 62,
                  "ours_freecf": 63
                },
                "steps": {
                  "baseline": 218,
                  "ours_freecf": 461
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 334,
                  "ours_freecf": 128
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 67,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 470,
                  "ours_freecf": 212
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 69,
                  "ours_freecf": 68
                },
                "steps": {
                  "baseline": 471,
                  "ours_freecf": 220
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 70,
                  "ours_freecf": 71
                },
                "steps": {
                  "baseline": 219,
                  "ours_freecf": 442
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 73,
                  "ours_freecf": 72
                },
                "steps": {
                  "baseline": 213,
                  "ours_freecf": 163
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 75,
                  "ours_freecf": 74
                },
                "steps": {
                  "baseline": 563,
                  "ours_freecf": 691
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 76,
                  "ours_freecf": 77
                },
                "steps": {
                  "baseline": 635,
                  "ours_freecf": 386
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 79,
                  "ours_freecf": 78
                },
                "steps": {
                  "baseline": 473,
                  "ours_freecf": 248
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 80,
                  "ours_freecf": 81
                },
                "steps": {
                  "baseline": 564,
                  "ours_freecf": 356
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 82,
                  "ours_freecf": 83
                },
                "steps": {
                  "baseline": 464,
                  "ours_freecf": 213
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 461,
                  "ours_freecf": 92
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 86,
                  "ours_freecf": 87
                },
                "steps": {
                  "baseline": 144,
                  "ours_freecf": 264
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 88,
                  "ours_freecf": 89
                },
                "steps": {
                  "baseline": 349,
                  "ours_freecf": 252
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 90,
                  "ours_freecf": 91
                },
                "steps": {
                  "baseline": 293,
                  "ours_freecf": 307
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 93,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 364,
                  "ours_freecf": 513
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/r2_eval_checkpoint100000/paired_round_outcomes.csv"
          },
          {
            "label": "DP-vs-IQL M1",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 1,
                  "ours_freecf": 0
                },
                "steps": {
                  "final_marker_iql": 504,
                  "ours_freecf": 197
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 3,
                  "ours_freecf": 4
                },
                "steps": {
                  "final_marker_iql": 474,
                  "ours_freecf": 452
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 7,
                  "ours_freecf": 8
                },
                "steps": {
                  "final_marker_iql": 108,
                  "ours_freecf": 231
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "final_marker_iql": 509,
                  "ours_freecf": 559
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 12,
                  "ours_freecf": 14
                },
                "steps": {
                  "final_marker_iql": 191,
                  "ours_freecf": 172
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 17,
                  "ours_freecf": 16
                },
                "steps": {
                  "final_marker_iql": 270,
                  "ours_freecf": 199
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 18,
                  "ours_freecf": 20
                },
                "steps": {
                  "final_marker_iql": 167,
                  "ours_freecf": 166
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 21,
                  "ours_freecf": 22
                },
                "steps": {
                  "final_marker_iql": 301,
                  "ours_freecf": 166
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 26,
                  "ours_freecf": 25
                },
                "steps": {
                  "final_marker_iql": 93,
                  "ours_freecf": 683
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 28,
                  "ours_freecf": 29
                },
                "steps": {
                  "final_marker_iql": 153,
                  "ours_freecf": 195
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 32,
                  "ours_freecf": 30
                },
                "steps": {
                  "final_marker_iql": 161,
                  "ours_freecf": 632
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 35,
                  "ours_freecf": 33
                },
                "steps": {
                  "final_marker_iql": 389,
                  "ours_freecf": 152
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 36,
                  "ours_freecf": 38
                },
                "steps": {
                  "final_marker_iql": 800,
                  "ours_freecf": 501
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 41,
                  "ours_freecf": 39
                },
                "steps": {
                  "final_marker_iql": 91,
                  "ours_freecf": 124
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 43,
                  "ours_freecf": 44
                },
                "steps": {
                  "final_marker_iql": 521,
                  "ours_freecf": 332
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 45,
                  "ours_freecf": 47
                },
                "steps": {
                  "final_marker_iql": 182,
                  "ours_freecf": 128
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 48,
                  "ours_freecf": 49
                },
                "steps": {
                  "final_marker_iql": 67,
                  "ours_freecf": 67
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 52,
                  "ours_freecf": 53
                },
                "steps": {
                  "final_marker_iql": 167,
                  "ours_freecf": 501
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 55,
                  "ours_freecf": 54
                },
                "steps": {
                  "final_marker_iql": 542,
                  "ours_freecf": 265
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 57,
                  "ours_freecf": 59
                },
                "steps": {
                  "final_marker_iql": 76,
                  "ours_freecf": 800
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 62,
                  "ours_freecf": 60
                },
                "steps": {
                  "final_marker_iql": 520,
                  "ours_freecf": 233
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 63,
                  "ours_freecf": 64
                },
                "steps": {
                  "final_marker_iql": 635,
                  "ours_freecf": 800
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 66,
                  "ours_freecf": 68
                },
                "steps": {
                  "final_marker_iql": 579,
                  "ours_freecf": 164
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 69,
                  "ours_freecf": 71
                },
                "steps": {
                  "final_marker_iql": 370,
                  "ours_freecf": 167
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 73,
                  "ours_freecf": 72
                },
                "steps": {
                  "final_marker_iql": 327,
                  "ours_freecf": 467
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 76,
                  "ours_freecf": 75
                },
                "steps": {
                  "final_marker_iql": 449,
                  "ours_freecf": 219
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 77,
                  "ours_freecf": 78
                },
                "steps": {
                  "final_marker_iql": 91,
                  "ours_freecf": 429
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 80,
                  "ours_freecf": 79
                },
                "steps": {
                  "final_marker_iql": 403,
                  "ours_freecf": 246
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 82,
                  "ours_freecf": 81
                },
                "steps": {
                  "final_marker_iql": 88,
                  "ours_freecf": 206
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 83,
                  "ours_freecf": 84
                },
                "steps": {
                  "final_marker_iql": 177,
                  "ours_freecf": 487
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 85,
                  "ours_freecf": 86
                },
                "steps": {
                  "final_marker_iql": 90,
                  "ours_freecf": 150
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 88,
                  "ours_freecf": 87
                },
                "steps": {
                  "final_marker_iql": 800,
                  "ours_freecf": 169
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 89,
                  "ours_freecf": 90
                },
                "steps": {
                  "final_marker_iql": 161,
                  "ours_freecf": 245
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 92,
                  "ours_freecf": 91
                },
                "steps": {
                  "final_marker_iql": 81,
                  "ours_freecf": 495
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 94,
                  "ours_freecf": 93
                },
                "steps": {
                  "final_marker_iql": 165,
                  "ours_freecf": 143
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 95,
                  "ours_freecf": 96
                },
                "steps": {
                  "final_marker_iql": 197,
                  "ours_freecf": 183
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 98,
                  "ours_freecf": 97
                },
                "steps": {
                  "final_marker_iql": 239,
                  "ours_freecf": 603
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 100,
                  "ours_freecf": 99
                },
                "steps": {
                  "final_marker_iql": 160,
                  "ours_freecf": 194
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 101,
                  "ours_freecf": 102
                },
                "steps": {
                  "final_marker_iql": 155,
                  "ours_freecf": 60
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 104,
                  "ours_freecf": 103
                },
                "steps": {
                  "final_marker_iql": 223,
                  "ours_freecf": 322
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 105,
                  "ours_freecf": 106
                },
                "steps": {
                  "final_marker_iql": 177,
                  "ours_freecf": 383
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 108,
                  "ours_freecf": 107
                },
                "steps": {
                  "final_marker_iql": 163,
                  "ours_freecf": 149
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 109,
                  "ours_freecf": 110
                },
                "steps": {
                  "final_marker_iql": 157,
                  "ours_freecf": 145
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_marker_iql": 111,
                  "ours_freecf": 112
                },
                "steps": {
                  "final_marker_iql": 488,
                  "ours_freecf": 569
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 113,
                  "ours_freecf": 114
                },
                "steps": {
                  "final_marker_iql": 177,
                  "ours_freecf": 102
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 116,
                  "ours_freecf": 115
                },
                "steps": {
                  "final_marker_iql": 219,
                  "ours_freecf": 192
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 118,
                  "ours_freecf": 117
                },
                "steps": {
                  "final_marker_iql": 235,
                  "ours_freecf": 213
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 120,
                  "ours_freecf": 119
                },
                "steps": {
                  "final_marker_iql": 332,
                  "ours_freecf": 151
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_marker_iql": 121,
                  "ours_freecf": 122
                },
                "steps": {
                  "final_marker_iql": 76,
                  "ours_freecf": 74
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_marker_iql": 124,
                  "ours_freecf": 123
                },
                "steps": {
                  "final_marker_iql": 162,
                  "ours_freecf": 161
                }
              }
            ],
            "columns": [
              {
                "key": "final_marker_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/final_dp_vs_iql_eval_c100k/paired_round_outcomes.csv"
          }
        ],
        "R3": [
          {
            "label": "R3",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 2,
                  "final_marker_iql": 1,
                  "ours_freecf": 0
                },
                "steps": {
                  "baseline": 601,
                  "final_marker_iql": 388,
                  "ours_freecf": 425
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 3,
                  "final_marker_iql": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 314,
                  "final_marker_iql": 830,
                  "ours_freecf": 496
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 7,
                  "final_marker_iql": 8,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 319,
                  "final_marker_iql": 208,
                  "ours_freecf": 242
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 11,
                  "final_marker_iql": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 309,
                  "final_marker_iql": 162,
                  "ours_freecf": 160
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 13,
                  "final_marker_iql": 14,
                  "ours_freecf": 12
                },
                "steps": {
                  "baseline": 266,
                  "final_marker_iql": 362,
                  "ours_freecf": 167
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 17,
                  "final_marker_iql": 16,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 268,
                  "final_marker_iql": 189,
                  "ours_freecf": 200
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 19,
                  "final_marker_iql": 18,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 266,
                  "final_marker_iql": 240,
                  "ours_freecf": 226
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 23,
                  "final_marker_iql": 22,
                  "ours_freecf": 21
                },
                "steps": {
                  "baseline": 249,
                  "final_marker_iql": 204,
                  "ours_freecf": 754
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 25,
                  "final_marker_iql": 26,
                  "ours_freecf": 24
                },
                "steps": {
                  "baseline": 583,
                  "final_marker_iql": 157,
                  "ours_freecf": 144
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 28,
                  "final_marker_iql": 27,
                  "ours_freecf": 29
                },
                "steps": {
                  "baseline": 610,
                  "final_marker_iql": 693,
                  "ours_freecf": 46
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 32,
                  "final_marker_iql": 30,
                  "ours_freecf": 31
                },
                "steps": {
                  "baseline": 366,
                  "final_marker_iql": 613,
                  "ours_freecf": 244
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 33,
                  "final_marker_iql": 34,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 763,
                  "final_marker_iql": 826,
                  "ours_freecf": 826
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 36,
                  "final_marker_iql": 37,
                  "ours_freecf": 38
                },
                "steps": {
                  "baseline": 473,
                  "final_marker_iql": 125,
                  "ours_freecf": 77
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 41,
                  "final_marker_iql": 40,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 649,
                  "final_marker_iql": 450,
                  "ours_freecf": 449
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 42,
                  "final_marker_iql": 43,
                  "ours_freecf": 44
                },
                "steps": {
                  "baseline": 265,
                  "final_marker_iql": 308,
                  "ours_freecf": 422
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 47,
                  "final_marker_iql": 45,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 682,
                  "final_marker_iql": 163,
                  "ours_freecf": 170
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 50,
                  "final_marker_iql": 49,
                  "ours_freecf": 48
                },
                "steps": {
                  "baseline": 840,
                  "final_marker_iql": 155,
                  "ours_freecf": 532
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 52,
                  "final_marker_iql": 53,
                  "ours_freecf": 51
                },
                "steps": {
                  "baseline": 256,
                  "final_marker_iql": 214,
                  "ours_freecf": 267
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 56,
                  "final_marker_iql": 54,
                  "ours_freecf": 55
                },
                "steps": {
                  "baseline": 441,
                  "final_marker_iql": 87,
                  "ours_freecf": 595
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 57,
                  "final_marker_iql": 59,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 210,
                  "final_marker_iql": 373,
                  "ours_freecf": 583
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 62,
                  "final_marker_iql": 61,
                  "ours_freecf": 60
                },
                "steps": {
                  "baseline": 397,
                  "final_marker_iql": 236,
                  "ours_freecf": 242
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 63,
                  "final_marker_iql": 64,
                  "ours_freecf": 65
                },
                "steps": {
                  "baseline": 234,
                  "final_marker_iql": 218,
                  "ours_freecf": 112
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 67,
                  "final_marker_iql": 68,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 152,
                  "final_marker_iql": 214,
                  "ours_freecf": 321
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 71,
                  "final_marker_iql": 70,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 48,
                  "ours_freecf": 401
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 74,
                  "final_marker_iql": 73,
                  "ours_freecf": 72
                },
                "steps": {
                  "baseline": 326,
                  "final_marker_iql": 178,
                  "ours_freecf": 279
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 75,
                  "final_marker_iql": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "baseline": 194,
                  "final_marker_iql": 251,
                  "ours_freecf": 607
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 79,
                  "final_marker_iql": 78,
                  "ours_freecf": 80
                },
                "steps": {
                  "baseline": 603,
                  "final_marker_iql": 184,
                  "ours_freecf": 271
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 82,
                  "final_marker_iql": 83,
                  "ours_freecf": 81
                },
                "steps": {
                  "baseline": 82,
                  "final_marker_iql": 524,
                  "ours_freecf": 411
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 84,
                  "final_marker_iql": 85,
                  "ours_freecf": 86
                },
                "steps": {
                  "baseline": 171,
                  "final_marker_iql": 469,
                  "ours_freecf": 210
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 87,
                  "final_marker_iql": 89,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 783,
                  "final_marker_iql": 558,
                  "ours_freecf": 566
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 92,
                  "final_marker_iql": 91,
                  "ours_freecf": 90
                },
                "steps": {
                  "baseline": 377,
                  "final_marker_iql": 545,
                  "ours_freecf": 341
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 95,
                  "final_marker_iql": 93,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 254,
                  "final_marker_iql": 216,
                  "ours_freecf": 335
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 96,
                  "final_marker_iql": 98,
                  "ours_freecf": 97
                },
                "steps": {
                  "baseline": 203,
                  "final_marker_iql": 185,
                  "ours_freecf": 160
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 100,
                  "final_marker_iql": 101,
                  "ours_freecf": 99
                },
                "steps": {
                  "baseline": 451,
                  "final_marker_iql": 156,
                  "ours_freecf": 744
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 102,
                  "final_marker_iql": 104,
                  "ours_freecf": 103
                },
                "steps": {
                  "baseline": 624,
                  "final_marker_iql": 551,
                  "ours_freecf": 49
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 105,
                  "final_marker_iql": 106,
                  "ours_freecf": 107
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 800,
                  "ours_freecf": 631
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 110,
                  "final_marker_iql": 109,
                  "ours_freecf": 108
                },
                "steps": {
                  "baseline": 656,
                  "final_marker_iql": 225,
                  "ours_freecf": 177
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 111,
                  "final_marker_iql": 113,
                  "ours_freecf": 112
                },
                "steps": {
                  "baseline": 291,
                  "final_marker_iql": 601,
                  "ours_freecf": 800
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 114,
                  "final_marker_iql": 115,
                  "ours_freecf": 116
                },
                "steps": {
                  "baseline": 535,
                  "final_marker_iql": 566,
                  "ours_freecf": 541
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 118,
                  "final_marker_iql": 119,
                  "ours_freecf": 117
                },
                "steps": {
                  "baseline": 561,
                  "final_marker_iql": 297,
                  "ours_freecf": 441
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 121,
                  "final_marker_iql": 120,
                  "ours_freecf": 122
                },
                "steps": {
                  "baseline": 178,
                  "final_marker_iql": 800,
                  "ours_freecf": 431
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 125,
                  "final_marker_iql": 124,
                  "ours_freecf": 123
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 326,
                  "ours_freecf": 184
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 127,
                  "final_marker_iql": 126,
                  "ours_freecf": 128
                },
                "steps": {
                  "baseline": 471,
                  "final_marker_iql": 277,
                  "ours_freecf": 800
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 131,
                  "final_marker_iql": 130,
                  "ours_freecf": 129
                },
                "steps": {
                  "baseline": 307,
                  "final_marker_iql": 54,
                  "ours_freecf": 199
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 133,
                  "final_marker_iql": 134,
                  "ours_freecf": 132
                },
                "steps": {
                  "baseline": 541,
                  "final_marker_iql": 314,
                  "ours_freecf": 276
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 137,
                  "final_marker_iql": 136,
                  "ours_freecf": 135
                },
                "steps": {
                  "baseline": 475,
                  "final_marker_iql": 274,
                  "ours_freecf": 334
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 138,
                  "final_marker_iql": 139,
                  "ours_freecf": 140
                },
                "steps": {
                  "baseline": 571,
                  "final_marker_iql": 517,
                  "ours_freecf": 222
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 142,
                  "final_marker_iql": 141,
                  "ours_freecf": 143
                },
                "steps": {
                  "baseline": 412,
                  "final_marker_iql": 290,
                  "ours_freecf": 269
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 144,
                  "final_marker_iql": 146,
                  "ours_freecf": 145
                },
                "steps": {
                  "baseline": 542,
                  "final_marker_iql": 234,
                  "ours_freecf": 260
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 149,
                  "final_marker_iql": 147,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 518,
                  "final_marker_iql": 800,
                  "ours_freecf": 61
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_marker_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/r3_eval_trio_c100k/paired_round_outcomes.csv"
          }
        ],
        "R4": [
          {
            "label": "R4",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 0,
                  "final_marker_iql": 2,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 121,
                  "final_marker_iql": 210,
                  "ours_freecf": 426
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 4,
                  "final_marker_iql": 5,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 242,
                  "final_marker_iql": 151,
                  "ours_freecf": 302
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 6,
                  "final_marker_iql": 8,
                  "ours_freecf": 7
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 173,
                  "ours_freecf": 381
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 11,
                  "final_marker_iql": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 391,
                  "final_marker_iql": 204,
                  "ours_freecf": 524
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 12,
                  "final_marker_iql": 14,
                  "ours_freecf": 13
                },
                "steps": {
                  "baseline": 512,
                  "final_marker_iql": 144,
                  "ours_freecf": 402
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 15,
                  "final_marker_iql": 17,
                  "ours_freecf": 16
                },
                "steps": {
                  "baseline": 212,
                  "final_marker_iql": 141,
                  "ours_freecf": 443
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 20,
                  "final_marker_iql": 18,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 282,
                  "final_marker_iql": 618,
                  "ours_freecf": 542
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 23,
                  "final_marker_iql": 22,
                  "ours_freecf": 21
                },
                "steps": {
                  "baseline": 638,
                  "final_marker_iql": 138,
                  "ours_freecf": 501
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 24,
                  "final_marker_iql": 26,
                  "ours_freecf": 25
                },
                "steps": {
                  "baseline": 769,
                  "final_marker_iql": 404,
                  "ours_freecf": 82
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 29,
                  "final_marker_iql": 28,
                  "ours_freecf": 27
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 800,
                  "ours_freecf": 591
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 30,
                  "final_marker_iql": 32,
                  "ours_freecf": 31
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 800,
                  "ours_freecf": 800
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 35,
                  "final_marker_iql": 34,
                  "ours_freecf": 33
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 800,
                  "ours_freecf": 800
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 37,
                  "final_marker_iql": 38,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 369,
                  "final_marker_iql": 800,
                  "ours_freecf": 480
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 39,
                  "final_marker_iql": 40,
                  "ours_freecf": 41
                },
                "steps": {
                  "baseline": 168,
                  "final_marker_iql": 207,
                  "ours_freecf": 349
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 44,
                  "final_marker_iql": 42,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 601,
                  "ours_freecf": 214
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 47,
                  "final_marker_iql": 45,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 190,
                  "final_marker_iql": 451,
                  "ours_freecf": 334
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 50,
                  "final_marker_iql": 48,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 608,
                  "final_marker_iql": 800,
                  "ours_freecf": 601
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 51,
                  "final_marker_iql": 53,
                  "ours_freecf": 52
                },
                "steps": {
                  "baseline": 180,
                  "final_marker_iql": 800,
                  "ours_freecf": 800
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 56,
                  "final_marker_iql": 55,
                  "ours_freecf": 54
                },
                "steps": {
                  "baseline": 194,
                  "final_marker_iql": 286,
                  "ours_freecf": 195
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 59,
                  "final_marker_iql": 57,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 171,
                  "ours_freecf": 249
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 61,
                  "final_marker_iql": 60,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 247,
                  "final_marker_iql": 318,
                  "ours_freecf": 800
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 63,
                  "final_marker_iql": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 261,
                  "final_marker_iql": 441,
                  "ours_freecf": 318
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "final_marker_iql": 67,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 465,
                  "final_marker_iql": 800,
                  "ours_freecf": 704
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 69,
                  "final_marker_iql": 71,
                  "ours_freecf": 70
                },
                "steps": {
                  "baseline": 290,
                  "final_marker_iql": 198,
                  "ours_freecf": 147
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 73,
                  "final_marker_iql": 74,
                  "ours_freecf": 72
                },
                "steps": {
                  "baseline": 727,
                  "final_marker_iql": 211,
                  "ours_freecf": 201
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 75,
                  "final_marker_iql": 76,
                  "ours_freecf": 77
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 365,
                  "ours_freecf": 800
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 80,
                  "final_marker_iql": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 311,
                  "final_marker_iql": 356,
                  "ours_freecf": 242
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 81,
                  "final_marker_iql": 82,
                  "ours_freecf": 83
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 129,
                  "ours_freecf": 137
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 84,
                  "final_marker_iql": 86,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 170,
                  "final_marker_iql": 219,
                  "ours_freecf": 166
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 89,
                  "final_marker_iql": 87,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 195,
                  "final_marker_iql": 800,
                  "ours_freecf": 800
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 90,
                  "final_marker_iql": 91,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 252,
                  "final_marker_iql": 170,
                  "ours_freecf": 188
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 94,
                  "final_marker_iql": 95,
                  "ours_freecf": 93
                },
                "steps": {
                  "baseline": 222,
                  "final_marker_iql": 259,
                  "ours_freecf": 205
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 97,
                  "final_marker_iql": 96,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 233,
                  "ours_freecf": 800
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 103,
                  "final_marker_iql": 102,
                  "ours_freecf": 104
                },
                "steps": {
                  "baseline": 116,
                  "final_marker_iql": 196,
                  "ours_freecf": 517
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 101,
                  "final_marker_iql": 99,
                  "ours_freecf": 100
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 211,
                  "ours_freecf": 203
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 105,
                  "final_marker_iql": 107,
                  "ours_freecf": 106
                },
                "steps": {
                  "baseline": 183,
                  "final_marker_iql": 149,
                  "ours_freecf": 147
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 110,
                  "final_marker_iql": 109,
                  "ours_freecf": 108
                },
                "steps": {
                  "baseline": 172,
                  "final_marker_iql": 153,
                  "ours_freecf": 783
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 112,
                  "final_marker_iql": 111,
                  "ours_freecf": 113
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 200,
                  "ours_freecf": 328
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 115,
                  "final_marker_iql": 114,
                  "ours_freecf": 116
                },
                "steps": {
                  "baseline": 208,
                  "final_marker_iql": 301,
                  "ours_freecf": 253
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 118,
                  "final_marker_iql": 119,
                  "ours_freecf": 117
                },
                "steps": {
                  "baseline": 141,
                  "final_marker_iql": 436,
                  "ours_freecf": 326
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 122,
                  "final_marker_iql": 121,
                  "ours_freecf": 120
                },
                "steps": {
                  "baseline": 138,
                  "final_marker_iql": 535,
                  "ours_freecf": 164
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 124,
                  "final_marker_iql": 125,
                  "ours_freecf": 123
                },
                "steps": {
                  "baseline": 165,
                  "final_marker_iql": 175,
                  "ours_freecf": 798
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 126,
                  "final_marker_iql": 127,
                  "ours_freecf": 128
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 211,
                  "ours_freecf": 627
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 129,
                  "final_marker_iql": 130,
                  "ours_freecf": 131
                },
                "steps": {
                  "baseline": 700,
                  "final_marker_iql": 239,
                  "ours_freecf": 159
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 133,
                  "final_marker_iql": 132,
                  "ours_freecf": 134
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 90,
                  "ours_freecf": 201
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 135,
                  "final_marker_iql": 136,
                  "ours_freecf": 137
                },
                "steps": {
                  "baseline": 246,
                  "final_marker_iql": 164,
                  "ours_freecf": 800
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 140,
                  "final_marker_iql": 138,
                  "ours_freecf": 139
                },
                "steps": {
                  "baseline": 94,
                  "final_marker_iql": 177,
                  "ours_freecf": 254
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 143,
                  "final_marker_iql": 141,
                  "ours_freecf": 142
                },
                "steps": {
                  "baseline": 179,
                  "final_marker_iql": 101,
                  "ours_freecf": 189
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 145,
                  "final_marker_iql": 146,
                  "ours_freecf": 144
                },
                "steps": {
                  "baseline": 184,
                  "final_marker_iql": 257,
                  "ours_freecf": 282
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 148,
                  "final_marker_iql": 147,
                  "ours_freecf": 149
                },
                "steps": {
                  "baseline": 355,
                  "final_marker_iql": 629,
                  "ours_freecf": 733
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_marker_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/r4_eval/paired_round_outcomes.csv"
          }
        ],
        "R5": [
          {
            "label": "R5",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 0,
                  "final_marker_iql": 2,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 384,
                  "final_marker_iql": 461,
                  "ours_freecf": 546
                },
                "video_start": 0
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 5,
                  "final_marker_iql": 4,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 381,
                  "final_marker_iql": 193,
                  "ours_freecf": 241
                },
                "video_start": 4.55
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 7,
                  "final_marker_iql": 8,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 601,
                  "final_marker_iql": 198,
                  "ours_freecf": 208
                },
                "video_start": 7.725
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 11,
                  "final_marker_iql": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 151,
                  "final_marker_iql": 172,
                  "ours_freecf": 800
                },
                "video_start": 12.733333333333334
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 14,
                  "final_marker_iql": 12,
                  "ours_freecf": 13
                },
                "steps": {
                  "baseline": 246,
                  "final_marker_iql": 165,
                  "ours_freecf": 350
                },
                "video_start": 19.400000000000002
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 15,
                  "final_marker_iql": 17,
                  "ours_freecf": 16
                },
                "steps": {
                  "baseline": 106,
                  "final_marker_iql": 247,
                  "ours_freecf": 234
                },
                "video_start": 22.31666666666667
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 29,
                  "final_marker_iql": 27,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 185,
                  "final_marker_iql": 259,
                  "ours_freecf": 552
                },
                "video_start": 24.375000000000004
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 30,
                  "final_marker_iql": 31,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 460,
                  "final_marker_iql": 161,
                  "ours_freecf": 237
                },
                "video_start": 28.975
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 34,
                  "final_marker_iql": 35,
                  "ours_freecf": 33
                },
                "steps": {
                  "baseline": 99,
                  "final_marker_iql": 193,
                  "ours_freecf": 391
                },
                "video_start": 32.80833333333334
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 19,
                  "final_marker_iql": 20,
                  "ours_freecf": 18
                },
                "steps": {
                  "baseline": 101,
                  "final_marker_iql": 142,
                  "ours_freecf": 431
                },
                "video_start": 36.06666666666667
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 22,
                  "final_marker_iql": 23,
                  "ours_freecf": 21
                },
                "steps": {
                  "baseline": 256,
                  "final_marker_iql": 188,
                  "ours_freecf": 208
                },
                "video_start": 39.65833333333334
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 24,
                  "final_marker_iql": 25,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 80,
                  "final_marker_iql": 221,
                  "ours_freecf": 720
                },
                "video_start": 41.79166666666667
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 37,
                  "final_marker_iql": 38,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 281,
                  "final_marker_iql": 190,
                  "ours_freecf": 313
                },
                "video_start": 47.79166666666667
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 39,
                  "final_marker_iql": 40,
                  "ours_freecf": 41
                },
                "steps": {
                  "baseline": 183,
                  "final_marker_iql": 799,
                  "ours_freecf": 239
                },
                "video_start": 50.400000000000006
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 42,
                  "final_marker_iql": 44,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 578,
                  "final_marker_iql": 203,
                  "ours_freecf": 438
                },
                "video_start": 57.05833333333334
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 47,
                  "final_marker_iql": 46,
                  "ours_freecf": 45
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 800,
                  "ours_freecf": 311
                },
                "video_start": 61.875
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 49,
                  "final_marker_iql": 50,
                  "ours_freecf": 48
                },
                "steps": {
                  "baseline": 652,
                  "final_marker_iql": 494,
                  "ours_freecf": 800
                },
                "video_start": 68.54166666666667
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 51,
                  "final_marker_iql": 52,
                  "ours_freecf": 53
                },
                "steps": {
                  "baseline": 121,
                  "final_marker_iql": 243,
                  "ours_freecf": 324
                },
                "video_start": 75.20833333333334
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 54,
                  "final_marker_iql": 55,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 141,
                  "final_marker_iql": 176,
                  "ours_freecf": 249
                },
                "video_start": 77.90833333333335
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 58,
                  "final_marker_iql": 59,
                  "ours_freecf": 57
                },
                "steps": {
                  "baseline": 370,
                  "final_marker_iql": 414,
                  "ours_freecf": 325
                },
                "video_start": 79.98333333333335
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 62,
                  "final_marker_iql": 61,
                  "ours_freecf": 60
                },
                "steps": {
                  "baseline": 364,
                  "final_marker_iql": 154,
                  "ours_freecf": 161
                },
                "video_start": 83.43333333333335
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 63,
                  "final_marker_iql": 64,
                  "ours_freecf": 65
                },
                "steps": {
                  "baseline": 216,
                  "final_marker_iql": 146,
                  "ours_freecf": 548
                },
                "video_start": 86.46666666666668
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "final_marker_iql": 67,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 241,
                  "final_marker_iql": 616,
                  "ours_freecf": 235
                },
                "video_start": 91.03333333333335
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 69,
                  "final_marker_iql": 71,
                  "ours_freecf": 70
                },
                "steps": {
                  "baseline": 614,
                  "final_marker_iql": 293,
                  "ours_freecf": 426
                },
                "video_start": 96.16666666666669
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 72,
                  "final_marker_iql": 73,
                  "ours_freecf": 74
                },
                "steps": {
                  "baseline": 461,
                  "final_marker_iql": 380,
                  "ours_freecf": 240
                },
                "video_start": 101.28333333333335
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 75,
                  "final_marker_iql": 76,
                  "ours_freecf": 77
                },
                "steps": {
                  "baseline": 84,
                  "final_marker_iql": 85,
                  "ours_freecf": 135
                },
                "video_start": 105.12500000000001
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 80,
                  "final_marker_iql": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 198,
                  "final_marker_iql": 312,
                  "ours_freecf": 470
                },
                "video_start": 106.25000000000001
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 81,
                  "final_marker_iql": 82,
                  "ours_freecf": 83
                },
                "steps": {
                  "baseline": 471,
                  "final_marker_iql": 176,
                  "ours_freecf": 180
                },
                "video_start": 110.16666666666669
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 85,
                  "final_marker_iql": 86,
                  "ours_freecf": 84
                },
                "steps": {
                  "baseline": 702,
                  "final_marker_iql": 167,
                  "ours_freecf": 591
                },
                "video_start": 114.09166666666668
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 89,
                  "final_marker_iql": 88,
                  "ours_freecf": 87
                },
                "steps": {
                  "baseline": 402,
                  "final_marker_iql": 148,
                  "ours_freecf": 170
                },
                "video_start": 119.94166666666668
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 90,
                  "final_marker_iql": 91,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 175,
                  "final_marker_iql": 403,
                  "ours_freecf": 654
                },
                "video_start": 123.29166666666667
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 95,
                  "final_marker_iql": 93,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 243,
                  "final_marker_iql": 710,
                  "ours_freecf": 613
                },
                "video_start": 128.74166666666667
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 98,
                  "final_marker_iql": 96,
                  "ours_freecf": 97
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 445,
                  "ours_freecf": 652
                },
                "video_start": 134.65833333333333
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 100,
                  "final_marker_iql": 101,
                  "ours_freecf": 99
                },
                "steps": {
                  "baseline": 307,
                  "final_marker_iql": 195,
                  "ours_freecf": 200
                },
                "video_start": 141.325
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 102,
                  "final_marker_iql": 104,
                  "ours_freecf": 103
                },
                "steps": {
                  "baseline": 519,
                  "final_marker_iql": 169,
                  "ours_freecf": 271
                },
                "video_start": 143.88333333333333
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 105,
                  "final_marker_iql": 106,
                  "ours_freecf": 107
                },
                "steps": {
                  "baseline": 729,
                  "final_marker_iql": 148,
                  "ours_freecf": 195
                },
                "video_start": 148.20833333333331
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 110,
                  "final_marker_iql": 109,
                  "ours_freecf": 108
                },
                "steps": {
                  "baseline": 539,
                  "final_marker_iql": 187,
                  "ours_freecf": 198
                },
                "video_start": 154.2833333333333
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 111,
                  "final_marker_iql": 113,
                  "ours_freecf": 112
                },
                "steps": {
                  "baseline": 494,
                  "final_marker_iql": 126,
                  "ours_freecf": 252
                },
                "video_start": 158.77499999999998
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 114,
                  "final_marker_iql": 116,
                  "ours_freecf": 115
                },
                "steps": {
                  "baseline": 695,
                  "final_marker_iql": 199,
                  "ours_freecf": 157
                },
                "video_start": 162.89166666666665
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 117,
                  "final_marker_iql": 119,
                  "ours_freecf": 118
                },
                "steps": {
                  "baseline": 476,
                  "final_marker_iql": 196,
                  "ours_freecf": 710
                },
                "video_start": 168.6833333333333
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 121,
                  "final_marker_iql": 122,
                  "ours_freecf": 120
                },
                "steps": {
                  "baseline": 786,
                  "final_marker_iql": 206,
                  "ours_freecf": 408
                },
                "video_start": 174.59999999999997
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 123,
                  "final_marker_iql": 125,
                  "ours_freecf": 124
                },
                "steps": {
                  "baseline": 399,
                  "final_marker_iql": 228,
                  "ours_freecf": 689
                },
                "video_start": 181.14999999999998
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 128,
                  "final_marker_iql": 126,
                  "ours_freecf": 127
                },
                "steps": {
                  "baseline": 105,
                  "final_marker_iql": 206,
                  "ours_freecf": 709
                },
                "video_start": 186.89166666666665
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 131,
                  "final_marker_iql": 130,
                  "ours_freecf": 129
                },
                "steps": {
                  "baseline": 733,
                  "final_marker_iql": 248,
                  "ours_freecf": 245
                },
                "video_start": 192.79999999999998
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 134,
                  "final_marker_iql": 133,
                  "ours_freecf": 132
                },
                "steps": {
                  "baseline": 737,
                  "final_marker_iql": 549,
                  "ours_freecf": 373
                },
                "video_start": 198.9083333333333
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 137,
                  "final_marker_iql": 135,
                  "ours_freecf": 136
                },
                "steps": {
                  "baseline": 730,
                  "final_marker_iql": 480,
                  "ours_freecf": 600
                },
                "video_start": 205.04999999999998
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 139,
                  "final_marker_iql": 140,
                  "ours_freecf": 138
                },
                "steps": {
                  "baseline": 333,
                  "final_marker_iql": 195,
                  "ours_freecf": 215
                },
                "video_start": 211.13333333333333
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 143,
                  "final_marker_iql": 142,
                  "ours_freecf": 141
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 362,
                  "ours_freecf": 552
                },
                "video_start": 213.90833333333333
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "final_marker_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 146,
                  "final_marker_iql": 145,
                  "ours_freecf": 144
                },
                "steps": {
                  "baseline": 80,
                  "final_marker_iql": 621,
                  "ours_freecf": 313
                },
                "video_start": 220.575
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "final_marker_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 149,
                  "final_marker_iql": 147,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 800,
                  "final_marker_iql": 367,
                  "ours_freecf": 303
                },
                "video_start": 225.75
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_marker_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/marker_d2/r5_repeat_eval/paired_round_outcomes.csv",
            "video": {
              "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r5_repeat_eval/marker_d2_r5_repeat_rollouts_side_by_side.mp4",
              "speed": 8,
              "duration": 232.416667
            }
          }
        ]
      }
    },
    {
      "key": "square_d2",
      "title": "Thread nut",
      "points": [
        {
          "round": "R0",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 5,
          "value": 0.1,
          "lo": 0.06510883388685615,
          "hi": 0.15057744062294778,
          "throughput": 0.6864988558352403,
          "throughput_lo": 0.14888152841781874,
          "throughput_hi": 1.2778680746997646
        },
        {
          "round": "R0",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 14,
          "value": 0.28,
          "lo": 0.22129349537259535,
          "hi": 0.3473339556077969,
          "throughput": 1.7781541066892466,
          "throughput_lo": 1.0093886391029239,
          "throughput_hi": 2.6682340992973366
        },
        {
          "round": "R1",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 11,
          "value": 0.22,
          "lo": 0.1672248707525348,
          "hi": 0.28375552140432797,
          "throughput": 1.0897083104017613,
          "throughput_lo": 0.5273424626653892,
          "throughput_hi": 1.7826240040518482
        },
        {
          "round": "R1",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 17,
          "value": 0.34,
          "lo": 0.27673061089460355,
          "hi": 0.409543898909318,
          "throughput": 1.597911227154047,
          "throughput_lo": 0.941619137894161,
          "throughput_hi": 2.3964277257338598
        },
        {
          "round": "R2",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 18,
          "value": 0.36,
          "lo": 0.29547562039839825,
          "hi": 0.4300145756800331,
          "throughput": 1.5248493975903614,
          "throughput_lo": 0.9329587116251312,
          "throughput_hi": 2.216535850528934
        },
        {
          "round": "R2",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 27,
          "value": 0.54,
          "lo": 0.46942167948800917,
          "hi": 0.6090096930610106,
          "throughput": 2.536799248355778,
          "throughput_lo": 1.7643868823695663,
          "throughput_hi": 3.4595239043739436
        },
        {
          "round": "R3",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 100,
          "successes": 49,
          "value": 0.49,
          "lo": 0.4403570032194833,
          "hi": 0.539841016582497,
          "throughput": 1.7154193247238214,
          "throughput_lo": 1.3246007808175064,
          "throughput_hi": 2.1637499758150676
        },
        {
          "round": "R3",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 150,
          "successes": 77,
          "value": 0.5133333333333333,
          "lo": 0.4725699842530527,
          "hi": 0.5539200819721128,
          "throughput": 1.96852630382911,
          "throughput_lo": 1.5895741747645753,
          "throughput_hi": 2.400082295092423
        },
        {
          "round": "R3",
          "arm": "final_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 100,
          "successes": 62,
          "value": 0.62,
          "lo": 0.570499513272254,
          "hi": 0.6671242491039836,
          "throughput": 2.793771591648726,
          "throughput_lo": 2.2405257977552226,
          "throughput_hi": 3.4179968819247573
        },
        {
          "round": "R4",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 28,
          "value": 0.56,
          "lo": 0.48930549842652615,
          "hi": 0.6283415603970033,
          "throughput": 1.7193150030702056,
          "throughput_lo": 1.1721510113498064,
          "throughput_hi": 2.396605103140226
        },
        {
          "round": "R4",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 33,
          "value": 0.66,
          "lo": 0.5904561010906819,
          "hi": 0.7232693891053965,
          "throughput": 2.438824109049105,
          "throughput_lo": 1.7083772000490274,
          "throughput_hi": 3.395044800973507
        },
        {
          "round": "R4",
          "arm": "final_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 41,
          "value": 0.82,
          "lo": 0.7595638144433995,
          "hi": 0.8678871659487574,
          "throughput": 3.5189776845317566,
          "throughput_lo": 2.626029299927555,
          "throughput_hi": 4.6519641626464505
        },
        {
          "round": "R5",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 100,
          "successes": 55,
          "value": 0.55,
          "lo": 0.5,
          "hi": 0.5990099009900991,
          "throughput": 1.4504644416444459,
          "throughput_lo": 1.0840427574690592,
          "throughput_hi": 1.892909247690777
        },
        {
          "round": "R5",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 100,
          "successes": 63,
          "value": 0.63,
          "lo": 0.5806548075266867,
          "hi": 0.6767709350475707,
          "throughput": 1.882720148758135,
          "throughput_lo": 1.458841752203312,
          "throughput_hi": 2.401759096929845
        },
        {
          "round": "R5",
          "arm": "final_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 36,
          "value": 0.72,
          "lo": 0.6526660443922032,
          "hi": 0.7787065046274046,
          "throughput": 2.421162755940816,
          "throughput_lo": 1.6966727260649124,
          "throughput_hi": 3.3938011581286123
        }
      ],
      "rounds": {
        "R0": [
          {
            "label": "R0",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 1,
                  "ours_freecf": 0
                },
                "steps": {
                  "baseline": 49,
                  "ours_freecf": 400
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 2,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 197,
                  "ours_freecf": 118
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 4,
                  "ours_freecf": 5
                },
                "steps": {
                  "baseline": 75,
                  "ours_freecf": 131
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 7,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 79,
                  "ours_freecf": 71
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 8
                },
                "steps": {
                  "baseline": 90,
                  "ours_freecf": 349
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 10,
                  "ours_freecf": 11
                },
                "steps": {
                  "baseline": 128,
                  "ours_freecf": 117
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 13,
                  "ours_freecf": 12
                },
                "steps": {
                  "baseline": 114,
                  "ours_freecf": 126
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 14,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 85,
                  "ours_freecf": 71
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 16,
                  "ours_freecf": 17
                },
                "steps": {
                  "baseline": 54,
                  "ours_freecf": 67
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 18,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 108,
                  "ours_freecf": 46
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 20,
                  "ours_freecf": 21
                },
                "steps": {
                  "baseline": 133,
                  "ours_freecf": 122
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 23,
                  "ours_freecf": 22
                },
                "steps": {
                  "baseline": 85,
                  "ours_freecf": 258
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 25,
                  "ours_freecf": 24
                },
                "steps": {
                  "baseline": 207,
                  "ours_freecf": 93
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 27,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 88,
                  "ours_freecf": 119
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 29,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 73,
                  "ours_freecf": 158
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 31,
                  "ours_freecf": 30
                },
                "steps": {
                  "baseline": 76,
                  "ours_freecf": 131
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 33,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 108,
                  "ours_freecf": 73
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 34,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 195,
                  "ours_freecf": 55
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 37,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 188,
                  "ours_freecf": 83
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 106,
                  "ours_freecf": 127
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 40,
                  "ours_freecf": 41
                },
                "steps": {
                  "baseline": 134,
                  "ours_freecf": 166
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 43,
                  "ours_freecf": 42
                },
                "steps": {
                  "baseline": 141,
                  "ours_freecf": 163
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 45,
                  "ours_freecf": 44
                },
                "steps": {
                  "baseline": 61,
                  "ours_freecf": 115
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 46,
                  "ours_freecf": 47
                },
                "steps": {
                  "baseline": 84,
                  "ours_freecf": 116
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 48,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 195,
                  "ours_freecf": 121
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 50
                },
                "steps": {
                  "baseline": 71,
                  "ours_freecf": 59
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 53,
                  "ours_freecf": 52
                },
                "steps": {
                  "baseline": 72,
                  "ours_freecf": 73
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 54,
                  "ours_freecf": 55
                },
                "steps": {
                  "baseline": 111,
                  "ours_freecf": 127
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 71,
                  "ours_freecf": 67
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 58,
                  "ours_freecf": 59
                },
                "steps": {
                  "baseline": 57,
                  "ours_freecf": 278
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 61
                },
                "steps": {
                  "baseline": 253,
                  "ours_freecf": 66
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 63,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 181,
                  "ours_freecf": 135
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 95,
                  "ours_freecf": 98
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 66,
                  "ours_freecf": 67
                },
                "steps": {
                  "baseline": 129,
                  "ours_freecf": 159
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 295,
                  "ours_freecf": 250
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 70,
                  "ours_freecf": 71
                },
                "steps": {
                  "baseline": 92,
                  "ours_freecf": 122
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 72,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 54,
                  "ours_freecf": 307
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 75,
                  "ours_freecf": 74
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 71
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 76,
                  "ours_freecf": 77
                },
                "steps": {
                  "baseline": 141,
                  "ours_freecf": 136
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 151
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 81,
                  "ours_freecf": 80
                },
                "steps": {
                  "baseline": 120,
                  "ours_freecf": 316
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 83,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 329
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 231,
                  "ours_freecf": 176
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 86,
                  "ours_freecf": 87
                },
                "steps": {
                  "baseline": 76,
                  "ours_freecf": 201
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 89,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 101,
                  "ours_freecf": 55
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 90,
                  "ours_freecf": 91
                },
                "steps": {
                  "baseline": 121,
                  "ours_freecf": 160
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 93,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 86,
                  "ours_freecf": 82
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 94,
                  "ours_freecf": 95
                },
                "steps": {
                  "baseline": 134,
                  "ours_freecf": 76
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 96
                },
                "steps": {
                  "baseline": 62,
                  "ours_freecf": 62
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 99,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 345,
                  "ours_freecf": 134
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r0_baseline_vs_ours_heval_sobol50_checkpoint_75000/paired_round_outcomes.csv"
          }
        ],
        "R1": [
          {
            "label": "R1",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 2,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 142,
                  "ours_freecf": 153
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 4,
                  "ours_freecf": 5
                },
                "steps": {
                  "baseline": 173,
                  "ours_freecf": 161
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 6,
                  "ours_freecf": 7
                },
                "steps": {
                  "baseline": 118,
                  "ours_freecf": 47
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 10,
                  "ours_freecf": 11
                },
                "steps": {
                  "baseline": 126,
                  "ours_freecf": 355
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 13,
                  "ours_freecf": 12
                },
                "steps": {
                  "baseline": 208,
                  "ours_freecf": 133
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 17,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 131,
                  "ours_freecf": 69
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 20,
                  "ours_freecf": 18
                },
                "steps": {
                  "baseline": 54,
                  "ours_freecf": 107
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 23
                },
                "steps": {
                  "baseline": 259,
                  "ours_freecf": 125
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 24,
                  "ours_freecf": 25
                },
                "steps": {
                  "baseline": 151,
                  "ours_freecf": 237
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 29,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 319,
                  "ours_freecf": 145
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 31,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 185,
                  "ours_freecf": 274
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 33,
                  "ours_freecf": 34
                },
                "steps": {
                  "baseline": 85,
                  "ours_freecf": 151
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 119,
                  "ours_freecf": 197
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 39,
                  "ours_freecf": 41
                },
                "steps": {
                  "baseline": 295,
                  "ours_freecf": 60
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 43,
                  "ours_freecf": 42
                },
                "steps": {
                  "baseline": 215,
                  "ours_freecf": 127
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 47,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 120,
                  "ours_freecf": 78
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 49,
                  "ours_freecf": 50
                },
                "steps": {
                  "baseline": 232,
                  "ours_freecf": 304
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 52
                },
                "steps": {
                  "baseline": 54,
                  "ours_freecf": 67
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 54,
                  "ours_freecf": 55
                },
                "steps": {
                  "baseline": 340,
                  "ours_freecf": 62
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 59
                },
                "steps": {
                  "baseline": 130,
                  "ours_freecf": 127
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 120,
                  "ours_freecf": 96
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 65,
                  "ours_freecf": 63
                },
                "steps": {
                  "baseline": 52,
                  "ours_freecf": 221
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 67,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 84,
                  "ours_freecf": 163
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 71,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 153,
                  "ours_freecf": 66
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 74,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 109,
                  "ours_freecf": 116
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 76,
                  "ours_freecf": 77
                },
                "steps": {
                  "baseline": 210,
                  "ours_freecf": 327
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 80,
                  "ours_freecf": 78
                },
                "steps": {
                  "baseline": 56,
                  "ours_freecf": 156
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 81,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 58,
                  "ours_freecf": 61
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 175,
                  "ours_freecf": 404
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 89,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 173,
                  "ours_freecf": 712
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 92,
                  "ours_freecf": 91
                },
                "steps": {
                  "baseline": 53,
                  "ours_freecf": 160
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 95,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 91,
                  "ours_freecf": 222
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 172,
                  "ours_freecf": 694
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 101,
                  "ours_freecf": 100
                },
                "steps": {
                  "baseline": 133,
                  "ours_freecf": 199
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 103,
                  "ours_freecf": 102
                },
                "steps": {
                  "baseline": 296,
                  "ours_freecf": 254
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 105,
                  "ours_freecf": 106
                },
                "steps": {
                  "baseline": 145,
                  "ours_freecf": 168
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 110,
                  "ours_freecf": 109
                },
                "steps": {
                  "baseline": 70,
                  "ours_freecf": 64
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 113,
                  "ours_freecf": 111
                },
                "steps": {
                  "baseline": 119,
                  "ours_freecf": 156
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 116,
                  "ours_freecf": 114
                },
                "steps": {
                  "baseline": 381,
                  "ours_freecf": 181
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 119,
                  "ours_freecf": 118
                },
                "steps": {
                  "baseline": 476,
                  "ours_freecf": 272
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 120,
                  "ours_freecf": 122
                },
                "steps": {
                  "baseline": 361,
                  "ours_freecf": 146
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 125,
                  "ours_freecf": 123
                },
                "steps": {
                  "baseline": 167,
                  "ours_freecf": 169
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 128,
                  "ours_freecf": 127
                },
                "steps": {
                  "baseline": 140,
                  "ours_freecf": 71
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 131,
                  "ours_freecf": 129
                },
                "steps": {
                  "baseline": 271,
                  "ours_freecf": 373
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 132,
                  "ours_freecf": 133
                },
                "steps": {
                  "baseline": 143,
                  "ours_freecf": 158
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 136,
                  "ours_freecf": 137
                },
                "steps": {
                  "baseline": 60,
                  "ours_freecf": 318
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 138,
                  "ours_freecf": 140
                },
                "steps": {
                  "baseline": 182,
                  "ours_freecf": 149
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 142,
                  "ours_freecf": 143
                },
                "steps": {
                  "baseline": 247,
                  "ours_freecf": 142
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 146,
                  "ours_freecf": 145
                },
                "steps": {
                  "baseline": 160,
                  "ours_freecf": 188
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 149,
                  "ours_freecf": 147
                },
                "steps": {
                  "baseline": 772,
                  "ours_freecf": 190
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r1_eval_checkpoint100000/paired_round_outcomes.csv"
          }
        ],
        "R2": [
          {
            "label": "R2",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 1,
                  "ours_freecf": 0
                },
                "steps": {
                  "baseline": 80,
                  "ours_freecf": 78
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 134,
                  "ours_freecf": 117
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 7,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 320,
                  "ours_freecf": 133
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 11
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 153
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 12,
                  "ours_freecf": 13
                },
                "steps": {
                  "baseline": 168,
                  "ours_freecf": 370
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 16,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 123,
                  "ours_freecf": 157
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 20,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 299,
                  "ours_freecf": 400
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 22,
                  "ours_freecf": 23
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 170
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 26,
                  "ours_freecf": 24
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 116
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 28,
                  "ours_freecf": 27
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 108
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 30,
                  "ours_freecf": 31
                },
                "steps": {
                  "baseline": 106,
                  "ours_freecf": 164
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 33,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 163,
                  "ours_freecf": 483
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 525,
                  "ours_freecf": 117
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 40,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 130,
                  "ours_freecf": 220
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 42,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 149,
                  "ours_freecf": 110
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 46,
                  "ours_freecf": 47
                },
                "steps": {
                  "baseline": 215,
                  "ours_freecf": 106
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 49,
                  "ours_freecf": 48
                },
                "steps": {
                  "baseline": 196,
                  "ours_freecf": 69
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 52
                },
                "steps": {
                  "baseline": 138,
                  "ours_freecf": 117
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 55,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 189,
                  "ours_freecf": 65
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 197,
                  "ours_freecf": 167
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 61
                },
                "steps": {
                  "baseline": 151,
                  "ours_freecf": 155
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 65,
                  "ours_freecf": 63
                },
                "steps": {
                  "baseline": 249,
                  "ours_freecf": 159
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 134,
                  "ours_freecf": 133
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 69,
                  "ours_freecf": 71
                },
                "steps": {
                  "baseline": 249,
                  "ours_freecf": 400
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 73,
                  "ours_freecf": 74
                },
                "steps": {
                  "baseline": 116,
                  "ours_freecf": 126
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "baseline": 395,
                  "ours_freecf": 281
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 79,
                  "ours_freecf": 80
                },
                "steps": {
                  "baseline": 99,
                  "ours_freecf": 170
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 83,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 139,
                  "ours_freecf": 145
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 171,
                  "ours_freecf": 104
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 88,
                  "ours_freecf": 89
                },
                "steps": {
                  "baseline": 87,
                  "ours_freecf": 127
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 91,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 400,
                  "ours_freecf": 235
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 95,
                  "ours_freecf": 93
                },
                "steps": {
                  "baseline": 112,
                  "ours_freecf": 229
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 98,
                  "ours_freecf": 96
                },
                "steps": {
                  "baseline": 191,
                  "ours_freecf": 314
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 101,
                  "ours_freecf": 99
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 400
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 103,
                  "ours_freecf": 102
                },
                "steps": {
                  "baseline": 151,
                  "ours_freecf": 86
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 107,
                  "ours_freecf": 105
                },
                "steps": {
                  "baseline": 146,
                  "ours_freecf": 113
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 109,
                  "ours_freecf": 108
                },
                "steps": {
                  "baseline": 173,
                  "ours_freecf": 400
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 113,
                  "ours_freecf": 112
                },
                "steps": {
                  "baseline": 191,
                  "ours_freecf": 170
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 116,
                  "ours_freecf": 115
                },
                "steps": {
                  "baseline": 241,
                  "ours_freecf": 121
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 119,
                  "ours_freecf": 117
                },
                "steps": {
                  "baseline": 271,
                  "ours_freecf": 127
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 121,
                  "ours_freecf": 120
                },
                "steps": {
                  "baseline": 256,
                  "ours_freecf": 231
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 123,
                  "ours_freecf": 124
                },
                "steps": {
                  "baseline": 158,
                  "ours_freecf": 214
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 127,
                  "ours_freecf": 126
                },
                "steps": {
                  "baseline": 262,
                  "ours_freecf": 439
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 131,
                  "ours_freecf": 129
                },
                "steps": {
                  "baseline": 184,
                  "ours_freecf": 137
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 133,
                  "ours_freecf": 132
                },
                "steps": {
                  "baseline": 178,
                  "ours_freecf": 275
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 135,
                  "ours_freecf": 136
                },
                "steps": {
                  "baseline": 462,
                  "ours_freecf": 141
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 140,
                  "ours_freecf": 139
                },
                "steps": {
                  "baseline": 152,
                  "ours_freecf": 156
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 142,
                  "ours_freecf": 143
                },
                "steps": {
                  "baseline": 233,
                  "ours_freecf": 192
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 146,
                  "ours_freecf": 144
                },
                "steps": {
                  "baseline": 203,
                  "ours_freecf": 217
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 149,
                  "ours_freecf": 147
                },
                "steps": {
                  "baseline": 134,
                  "ours_freecf": 162
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r2_eval_checkpoint100000/paired_round_outcomes.csv"
          }
        ],
        "R3": [
          {
            "label": "R3 complete",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 2
                },
                "steps": {
                  "baseline": 158,
                  "ours_freecf": 333
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 4,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 302,
                  "ours_freecf": 200
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 147,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 201,
                  "ours_freecf": 314
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 8,
                  "ours_freecf": 7
                },
                "steps": {
                  "baseline": 176,
                  "ours_freecf": 110
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 11,
                  "ours_freecf": 9
                },
                "steps": {
                  "baseline": 132,
                  "ours_freecf": 116
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 13,
                  "ours_freecf": 12
                },
                "steps": {
                  "baseline": 139,
                  "ours_freecf": 146
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 17,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 161,
                  "ours_freecf": 294
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 18,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 137,
                  "ours_freecf": 370
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 23
                },
                "steps": {
                  "baseline": 165,
                  "ours_freecf": 316
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 25,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 114,
                  "ours_freecf": 163
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 27,
                  "ours_freecf": 29
                },
                "steps": {
                  "baseline": 429,
                  "ours_freecf": 478
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 30,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 121,
                  "ours_freecf": 355
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 34,
                  "ours_freecf": 33
                },
                "steps": {
                  "baseline": 231,
                  "ours_freecf": 152
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 36,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 301,
                  "ours_freecf": 307
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 40,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 184,
                  "ours_freecf": 179
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 44,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 559,
                  "ours_freecf": 247
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 45,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 114,
                  "ours_freecf": 110
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 49,
                  "ours_freecf": 50
                },
                "steps": {
                  "baseline": 133,
                  "ours_freecf": 106
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 53
                },
                "steps": {
                  "baseline": 237,
                  "ours_freecf": 239
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 54,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 155,
                  "ours_freecf": 280
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 80,
                  "ours_freecf": 440
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 61,
                  "ours_freecf": 60
                },
                "steps": {
                  "baseline": 159,
                  "ours_freecf": 137
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 63,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 557,
                  "ours_freecf": 61
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 67,
                  "ours_freecf": 68
                },
                "steps": {
                  "baseline": 614,
                  "ours_freecf": 181
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 69,
                  "ours_freecf": 71
                },
                "steps": {
                  "baseline": 142,
                  "ours_freecf": 220
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 72,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 187,
                  "ours_freecf": 151
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 75
                },
                "steps": {
                  "baseline": 167,
                  "ours_freecf": 121
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 78,
                  "ours_freecf": 80
                },
                "steps": {
                  "baseline": 143,
                  "ours_freecf": 813
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 83,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 177,
                  "ours_freecf": 112
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 86,
                  "ours_freecf": 84
                },
                "steps": {
                  "baseline": 170,
                  "ours_freecf": 300
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 87,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 127,
                  "ours_freecf": 160
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 90,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 140,
                  "ours_freecf": 124
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 93,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 389,
                  "ours_freecf": 388
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 271,
                  "ours_freecf": 154
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 99,
                  "ours_freecf": 101
                },
                "steps": {
                  "baseline": 310,
                  "ours_freecf": 143
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 104,
                  "ours_freecf": 102
                },
                "steps": {
                  "baseline": 327,
                  "ours_freecf": 177
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 107,
                  "ours_freecf": 105
                },
                "steps": {
                  "baseline": 663,
                  "ours_freecf": 512
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 109,
                  "ours_freecf": 110
                },
                "steps": {
                  "baseline": 142,
                  "ours_freecf": 183
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 111,
                  "ours_freecf": 112
                },
                "steps": {
                  "baseline": 136,
                  "ours_freecf": 114
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 115,
                  "ours_freecf": 116
                },
                "steps": {
                  "baseline": 183,
                  "ours_freecf": 306
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 117,
                  "ours_freecf": 118
                },
                "steps": {
                  "baseline": 143,
                  "ours_freecf": 141
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 120,
                  "ours_freecf": 121
                },
                "steps": {
                  "baseline": 359,
                  "ours_freecf": 284
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 125,
                  "ours_freecf": 124
                },
                "steps": {
                  "baseline": 159,
                  "ours_freecf": 312
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 127,
                  "ours_freecf": 126
                },
                "steps": {
                  "baseline": 211,
                  "ours_freecf": 783
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 131,
                  "ours_freecf": 129
                },
                "steps": {
                  "baseline": 304,
                  "ours_freecf": 115
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 134,
                  "ours_freecf": 132
                },
                "steps": {
                  "baseline": 381,
                  "ours_freecf": 108
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 136,
                  "ours_freecf": 135
                },
                "steps": {
                  "baseline": 374,
                  "ours_freecf": 62
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 138,
                  "ours_freecf": 139
                },
                "steps": {
                  "baseline": 150,
                  "ours_freecf": 127
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 142,
                  "ours_freecf": 141
                },
                "steps": {
                  "baseline": 72,
                  "ours_freecf": 778
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 146,
                  "ours_freecf": 145
                },
                "steps": {
                  "baseline": 72,
                  "ours_freecf": 261
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r3_eval_checkpoint100000/paired_round_outcomes.csv"
          },
          {
            "label": "back-50 trio",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 2,
                  "final_iql": 0,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 208,
                  "final_iql": 147,
                  "ours_freecf": 116
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 4,
                  "final_iql": 5,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 342,
                  "final_iql": 203,
                  "ours_freecf": 208
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 7,
                  "final_iql": 6,
                  "ours_freecf": 8
                },
                "steps": {
                  "baseline": 207,
                  "final_iql": 112,
                  "ours_freecf": 113
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 9,
                  "final_iql": 11,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 270,
                  "final_iql": 143,
                  "ours_freecf": 206
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 12,
                  "final_iql": 13,
                  "ours_freecf": 14
                },
                "steps": {
                  "baseline": 110,
                  "final_iql": 149,
                  "ours_freecf": 146
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 15,
                  "final_iql": 16,
                  "ours_freecf": 17
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 132,
                  "ours_freecf": 130
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 19,
                  "final_iql": 18,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 362,
                  "final_iql": 128,
                  "ours_freecf": 197
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 21,
                  "final_iql": 22,
                  "ours_freecf": 23
                },
                "steps": {
                  "baseline": 116,
                  "final_iql": 138,
                  "ours_freecf": 172
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 26,
                  "final_iql": 24,
                  "ours_freecf": 25
                },
                "steps": {
                  "baseline": 170,
                  "final_iql": 396,
                  "ours_freecf": 257
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 27,
                  "final_iql": 29,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 360,
                  "final_iql": 184,
                  "ours_freecf": 179
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 30,
                  "final_iql": 31,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 429,
                  "final_iql": 201,
                  "ours_freecf": 201
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 33,
                  "final_iql": 35,
                  "ours_freecf": 34
                },
                "steps": {
                  "baseline": 264,
                  "final_iql": 134,
                  "ours_freecf": 214
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 38,
                  "final_iql": 36,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 434,
                  "final_iql": 119,
                  "ours_freecf": 136
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 40,
                  "final_iql": 41,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 252,
                  "final_iql": 55,
                  "ours_freecf": 271
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 44,
                  "final_iql": 43,
                  "ours_freecf": 42
                },
                "steps": {
                  "baseline": 436,
                  "final_iql": 251,
                  "ours_freecf": 376
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 46,
                  "final_iql": 45,
                  "ours_freecf": 47
                },
                "steps": {
                  "baseline": 294,
                  "final_iql": 88,
                  "ours_freecf": 297
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 50,
                  "final_iql": 48,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 205,
                  "final_iql": 309,
                  "ours_freecf": 252
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 53,
                  "final_iql": 52,
                  "ours_freecf": 51
                },
                "steps": {
                  "baseline": 268,
                  "final_iql": 124,
                  "ours_freecf": 142
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 54,
                  "final_iql": 55,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 156,
                  "final_iql": 350,
                  "ours_freecf": 72
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 58,
                  "final_iql": 59,
                  "ours_freecf": 57
                },
                "steps": {
                  "baseline": 290,
                  "final_iql": 294,
                  "ours_freecf": 190
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 61,
                  "final_iql": 62,
                  "ours_freecf": 60
                },
                "steps": {
                  "baseline": 154,
                  "final_iql": 146,
                  "ours_freecf": 150
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 63,
                  "final_iql": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 234,
                  "final_iql": 600,
                  "ours_freecf": 275
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 67,
                  "final_iql": 68,
                  "ours_freecf": 66
                },
                "steps": {
                  "baseline": 360,
                  "final_iql": 183,
                  "ours_freecf": 301
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 69,
                  "final_iql": 71,
                  "ours_freecf": 70
                },
                "steps": {
                  "baseline": 443,
                  "final_iql": 214,
                  "ours_freecf": 297
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 72,
                  "final_iql": 74,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 167,
                  "final_iql": 75,
                  "ours_freecf": 162
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 76,
                  "final_iql": 77,
                  "ours_freecf": 75
                },
                "steps": {
                  "baseline": 375,
                  "final_iql": 120,
                  "ours_freecf": 127
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 80,
                  "final_iql": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 150,
                  "final_iql": 199,
                  "ours_freecf": 359
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 81,
                  "final_iql": 83,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 143,
                  "final_iql": 133,
                  "ours_freecf": 132
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 85,
                  "final_iql": 86,
                  "ours_freecf": 84
                },
                "steps": {
                  "baseline": 97,
                  "final_iql": 147,
                  "ours_freecf": 166
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 88,
                  "final_iql": 87,
                  "ours_freecf": 89
                },
                "steps": {
                  "baseline": 446,
                  "final_iql": 303,
                  "ours_freecf": 401
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 92,
                  "final_iql": 90,
                  "ours_freecf": 91
                },
                "steps": {
                  "baseline": 208,
                  "final_iql": 296,
                  "ours_freecf": 216
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 95,
                  "final_iql": 94,
                  "ours_freecf": 93
                },
                "steps": {
                  "baseline": 320,
                  "final_iql": 193,
                  "ours_freecf": 125
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 96,
                  "final_iql": 98,
                  "ours_freecf": 97
                },
                "steps": {
                  "baseline": 212,
                  "final_iql": 57,
                  "ours_freecf": 346
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 101,
                  "final_iql": 99,
                  "ours_freecf": 100
                },
                "steps": {
                  "baseline": 129,
                  "final_iql": 118,
                  "ours_freecf": 106
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 102,
                  "final_iql": 103,
                  "ours_freecf": 104
                },
                "steps": {
                  "baseline": 213,
                  "final_iql": 227,
                  "ours_freecf": 167
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 105,
                  "final_iql": 106,
                  "ours_freecf": 107
                },
                "steps": {
                  "baseline": 121,
                  "final_iql": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 109,
                  "final_iql": 108,
                  "ours_freecf": 110
                },
                "steps": {
                  "baseline": 236,
                  "final_iql": 154,
                  "ours_freecf": 162
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 111,
                  "final_iql": 112,
                  "ours_freecf": 113
                },
                "steps": {
                  "baseline": 167,
                  "final_iql": 269,
                  "ours_freecf": 262
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 115,
                  "final_iql": 114,
                  "ours_freecf": 116
                },
                "steps": {
                  "baseline": 116,
                  "final_iql": 397,
                  "ours_freecf": 72
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 117,
                  "final_iql": 118,
                  "ours_freecf": 119
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 56,
                  "ours_freecf": 61
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 122,
                  "final_iql": 121,
                  "ours_freecf": 120
                },
                "steps": {
                  "baseline": 482,
                  "final_iql": 214,
                  "ours_freecf": 243
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 125,
                  "final_iql": 124,
                  "ours_freecf": 123
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 246,
                  "ours_freecf": 239
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 127,
                  "final_iql": 126,
                  "ours_freecf": 128
                },
                "steps": {
                  "baseline": 142,
                  "final_iql": 121,
                  "ours_freecf": 49
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 129,
                  "final_iql": 130,
                  "ours_freecf": 131
                },
                "steps": {
                  "baseline": 437,
                  "final_iql": 150,
                  "ours_freecf": 162
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 133,
                  "final_iql": 132,
                  "ours_freecf": 134
                },
                "steps": {
                  "baseline": 459,
                  "final_iql": 600,
                  "ours_freecf": 120
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 136,
                  "final_iql": 137,
                  "ours_freecf": 135
                },
                "steps": {
                  "baseline": 430,
                  "final_iql": 144,
                  "ours_freecf": 255
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 138,
                  "final_iql": 139,
                  "ours_freecf": 140
                },
                "steps": {
                  "baseline": 123,
                  "final_iql": 117,
                  "ours_freecf": 120
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 143,
                  "final_iql": 142,
                  "ours_freecf": 141
                },
                "steps": {
                  "baseline": 279,
                  "final_iql": 116,
                  "ours_freecf": 274
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 145,
                  "final_iql": 144,
                  "ours_freecf": 146
                },
                "steps": {
                  "baseline": 373,
                  "final_iql": 291,
                  "ours_freecf": 503
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 148,
                  "final_iql": 149,
                  "ours_freecf": 147
                },
                "steps": {
                  "baseline": 261,
                  "final_iql": 174,
                  "ours_freecf": 227
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/final_trio_eval_back50_c100k/paired_round_outcomes.csv"
          },
          {
            "label": "front-50 IQL",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 0,
                  "ours_freecf": 1
                },
                "steps": {
                  "final_iql": 146,
                  "ours_freecf": 153
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 2,
                  "ours_freecf": 3
                },
                "steps": {
                  "final_iql": 364,
                  "ours_freecf": 191
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 4,
                  "ours_freecf": 5
                },
                "steps": {
                  "final_iql": 111,
                  "ours_freecf": 122
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 6,
                  "ours_freecf": 7
                },
                "steps": {
                  "final_iql": 274,
                  "ours_freecf": 237
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 9,
                  "ours_freecf": 8
                },
                "steps": {
                  "final_iql": 77,
                  "ours_freecf": 54
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 10,
                  "ours_freecf": 11
                },
                "steps": {
                  "final_iql": 129,
                  "ours_freecf": 81
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 12,
                  "ours_freecf": 13
                },
                "steps": {
                  "final_iql": 274,
                  "ours_freecf": 122
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 15,
                  "ours_freecf": 14
                },
                "steps": {
                  "final_iql": 142,
                  "ours_freecf": 397
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 16,
                  "ours_freecf": 17
                },
                "steps": {
                  "final_iql": 461,
                  "ours_freecf": 600
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 19,
                  "ours_freecf": 18
                },
                "steps": {
                  "final_iql": 150,
                  "ours_freecf": 185
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 21,
                  "ours_freecf": 20
                },
                "steps": {
                  "final_iql": 221,
                  "ours_freecf": 391
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 22,
                  "ours_freecf": 23
                },
                "steps": {
                  "final_iql": 164,
                  "ours_freecf": 499
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 25,
                  "ours_freecf": 24
                },
                "steps": {
                  "final_iql": 189,
                  "ours_freecf": 97
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 26,
                  "ours_freecf": 27
                },
                "steps": {
                  "final_iql": 396,
                  "ours_freecf": 379
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 28,
                  "ours_freecf": 29
                },
                "steps": {
                  "final_iql": 199,
                  "ours_freecf": 463
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 30,
                  "ours_freecf": 31
                },
                "steps": {
                  "final_iql": 223,
                  "ours_freecf": 173
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 32,
                  "ours_freecf": 33
                },
                "steps": {
                  "final_iql": 146,
                  "ours_freecf": 135
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 35,
                  "ours_freecf": 34
                },
                "steps": {
                  "final_iql": 190,
                  "ours_freecf": 151
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 36,
                  "ours_freecf": 37
                },
                "steps": {
                  "final_iql": 131,
                  "ours_freecf": 172
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 39,
                  "ours_freecf": 38
                },
                "steps": {
                  "final_iql": 105,
                  "ours_freecf": 205
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 40,
                  "ours_freecf": 41
                },
                "steps": {
                  "final_iql": 188,
                  "ours_freecf": 323
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 42,
                  "ours_freecf": 43
                },
                "steps": {
                  "final_iql": 114,
                  "ours_freecf": 128
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 44,
                  "ours_freecf": 45
                },
                "steps": {
                  "final_iql": 277,
                  "ours_freecf": 179
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 47,
                  "ours_freecf": 46
                },
                "steps": {
                  "final_iql": 182,
                  "ours_freecf": 600
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 49,
                  "ours_freecf": 48
                },
                "steps": {
                  "final_iql": 509,
                  "ours_freecf": 156
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 50,
                  "ours_freecf": 51
                },
                "steps": {
                  "final_iql": 117,
                  "ours_freecf": 244
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 53,
                  "ours_freecf": 52
                },
                "steps": {
                  "final_iql": 123,
                  "ours_freecf": 271
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 55,
                  "ours_freecf": 54
                },
                "steps": {
                  "final_iql": 215,
                  "ours_freecf": 136
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 56,
                  "ours_freecf": 57
                },
                "steps": {
                  "final_iql": 222,
                  "ours_freecf": 457
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 58,
                  "ours_freecf": 59
                },
                "steps": {
                  "final_iql": 146,
                  "ours_freecf": 146
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 61,
                  "ours_freecf": 60
                },
                "steps": {
                  "final_iql": 353,
                  "ours_freecf": 546
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 62,
                  "ours_freecf": 63
                },
                "steps": {
                  "final_iql": 158,
                  "ours_freecf": 158
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "final_iql": 192,
                  "ours_freecf": 249
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 67,
                  "ours_freecf": 66
                },
                "steps": {
                  "final_iql": 187,
                  "ours_freecf": 157
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 68,
                  "ours_freecf": 69
                },
                "steps": {
                  "final_iql": 136,
                  "ours_freecf": 181
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 71,
                  "ours_freecf": 70
                },
                "steps": {
                  "final_iql": 123,
                  "ours_freecf": 245
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 73,
                  "ours_freecf": 72
                },
                "steps": {
                  "final_iql": 147,
                  "ours_freecf": 152
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 74,
                  "ours_freecf": 75
                },
                "steps": {
                  "final_iql": 62,
                  "ours_freecf": 73
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "final_iql": 94,
                  "ours_freecf": 214
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "final_iql": 202,
                  "ours_freecf": 117
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 81,
                  "ours_freecf": 80
                },
                "steps": {
                  "final_iql": 128,
                  "ours_freecf": 291
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 82,
                  "ours_freecf": 83
                },
                "steps": {
                  "final_iql": 112,
                  "ours_freecf": 368
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "final_iql": 542,
                  "ours_freecf": 271
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "final_iql": 86,
                  "ours_freecf": 87
                },
                "steps": {
                  "final_iql": 79,
                  "ours_freecf": 336
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 89,
                  "ours_freecf": 88
                },
                "steps": {
                  "final_iql": 50,
                  "ours_freecf": 53
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 91,
                  "ours_freecf": 90
                },
                "steps": {
                  "final_iql": 72,
                  "ours_freecf": 163
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 93,
                  "ours_freecf": 92
                },
                "steps": {
                  "final_iql": 197,
                  "ours_freecf": 385
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 94,
                  "ours_freecf": 95
                },
                "steps": {
                  "final_iql": 301,
                  "ours_freecf": 268
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "final_iql": 97,
                  "ours_freecf": 96
                },
                "steps": {
                  "final_iql": 58,
                  "ours_freecf": 155
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "final_iql": 99,
                  "ours_freecf": 98
                },
                "steps": {
                  "final_iql": 278,
                  "ours_freecf": 238
                }
              }
            ],
            "columns": [
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/final_dp_vs_iql_eval_c100k/paired_round_outcomes.csv"
          }
        ],
        "R4": [
          {
            "label": "R4",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 3,
                  "final_iql": 1,
                  "ours_freecf": 0
                },
                "steps": {
                  "baseline": 275,
                  "final_iql": 199,
                  "ours_freecf": 404
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 6,
                  "final_iql": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 124,
                  "final_iql": 124,
                  "ours_freecf": 127
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 11,
                  "final_iql": 8,
                  "ours_freecf": 9
                },
                "steps": {
                  "baseline": 421,
                  "final_iql": 367,
                  "ours_freecf": 223
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 14,
                  "final_iql": 13,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 118,
                  "ours_freecf": 413
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 17,
                  "final_iql": 16,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 127,
                  "final_iql": 117,
                  "ours_freecf": 112
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 23,
                  "final_iql": 21,
                  "ours_freecf": 22
                },
                "steps": {
                  "baseline": 171,
                  "final_iql": 234,
                  "ours_freecf": 144
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 25,
                  "final_iql": 27,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 189,
                  "final_iql": 473,
                  "ours_freecf": 160
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 31,
                  "final_iql": 30,
                  "ours_freecf": 29
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 201,
                  "ours_freecf": 501
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 34,
                  "final_iql": 32,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 531,
                  "final_iql": 147,
                  "ours_freecf": 134
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 37,
                  "final_iql": 38,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 361,
                  "final_iql": 125,
                  "ours_freecf": 119
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 41,
                  "final_iql": 42,
                  "ours_freecf": 40
                },
                "steps": {
                  "baseline": 394,
                  "final_iql": 172,
                  "ours_freecf": 221
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 45,
                  "final_iql": 44,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 145,
                  "final_iql": 142,
                  "ours_freecf": 163
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 50,
                  "final_iql": 51,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 166,
                  "final_iql": 122,
                  "ours_freecf": 123
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 55,
                  "final_iql": 53,
                  "ours_freecf": 54
                },
                "steps": {
                  "baseline": 100,
                  "final_iql": 130,
                  "ours_freecf": 132
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 58,
                  "final_iql": 56,
                  "ours_freecf": 57
                },
                "steps": {
                  "baseline": 422,
                  "final_iql": 127,
                  "ours_freecf": 85
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 60,
                  "final_iql": 62,
                  "ours_freecf": 61
                },
                "steps": {
                  "baseline": 194,
                  "final_iql": 123,
                  "ours_freecf": 119
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 65,
                  "final_iql": 67,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 120,
                  "final_iql": 162,
                  "ours_freecf": 159
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 71,
                  "final_iql": 68,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 341,
                  "final_iql": 145,
                  "ours_freecf": 153
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 72,
                  "final_iql": 75,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 295,
                  "final_iql": 600,
                  "ours_freecf": 487
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 79,
                  "final_iql": 78,
                  "ours_freecf": 77
                },
                "steps": {
                  "baseline": 85,
                  "final_iql": 289,
                  "ours_freecf": 405
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 83,
                  "final_iql": 80,
                  "ours_freecf": 81
                },
                "steps": {
                  "baseline": 412,
                  "final_iql": 304,
                  "ours_freecf": 275
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 86,
                  "final_iql": 87,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 273,
                  "final_iql": 149,
                  "ours_freecf": 125
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 90,
                  "final_iql": 91,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 106,
                  "final_iql": 111,
                  "ours_freecf": 59
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 93,
                  "final_iql": 94,
                  "ours_freecf": 95
                },
                "steps": {
                  "baseline": 158,
                  "final_iql": 111,
                  "ours_freecf": 552
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 96,
                  "final_iql": 97,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 377,
                  "final_iql": 136,
                  "ours_freecf": 120
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 101,
                  "final_iql": 100,
                  "ours_freecf": 103
                },
                "steps": {
                  "baseline": 256,
                  "final_iql": 512,
                  "ours_freecf": 340
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 104,
                  "final_iql": 105,
                  "ours_freecf": 107
                },
                "steps": {
                  "baseline": 153,
                  "final_iql": 116,
                  "ours_freecf": 147
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 108,
                  "final_iql": 109,
                  "ours_freecf": 110
                },
                "steps": {
                  "baseline": 121,
                  "final_iql": 207,
                  "ours_freecf": 223
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 113,
                  "final_iql": 112,
                  "ours_freecf": 115
                },
                "steps": {
                  "baseline": 142,
                  "final_iql": 148,
                  "ours_freecf": 137
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 116,
                  "final_iql": 119,
                  "ours_freecf": 118
                },
                "steps": {
                  "baseline": 315,
                  "final_iql": 164,
                  "ours_freecf": 169
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 121,
                  "final_iql": 123,
                  "ours_freecf": 122
                },
                "steps": {
                  "baseline": 573,
                  "final_iql": 258,
                  "ours_freecf": 600
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 126,
                  "final_iql": 124,
                  "ours_freecf": 125
                },
                "steps": {
                  "baseline": 488,
                  "final_iql": 118,
                  "ours_freecf": 129
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 130,
                  "final_iql": 131,
                  "ours_freecf": 128
                },
                "steps": {
                  "baseline": 163,
                  "final_iql": 517,
                  "ours_freecf": 475
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 132,
                  "final_iql": 135,
                  "ours_freecf": 134
                },
                "steps": {
                  "baseline": 516,
                  "final_iql": 118,
                  "ours_freecf": 119
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 137,
                  "final_iql": 139,
                  "ours_freecf": 138
                },
                "steps": {
                  "baseline": 205,
                  "final_iql": 109,
                  "ours_freecf": 120
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 140,
                  "final_iql": 141,
                  "ours_freecf": 142
                },
                "steps": {
                  "baseline": 168,
                  "final_iql": 146,
                  "ours_freecf": 146
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 145,
                  "final_iql": 144,
                  "ours_freecf": 147
                },
                "steps": {
                  "baseline": 567,
                  "final_iql": 169,
                  "ours_freecf": 152
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 149,
                  "final_iql": 150,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 130,
                  "final_iql": 341,
                  "ours_freecf": 205
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 154,
                  "final_iql": 155,
                  "ours_freecf": 152
                },
                "steps": {
                  "baseline": 441,
                  "final_iql": 423,
                  "ours_freecf": 504
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 158,
                  "final_iql": 159,
                  "ours_freecf": 156
                },
                "steps": {
                  "baseline": 157,
                  "final_iql": 154,
                  "ours_freecf": 164
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 162,
                  "final_iql": 163,
                  "ours_freecf": 161
                },
                "steps": {
                  "baseline": 344,
                  "final_iql": 163,
                  "ours_freecf": 130
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 166,
                  "final_iql": 167,
                  "ours_freecf": 165
                },
                "steps": {
                  "baseline": 165,
                  "final_iql": 138,
                  "ours_freecf": 125
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 170,
                  "final_iql": 171,
                  "ours_freecf": 168
                },
                "steps": {
                  "baseline": 322,
                  "final_iql": 134,
                  "ours_freecf": 130
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 174,
                  "final_iql": 175,
                  "ours_freecf": 172
                },
                "steps": {
                  "baseline": 465,
                  "final_iql": 113,
                  "ours_freecf": 521
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 177,
                  "final_iql": 179,
                  "ours_freecf": 178
                },
                "steps": {
                  "baseline": 123,
                  "final_iql": 117,
                  "ours_freecf": 580
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 183,
                  "final_iql": 182,
                  "ours_freecf": 181
                },
                "steps": {
                  "baseline": 244,
                  "final_iql": 600,
                  "ours_freecf": 328
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 187,
                  "final_iql": 185,
                  "ours_freecf": 184
                },
                "steps": {
                  "baseline": 436,
                  "final_iql": 113,
                  "ours_freecf": 111
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 188,
                  "final_iql": 189,
                  "ours_freecf": 190
                },
                "steps": {
                  "baseline": 386,
                  "final_iql": 345,
                  "ours_freecf": 177
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 193,
                  "final_iql": 194,
                  "ours_freecf": 195
                },
                "steps": {
                  "baseline": 190,
                  "final_iql": 146,
                  "ours_freecf": 600
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 198,
                  "final_iql": 197,
                  "ours_freecf": 196
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 189,
                  "ours_freecf": 331
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r4_eval/paired_round_outcomes.csv"
          }
        ],
        "R5": [
          {
            "label": "07-12 trio",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 140,
                  "ours_freecf": 146
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 4,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 346
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 7,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 566,
                  "ours_freecf": 146
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 14,
                  "ours_freecf": 12
                },
                "steps": {
                  "baseline": 291,
                  "ours_freecf": 145
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 15,
                  "ours_freecf": 16
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 138
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 19,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 226,
                  "ours_freecf": 133
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 22
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 176
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 26,
                  "ours_freecf": 25
                },
                "steps": {
                  "baseline": 342,
                  "ours_freecf": 237
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 29,
                  "ours_freecf": 27
                },
                "steps": {
                  "baseline": 189,
                  "ours_freecf": 133
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 31,
                  "ours_freecf": 32
                },
                "steps": {
                  "baseline": 361,
                  "ours_freecf": 153
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 35,
                  "ours_freecf": 34
                },
                "steps": {
                  "baseline": 125,
                  "ours_freecf": 128
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 37
                },
                "steps": {
                  "baseline": 134,
                  "ours_freecf": 167
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 40,
                  "ours_freecf": 41
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 261
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 43,
                  "ours_freecf": 42
                },
                "steps": {
                  "baseline": 321,
                  "ours_freecf": 383
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 45,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 231,
                  "ours_freecf": 507
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 50,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 168,
                  "ours_freecf": 314
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 52,
                  "ours_freecf": 53
                },
                "steps": {
                  "baseline": 256,
                  "ours_freecf": 202
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 56,
                  "ours_freecf": 55
                },
                "steps": {
                  "baseline": 241,
                  "ours_freecf": 600
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 180,
                  "ours_freecf": 263
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 61,
                  "ours_freecf": 60
                },
                "steps": {
                  "baseline": 176,
                  "ours_freecf": 140
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 63,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 451
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 67
                },
                "steps": {
                  "baseline": 143,
                  "ours_freecf": 414
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 69,
                  "ours_freecf": 71
                },
                "steps": {
                  "baseline": 281,
                  "ours_freecf": 164
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 73,
                  "ours_freecf": 72
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 529
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 75
                },
                "steps": {
                  "baseline": 598,
                  "ours_freecf": 173
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 225,
                  "ours_freecf": 375
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 81,
                  "ours_freecf": 83
                },
                "steps": {
                  "baseline": 389,
                  "ours_freecf": 136
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 86
                },
                "steps": {
                  "baseline": 127,
                  "ours_freecf": 142
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 87,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 409,
                  "ours_freecf": 139
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 91,
                  "ours_freecf": 92
                },
                "steps": {
                  "baseline": 527,
                  "ours_freecf": 154
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 95,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 327,
                  "ours_freecf": 163
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 96,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 481,
                  "ours_freecf": 133
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 101,
                  "ours_freecf": 100
                },
                "steps": {
                  "baseline": 196,
                  "ours_freecf": 167
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 103,
                  "ours_freecf": 102
                },
                "steps": {
                  "baseline": 152,
                  "ours_freecf": 124
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 105,
                  "ours_freecf": 106
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 325
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 108,
                  "ours_freecf": 109
                },
                "steps": {
                  "baseline": 158,
                  "ours_freecf": 142
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 111,
                  "ours_freecf": 112
                },
                "steps": {
                  "baseline": 141,
                  "ours_freecf": 245
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 116,
                  "ours_freecf": 115
                },
                "steps": {
                  "baseline": 156,
                  "ours_freecf": 116
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 119,
                  "ours_freecf": 117
                },
                "steps": {
                  "baseline": 214,
                  "ours_freecf": 331
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 121,
                  "ours_freecf": 122
                },
                "steps": {
                  "baseline": 137,
                  "ours_freecf": 108
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 123,
                  "ours_freecf": 125
                },
                "steps": {
                  "baseline": 161,
                  "ours_freecf": 120
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 127,
                  "ours_freecf": 128
                },
                "steps": {
                  "baseline": 124,
                  "ours_freecf": 114
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 131,
                  "ours_freecf": 130
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 133,
                  "ours_freecf": 134
                },
                "steps": {
                  "baseline": 431,
                  "ours_freecf": 600
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 136,
                  "ours_freecf": 137
                },
                "steps": {
                  "baseline": 111,
                  "ours_freecf": 131
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 139,
                  "ours_freecf": 140
                },
                "steps": {
                  "baseline": 262,
                  "ours_freecf": 240
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 142,
                  "ours_freecf": 141
                },
                "steps": {
                  "baseline": 332,
                  "ours_freecf": 200
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 145,
                  "ours_freecf": 144
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 514
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 149,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 150,
                  "ours_freecf": 600
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r5_eval/paired_round_outcomes.csv"
          },
          {
            "label": "07-09 2-arm",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 1
                },
                "steps": {
                  "baseline": 152,
                  "ours_freecf": 277
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 2,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 455,
                  "ours_freecf": 466
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 5,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 146,
                  "ours_freecf": 600
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 6,
                  "ours_freecf": 7
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 457
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 8,
                  "ours_freecf": 9
                },
                "steps": {
                  "baseline": 249,
                  "ours_freecf": 284
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 10,
                  "ours_freecf": 11
                },
                "steps": {
                  "baseline": 116,
                  "ours_freecf": 140
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 12,
                  "ours_freecf": 13
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 14,
                  "ours_freecf": 15
                },
                "steps": {
                  "baseline": 464,
                  "ours_freecf": 600
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 16,
                  "ours_freecf": 17
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 18,
                  "ours_freecf": 19
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 152
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 20
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 22,
                  "ours_freecf": 23
                },
                "steps": {
                  "baseline": 179,
                  "ours_freecf": 138
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 25,
                  "ours_freecf": 24
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 154
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 26,
                  "ours_freecf": 27
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 572
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 28,
                  "ours_freecf": 29
                },
                "steps": {
                  "baseline": 148,
                  "ours_freecf": 118
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 30,
                  "ours_freecf": 31
                },
                "steps": {
                  "baseline": 157,
                  "ours_freecf": 369
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 32,
                  "ours_freecf": 33
                },
                "steps": {
                  "baseline": 147,
                  "ours_freecf": 164
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 35,
                  "ours_freecf": 34
                },
                "steps": {
                  "baseline": 571,
                  "ours_freecf": 283
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 37,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 166,
                  "ours_freecf": 463
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 38,
                  "ours_freecf": 39
                },
                "steps": {
                  "baseline": 161,
                  "ours_freecf": 143
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 41,
                  "ours_freecf": 40
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 513
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 42,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 291
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 45,
                  "ours_freecf": 44
                },
                "steps": {
                  "baseline": 123,
                  "ours_freecf": 215
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 47,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 159
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 48,
                  "ours_freecf": 49
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 50
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 152
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 53,
                  "ours_freecf": 52
                },
                "steps": {
                  "baseline": 358,
                  "ours_freecf": 600
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 55,
                  "ours_freecf": 54
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 157
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 57,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 194,
                  "ours_freecf": 330
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 59,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 107,
                  "ours_freecf": 294
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 61
                },
                "steps": {
                  "baseline": 197,
                  "ours_freecf": 600
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 63,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 281,
                  "ours_freecf": 315
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 64,
                  "ours_freecf": 65
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 177
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 66,
                  "ours_freecf": 67
                },
                "steps": {
                  "baseline": 242,
                  "ours_freecf": 600
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 176
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 71,
                  "ours_freecf": 70
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 72,
                  "ours_freecf": 73
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 159
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 74,
                  "ours_freecf": 75
                },
                "steps": {
                  "baseline": 123,
                  "ours_freecf": 133
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "baseline": 115,
                  "ours_freecf": 117
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 78,
                  "ours_freecf": 79
                },
                "steps": {
                  "baseline": 187,
                  "ours_freecf": 600
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 80,
                  "ours_freecf": 81
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 600
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 83,
                  "ours_freecf": 82
                },
                "steps": {
                  "baseline": 146,
                  "ours_freecf": 140
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 84,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 140,
                  "ours_freecf": 600
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 86,
                  "ours_freecf": 87
                },
                "steps": {
                  "baseline": 600,
                  "ours_freecf": 161
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 89,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 255,
                  "ours_freecf": 125
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 91,
                  "ours_freecf": 90
                },
                "steps": {
                  "baseline": 123,
                  "ours_freecf": 128
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 92,
                  "ours_freecf": 93
                },
                "steps": {
                  "baseline": 240,
                  "ours_freecf": 521
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 95,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 281,
                  "ours_freecf": 257
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 96
                },
                "steps": {
                  "baseline": 534,
                  "ours_freecf": 460
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 98,
                  "ours_freecf": 99
                },
                "steps": {
                  "baseline": 189,
                  "ours_freecf": 188
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r5_2arm_eval/paired_round_outcomes.csv"
          },
          {
            "label": "07-19 cand3",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 2
                },
                "steps": {
                  "final_iql": 122
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 4
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 6
                },
                "steps": {
                  "final_iql": 176
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 9
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 13
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 16
                },
                "steps": {
                  "final_iql": 124
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 19
                },
                "steps": {
                  "final_iql": 346
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 22
                },
                "steps": {
                  "final_iql": 227
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 24
                },
                "steps": {
                  "final_iql": 291
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 28
                },
                "steps": {
                  "final_iql": 139
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 30
                },
                "steps": {
                  "final_iql": 149
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 34
                },
                "steps": {
                  "final_iql": 150
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 36
                },
                "steps": {
                  "final_iql": 133
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 40
                },
                "steps": {
                  "final_iql": 189
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 44
                },
                "steps": {
                  "final_iql": 116
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 46
                },
                "steps": {
                  "final_iql": 141
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 48
                },
                "steps": {
                  "final_iql": 143
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 52
                },
                "steps": {
                  "final_iql": 136
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 56
                },
                "steps": {
                  "final_iql": 471
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 59
                },
                "steps": {
                  "final_iql": 150
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 60
                },
                "steps": {
                  "final_iql": 119
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 64
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 68
                },
                "steps": {
                  "final_iql": 136
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "final_iql": "timeout"
                },
                "episodes": {
                  "final_iql": 71
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 74
                },
                "steps": {
                  "final_iql": 68
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "final_iql": "timeout"
                },
                "episodes": {
                  "final_iql": 76
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 79
                },
                "steps": {
                  "final_iql": 117
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 83
                },
                "steps": {
                  "final_iql": 215
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 85
                },
                "steps": {
                  "final_iql": 213
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 87
                },
                "steps": {
                  "final_iql": 203
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 90
                },
                "steps": {
                  "final_iql": 472
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 95
                },
                "steps": {
                  "final_iql": 176
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 96
                },
                "steps": {
                  "final_iql": 371
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 99
                },
                "steps": {
                  "final_iql": 124
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 103
                },
                "steps": {
                  "final_iql": 139
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 107
                },
                "steps": {
                  "final_iql": 172
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 109
                },
                "steps": {
                  "final_iql": 106
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 112
                },
                "steps": {
                  "final_iql": 119
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 114
                },
                "steps": {
                  "final_iql": 117
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 119
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 121
                },
                "steps": {
                  "final_iql": 124
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 123
                },
                "steps": {
                  "final_iql": 130
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 128
                },
                "steps": {
                  "final_iql": 126
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 131
                },
                "steps": {
                  "final_iql": 475
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 132
                },
                "steps": {
                  "final_iql": 143
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "final_iql": "success"
                },
                "episodes": {
                  "final_iql": 135
                },
                "steps": {
                  "final_iql": 123
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "final_iql": "timeout"
                },
                "episodes": {
                  "final_iql": 139
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "final_iql": "failure"
                },
                "episodes": {
                  "final_iql": 143
                },
                "steps": {
                  "final_iql": 191
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "final_iql": "timeout"
                },
                "episodes": {
                  "final_iql": 146
                },
                "steps": {
                  "final_iql": 600
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "final_iql": "timeout"
                },
                "episodes": {
                  "final_iql": 148
                },
                "steps": {
                  "final_iql": 600
                }
              }
            ],
            "columns": [
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              }
            ],
            "source": "paper/data/paper_context_2026-08-24/01b/square_d2/r5_updated_eval/paired_round_outcomes.csv"
          }
        ]
      }
    },
    {
      "key": "routing_d2",
      "title": "Route cable",
      "points": [
        {
          "round": "R0",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 1,
          "value": 0.02,
          "lo": 0.0076656146933148685,
          "hi": 0.05115791471844984,
          "throughput": 0.06821282401091405,
          "throughput_lo": 0.0,
          "throughput_hi": 0.22240527182866557
        },
        {
          "round": "R0",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 3,
          "value": 0.06,
          "lo": 0.03427173437659758,
          "hi": 0.10298316758418671,
          "throughput": 0.17918768250597295,
          "throughput_lo": 0.0,
          "throughput_hi": 0.4110261593384814
        },
        {
          "round": "R1",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 4,
          "value": 0.08,
          "lo": 0.04936425960470782,
          "hi": 0.1271063286305863,
          "throughput": 0.20812857720992078,
          "throughput_lo": 0.04843338217806079,
          "throughput_hi": 0.42061603072409115
        },
        {
          "round": "R1",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 3,
          "value": 0.06,
          "lo": 0.03427173437659758,
          "hi": 0.10298316758418671,
          "throughput": 0.15007503751875936,
          "throughput_lo": 0.0,
          "throughput_hi": 0.3259025962478214
        },
        {
          "round": "R2",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 7,
          "value": 0.14,
          "lo": 0.09796084695863175,
          "hi": 0.19615680010019185,
          "throughput": 0.3591585428424833,
          "throughput_lo": 0.13923644607351024,
          "throughput_hi": 0.6174807074063852
        },
        {
          "round": "R2",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 5,
          "value": 0.1,
          "lo": 0.06510883388685615,
          "hi": 0.15057744062294778,
          "throughput": 0.2319707201402134,
          "throughput_lo": 0.04755331593396516,
          "throughput_hi": 0.46081271021934916
        },
        {
          "round": "R3",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 8,
          "value": 0.16,
          "lo": 0.11490047536296438,
          "hi": 0.218432857970369,
          "throughput": 0.34134547006115773,
          "throughput_lo": 0.1309460736223765,
          "throughput_hi": 0.5966349787442236
        },
        {
          "round": "R3",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 11,
          "value": 0.22,
          "lo": 0.1672248707525348,
          "hi": 0.28375552140432797,
          "throughput": 0.5234771573604061,
          "throughput_lo": 0.2589912534129972,
          "throughput_hi": 0.8390184774327346
        },
        {
          "round": "R3",
          "arm": "final_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 10,
          "value": 0.2,
          "lo": 0.1495631113084507,
          "hi": 0.26220159457390224,
          "throughput": 0.5014765699002618,
          "throughput_lo": 0.22828053412355254,
          "throughput_hi": 0.8513166588320018
        },
        {
          "round": "R4",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 5,
          "value": 0.1,
          "lo": 0.06510883388685615,
          "hi": 0.15057744062294778,
          "throughput": 0.18423746161719548,
          "throughput_lo": 0.037819853533739484,
          "throughput_hi": 0.3510998542805877
        },
        {
          "round": "R4",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 16,
          "value": 0.32,
          "lo": 0.2581144026760303,
          "hi": 0.3889444208533815,
          "throughput": 0.6362953470902744,
          "throughput_lo": 0.36898599870064014,
          "throughput_hi": 0.9460770390832697
        },
        {
          "round": "R4",
          "arm": "final_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 16,
          "value": 0.32,
          "lo": 0.2581144026760303,
          "hi": 0.3889444208533815,
          "throughput": 0.7102342786683107,
          "throughput_lo": 0.40157706623326767,
          "throughput_hi": 1.0884084615585556
        },
        {
          "round": "R5",
          "arm": "baseline",
          "label": "HG-DAgger",
          "color": "#888888",
          "n": 50,
          "successes": 10,
          "value": 0.2,
          "lo": 0.1495631113084507,
          "hi": 0.26220159457390224,
          "throughput": 0.357838654526659,
          "throughput_lo": 0.1666717596878912,
          "throughput_hi": 0.5871146706554375
        },
        {
          "round": "R5",
          "arm": "ours_freecf",
          "label": "HG-DAgger + Mulligan",
          "color": "#17becf",
          "n": 50,
          "successes": 14,
          "value": 0.28,
          "lo": 0.22129349537259535,
          "hi": 0.3473339556077969,
          "throughput": 0.6198042205715972,
          "throughput_lo": 0.34328093151140177,
          "throughput_hi": 0.9595920556208903
        },
        {
          "round": "R5",
          "arm": "final_iql",
          "label": "HiL-IDQL + Mulligan",
          "color": "#9467bd",
          "n": 50,
          "successes": 17,
          "value": 0.34,
          "lo": 0.27673061089460355,
          "hi": 0.409543898909318,
          "throughput": 0.8482563619227145,
          "throughput_lo": 0.5257457863134318,
          "throughput_hi": 1.2116969142118585
        }
      ],
      "rounds": {
        "R0": [
          {
            "label": "R0",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 1,
                  "ours_freecf": 3
                },
                "steps": {
                  "baseline": 125,
                  "ours_freecf": 97
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 17,
                  "ours_freecf": 11
                },
                "steps": {
                  "baseline": 110,
                  "ours_freecf": 329
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 19,
                  "ours_freecf": 24
                },
                "steps": {
                  "baseline": 598,
                  "ours_freecf": 341
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 27,
                  "ours_freecf": 31
                },
                "steps": {
                  "baseline": 418,
                  "ours_freecf": 334
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 39,
                  "ours_freecf": 36
                },
                "steps": {
                  "baseline": 105,
                  "ours_freecf": 175
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 50,
                  "ours_freecf": 47
                },
                "steps": {
                  "baseline": 102,
                  "ours_freecf": 181
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 59,
                  "ours_freecf": 56
                },
                "steps": {
                  "baseline": 249,
                  "ours_freecf": 163
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 68,
                  "ours_freecf": 70
                },
                "steps": {
                  "baseline": 251,
                  "ours_freecf": 278
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 80,
                  "ours_freecf": 74
                },
                "steps": {
                  "baseline": 83,
                  "ours_freecf": 362
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 82,
                  "ours_freecf": 85
                },
                "steps": {
                  "baseline": 114,
                  "ours_freecf": 114
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 92,
                  "ours_freecf": 96
                },
                "steps": {
                  "baseline": 133,
                  "ours_freecf": 140
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 100,
                  "ours_freecf": 107
                },
                "steps": {
                  "baseline": 501,
                  "ours_freecf": 120
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 182,
                  "ours_freecf": 184
                },
                "steps": {
                  "baseline": 223,
                  "ours_freecf": 191
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 195,
                  "ours_freecf": 205
                },
                "steps": {
                  "baseline": 130,
                  "ours_freecf": 733
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 211,
                  "ours_freecf": 218
                },
                "steps": {
                  "baseline": 74,
                  "ours_freecf": 87
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 232,
                  "ours_freecf": 234
                },
                "steps": {
                  "baseline": 105,
                  "ours_freecf": 82
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 243,
                  "ours_freecf": 240
                },
                "steps": {
                  "baseline": 130,
                  "ours_freecf": 175
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 268,
                  "ours_freecf": 264
                },
                "steps": {
                  "baseline": 127,
                  "ours_freecf": 302
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 275,
                  "ours_freecf": 277
                },
                "steps": {
                  "baseline": 497,
                  "ours_freecf": 115
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 290,
                  "ours_freecf": 295
                },
                "steps": {
                  "baseline": 421,
                  "ours_freecf": 724
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 308,
                  "ours_freecf": 306
                },
                "steps": {
                  "baseline": 222,
                  "ours_freecf": 199
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 329,
                  "ours_freecf": 319
                },
                "steps": {
                  "baseline": 677,
                  "ours_freecf": 155
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 333,
                  "ours_freecf": 338
                },
                "steps": {
                  "baseline": 79,
                  "ours_freecf": 104
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 346,
                  "ours_freecf": 357
                },
                "steps": {
                  "baseline": 287,
                  "ours_freecf": 135
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 362,
                  "ours_freecf": 370
                },
                "steps": {
                  "baseline": 256,
                  "ours_freecf": 518
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 388,
                  "ours_freecf": 375
                },
                "steps": {
                  "baseline": 199,
                  "ours_freecf": 247
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 399,
                  "ours_freecf": 390
                },
                "steps": {
                  "baseline": 294,
                  "ours_freecf": 159
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 418,
                  "ours_freecf": 405
                },
                "steps": {
                  "baseline": 188,
                  "ours_freecf": 328
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 420,
                  "ours_freecf": 432
                },
                "steps": {
                  "baseline": 130,
                  "ours_freecf": 402
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 441,
                  "ours_freecf": 449
                },
                "steps": {
                  "baseline": 219,
                  "ours_freecf": 192
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 459,
                  "ours_freecf": 453
                },
                "steps": {
                  "baseline": 322,
                  "ours_freecf": 312
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 466,
                  "ours_freecf": 478
                },
                "steps": {
                  "baseline": 140,
                  "ours_freecf": 158
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 484,
                  "ours_freecf": 482
                },
                "steps": {
                  "baseline": 219,
                  "ours_freecf": 742
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 496,
                  "ours_freecf": 497
                },
                "steps": {
                  "baseline": 601,
                  "ours_freecf": 85
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 511,
                  "ours_freecf": 512
                },
                "steps": {
                  "baseline": 315,
                  "ours_freecf": 164
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 536,
                  "ours_freecf": 531
                },
                "steps": {
                  "baseline": 205,
                  "ours_freecf": 240
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 552,
                  "ours_freecf": 549
                },
                "steps": {
                  "baseline": 391,
                  "ours_freecf": 525
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 561,
                  "ours_freecf": 569
                },
                "steps": {
                  "baseline": 241,
                  "ours_freecf": 162
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 581,
                  "ours_freecf": 583
                },
                "steps": {
                  "baseline": 499,
                  "ours_freecf": 759
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 597,
                  "ours_freecf": 591
                },
                "steps": {
                  "baseline": 202,
                  "ours_freecf": 157
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 612,
                  "ours_freecf": 603
                },
                "steps": {
                  "baseline": 487,
                  "ours_freecf": 270
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 625,
                  "ours_freecf": 627
                },
                "steps": {
                  "baseline": 281,
                  "ours_freecf": 269
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 634,
                  "ours_freecf": 638
                },
                "steps": {
                  "baseline": 209,
                  "ours_freecf": 196
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 657,
                  "ours_freecf": 655
                },
                "steps": {
                  "baseline": 192,
                  "ours_freecf": 185
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 666,
                  "ours_freecf": 662
                },
                "steps": {
                  "baseline": 354,
                  "ours_freecf": 809
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 676,
                  "ours_freecf": 687
                },
                "steps": {
                  "baseline": 92,
                  "ours_freecf": 514
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 704,
                  "ours_freecf": 702
                },
                "steps": {
                  "baseline": 231,
                  "ours_freecf": 324
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 717,
                  "ours_freecf": 716
                },
                "steps": {
                  "baseline": 517,
                  "ours_freecf": 794
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 732,
                  "ours_freecf": 731
                },
                "steps": {
                  "baseline": 120,
                  "ours_freecf": 330
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 743,
                  "ours_freecf": 749
                },
                "steps": {
                  "baseline": 529,
                  "ours_freecf": 591
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/routing_d2/2026-09-09/paired_round_outcomes.csv"
          }
        ],
        "R1": [
          {
            "label": "R1",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 0,
                  "ours_freecf": 6
                },
                "steps": {
                  "baseline": 463,
                  "ours_freecf": 155
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 9,
                  "ours_freecf": 10
                },
                "steps": {
                  "baseline": 167,
                  "ours_freecf": 363
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 21,
                  "ours_freecf": 26
                },
                "steps": {
                  "baseline": 796,
                  "ours_freecf": 207
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 30,
                  "ours_freecf": 28
                },
                "steps": {
                  "baseline": 807,
                  "ours_freecf": 205
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 41,
                  "ours_freecf": 40
                },
                "steps": {
                  "baseline": 151,
                  "ours_freecf": 321
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 51,
                  "ours_freecf": 48
                },
                "steps": {
                  "baseline": 126,
                  "ours_freecf": 734
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 60,
                  "ours_freecf": 57
                },
                "steps": {
                  "baseline": 353,
                  "ours_freecf": 259
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 65,
                  "ours_freecf": 64
                },
                "steps": {
                  "baseline": 417,
                  "ours_freecf": 165
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 77,
                  "ours_freecf": 76
                },
                "steps": {
                  "baseline": 325,
                  "ours_freecf": 288
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 81,
                  "ours_freecf": 84
                },
                "steps": {
                  "baseline": 148,
                  "ours_freecf": 464
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 91,
                  "ours_freecf": 94
                },
                "steps": {
                  "baseline": 176,
                  "ours_freecf": 384
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 105,
                  "ours_freecf": 99
                },
                "steps": {
                  "baseline": 287,
                  "ours_freecf": 371
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 193,
                  "ours_freecf": 189
                },
                "steps": {
                  "baseline": 235,
                  "ours_freecf": 352
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 203,
                  "ours_freecf": 197
                },
                "steps": {
                  "baseline": 207,
                  "ours_freecf": 338
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 223,
                  "ours_freecf": 217
                },
                "steps": {
                  "baseline": 437,
                  "ours_freecf": 94
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 235,
                  "ours_freecf": 225
                },
                "steps": {
                  "baseline": 427,
                  "ours_freecf": 48
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 248,
                  "ours_freecf": 244
                },
                "steps": {
                  "baseline": 332,
                  "ours_freecf": 139
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 261,
                  "ours_freecf": 259
                },
                "steps": {
                  "baseline": 356,
                  "ours_freecf": 669
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 273,
                  "ours_freecf": 272
                },
                "steps": {
                  "baseline": 145,
                  "ours_freecf": 327
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 288,
                  "ours_freecf": 289
                },
                "steps": {
                  "baseline": 205,
                  "ours_freecf": 182
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 301,
                  "ours_freecf": 312
                },
                "steps": {
                  "baseline": 246,
                  "ours_freecf": 313
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 318,
                  "ours_freecf": 320
                },
                "steps": {
                  "baseline": 459,
                  "ours_freecf": 459
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 335,
                  "ours_freecf": 330
                },
                "steps": {
                  "baseline": 198,
                  "ours_freecf": 208
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 351,
                  "ours_freecf": 345
                },
                "steps": {
                  "baseline": 119,
                  "ours_freecf": 109
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 366,
                  "ours_freecf": 373
                },
                "steps": {
                  "baseline": 380,
                  "ours_freecf": 378
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 376,
                  "ours_freecf": 379
                },
                "steps": {
                  "baseline": 319,
                  "ours_freecf": 449
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 394,
                  "ours_freecf": 402
                },
                "steps": {
                  "baseline": 217,
                  "ours_freecf": 186
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 414,
                  "ours_freecf": 406
                },
                "steps": {
                  "baseline": 259,
                  "ours_freecf": 597
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 433,
                  "ours_freecf": 427
                },
                "steps": {
                  "baseline": 440,
                  "ours_freecf": 440
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 435,
                  "ours_freecf": 440
                },
                "steps": {
                  "baseline": 850,
                  "ours_freecf": 574
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 452,
                  "ours_freecf": 458
                },
                "steps": {
                  "baseline": 808,
                  "ours_freecf": 850
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 475,
                  "ours_freecf": 467
                },
                "steps": {
                  "baseline": 135,
                  "ours_freecf": 127
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 492,
                  "ours_freecf": 483
                },
                "steps": {
                  "baseline": 124,
                  "ours_freecf": 331
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 499,
                  "ours_freecf": 508
                },
                "steps": {
                  "baseline": 303,
                  "ours_freecf": 741
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 518,
                  "ours_freecf": 523
                },
                "steps": {
                  "baseline": 139,
                  "ours_freecf": 323
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 539,
                  "ours_freecf": 537
                },
                "steps": {
                  "baseline": 310,
                  "ours_freecf": 729
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 546,
                  "ours_freecf": 544
                },
                "steps": {
                  "baseline": 227,
                  "ours_freecf": 454
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 559,
                  "ours_freecf": 562
                },
                "steps": {
                  "baseline": 537,
                  "ours_freecf": 486
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 575,
                  "ours_freecf": 579
                },
                "steps": {
                  "baseline": 650,
                  "ours_freecf": 468
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 596,
                  "ours_freecf": 588
                },
                "steps": {
                  "baseline": 314,
                  "ours_freecf": 109
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 605,
                  "ours_freecf": 607
                },
                "steps": {
                  "baseline": 458,
                  "ours_freecf": 123
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 622,
                  "ours_freecf": 618
                },
                "steps": {
                  "baseline": 185,
                  "ours_freecf": 258
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 632,
                  "ours_freecf": 633
                },
                "steps": {
                  "baseline": 277,
                  "ours_freecf": 262
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 659,
                  "ours_freecf": 651
                },
                "steps": {
                  "baseline": 190,
                  "ours_freecf": 548
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 663,
                  "ours_freecf": 672
                },
                "steps": {
                  "baseline": 407,
                  "ours_freecf": 336
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 675,
                  "ours_freecf": 678
                },
                "steps": {
                  "baseline": 387,
                  "ours_freecf": 538
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 700,
                  "ours_freecf": 698
                },
                "steps": {
                  "baseline": 135,
                  "ours_freecf": 403
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 718,
                  "ours_freecf": 719
                },
                "steps": {
                  "baseline": 591,
                  "ours_freecf": 262
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 724,
                  "ours_freecf": 726
                },
                "steps": {
                  "baseline": 850,
                  "ours_freecf": 213
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 747,
                  "ours_freecf": 742
                },
                "steps": {
                  "baseline": 223,
                  "ours_freecf": 652
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/routing_d2/2026-09-09/paired_round_outcomes.csv"
          }
        ],
        "R2": [
          {
            "label": "R2",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 7,
                  "ours_freecf": 4
                },
                "steps": {
                  "baseline": 140,
                  "ours_freecf": 114
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 12,
                  "ours_freecf": 16
                },
                "steps": {
                  "baseline": 314,
                  "ours_freecf": 140
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 20,
                  "ours_freecf": 18
                },
                "steps": {
                  "baseline": 152,
                  "ours_freecf": 208
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 34,
                  "ours_freecf": 35
                },
                "steps": {
                  "baseline": 650,
                  "ours_freecf": 564
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 42,
                  "ours_freecf": 44
                },
                "steps": {
                  "baseline": 492,
                  "ours_freecf": 584
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 53,
                  "ours_freecf": 52
                },
                "steps": {
                  "baseline": 320,
                  "ours_freecf": 270
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 55,
                  "ours_freecf": 58
                },
                "steps": {
                  "baseline": 301,
                  "ours_freecf": 177
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 71,
                  "ours_freecf": 69
                },
                "steps": {
                  "baseline": 167,
                  "ours_freecf": 168
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 78,
                  "ours_freecf": 72
                },
                "steps": {
                  "baseline": 313,
                  "ours_freecf": 435
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 86,
                  "ours_freecf": 88
                },
                "steps": {
                  "baseline": 375,
                  "ours_freecf": 367
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 97,
                  "ours_freecf": 95
                },
                "steps": {
                  "baseline": 150,
                  "ours_freecf": 390
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 102,
                  "ours_freecf": 103
                },
                "steps": {
                  "baseline": 196,
                  "ours_freecf": 139
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 194,
                  "ours_freecf": 185
                },
                "steps": {
                  "baseline": 230,
                  "ours_freecf": 492
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 204,
                  "ours_freecf": 199
                },
                "steps": {
                  "baseline": 675,
                  "ours_freecf": 196
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 216,
                  "ours_freecf": 213
                },
                "steps": {
                  "baseline": 792,
                  "ours_freecf": 358
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 228,
                  "ours_freecf": 237
                },
                "steps": {
                  "baseline": 403,
                  "ours_freecf": 211
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 249,
                  "ours_freecf": 254
                },
                "steps": {
                  "baseline": 283,
                  "ours_freecf": 239
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 262,
                  "ours_freecf": 267
                },
                "steps": {
                  "baseline": 361,
                  "ours_freecf": 230
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 278,
                  "ours_freecf": 280
                },
                "steps": {
                  "baseline": 236,
                  "ours_freecf": 596
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 287,
                  "ours_freecf": 286
                },
                "steps": {
                  "baseline": 361,
                  "ours_freecf": 205
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 300,
                  "ours_freecf": 307
                },
                "steps": {
                  "baseline": 341,
                  "ours_freecf": 322
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 324,
                  "ours_freecf": 317
                },
                "steps": {
                  "baseline": 238,
                  "ours_freecf": 506
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 337,
                  "ours_freecf": 339
                },
                "steps": {
                  "baseline": 188,
                  "ours_freecf": 154
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 348,
                  "ours_freecf": 359
                },
                "steps": {
                  "baseline": 271,
                  "ours_freecf": 451
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 369,
                  "ours_freecf": 364
                },
                "steps": {
                  "baseline": 713,
                  "ours_freecf": 421
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 385,
                  "ours_freecf": 381
                },
                "steps": {
                  "baseline": 201,
                  "ours_freecf": 532
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 392,
                  "ours_freecf": 403
                },
                "steps": {
                  "baseline": 381,
                  "ours_freecf": 104
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 413,
                  "ours_freecf": 410
                },
                "steps": {
                  "baseline": 177,
                  "ours_freecf": 190
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 422,
                  "ours_freecf": 421
                },
                "steps": {
                  "baseline": 850,
                  "ours_freecf": 133
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 442,
                  "ours_freecf": 439
                },
                "steps": {
                  "baseline": 459,
                  "ours_freecf": 850
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 450,
                  "ours_freecf": 460
                },
                "steps": {
                  "baseline": 581,
                  "ours_freecf": 731
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 477,
                  "ours_freecf": 469
                },
                "steps": {
                  "baseline": 139,
                  "ours_freecf": 327
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 481,
                  "ours_freecf": 486
                },
                "steps": {
                  "baseline": 431,
                  "ours_freecf": 289
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 504,
                  "ours_freecf": 502
                },
                "steps": {
                  "baseline": 269,
                  "ours_freecf": 793
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 515,
                  "ours_freecf": 516
                },
                "steps": {
                  "baseline": 145,
                  "ours_freecf": 850
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 534,
                  "ours_freecf": 529
                },
                "steps": {
                  "baseline": 489,
                  "ours_freecf": 850
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 541,
                  "ours_freecf": 553
                },
                "steps": {
                  "baseline": 441,
                  "ours_freecf": 223
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 557,
                  "ours_freecf": 565
                },
                "steps": {
                  "baseline": 356,
                  "ours_freecf": 772
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 571,
                  "ours_freecf": 570
                },
                "steps": {
                  "baseline": 169,
                  "ours_freecf": 428
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 586,
                  "ours_freecf": 598
                },
                "steps": {
                  "baseline": 308,
                  "ours_freecf": 302
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 606,
                  "ours_freecf": 608
                },
                "steps": {
                  "baseline": 120,
                  "ours_freecf": 605
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 621,
                  "ours_freecf": 626
                },
                "steps": {
                  "baseline": 759,
                  "ours_freecf": 283
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 641,
                  "ours_freecf": 630
                },
                "steps": {
                  "baseline": 320,
                  "ours_freecf": 334
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 645,
                  "ours_freecf": 654
                },
                "steps": {
                  "baseline": 158,
                  "ours_freecf": 231
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 674,
                  "ours_freecf": 671
                },
                "steps": {
                  "baseline": 425,
                  "ours_freecf": 425
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 688,
                  "ours_freecf": 679
                },
                "steps": {
                  "baseline": 154,
                  "ours_freecf": 455
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 701,
                  "ours_freecf": 693
                },
                "steps": {
                  "baseline": 499,
                  "ours_freecf": 504
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 709,
                  "ours_freecf": 715
                },
                "steps": {
                  "baseline": 311,
                  "ours_freecf": 377
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 729,
                  "ours_freecf": 722
                },
                "steps": {
                  "baseline": 398,
                  "ours_freecf": 322
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 737,
                  "ours_freecf": 744
                },
                "steps": {
                  "baseline": 339,
                  "ours_freecf": 552
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/routing_d2/2026-09-09/paired_round_outcomes.csv"
          }
        ],
        "R3": [
          {
            "label": "R3",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 2,
                  "final_iql": 8,
                  "ours_freecf": 5
                },
                "steps": {
                  "baseline": 319,
                  "final_iql": 658,
                  "ours_freecf": 124
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 15,
                  "final_iql": 13,
                  "ours_freecf": 14
                },
                "steps": {
                  "baseline": 181,
                  "final_iql": 327,
                  "ours_freecf": 335
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 22,
                  "final_iql": 23,
                  "ours_freecf": 25
                },
                "steps": {
                  "baseline": 667,
                  "final_iql": 103,
                  "ours_freecf": 321
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 32,
                  "final_iql": 29,
                  "ours_freecf": 33
                },
                "steps": {
                  "baseline": 271,
                  "final_iql": 734,
                  "ours_freecf": 526
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 37,
                  "final_iql": 38,
                  "ours_freecf": 43
                },
                "steps": {
                  "baseline": 207,
                  "final_iql": 850,
                  "ours_freecf": 302
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 49,
                  "final_iql": 45,
                  "ours_freecf": 46
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 286,
                  "ours_freecf": 259
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 54,
                  "final_iql": 61,
                  "ours_freecf": 62
                },
                "steps": {
                  "baseline": 395,
                  "final_iql": 336,
                  "ours_freecf": 390
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 66,
                  "final_iql": 63,
                  "ours_freecf": 67
                },
                "steps": {
                  "baseline": 234,
                  "final_iql": 365,
                  "ours_freecf": 480
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 73,
                  "final_iql": 79,
                  "ours_freecf": 75
                },
                "steps": {
                  "baseline": 544,
                  "final_iql": 242,
                  "ours_freecf": 636
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 89,
                  "final_iql": 87,
                  "ours_freecf": 83
                },
                "steps": {
                  "baseline": 827,
                  "final_iql": 295,
                  "ours_freecf": 467
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 93,
                  "final_iql": 90,
                  "ours_freecf": 98
                },
                "steps": {
                  "baseline": 397,
                  "final_iql": 836,
                  "ours_freecf": 731
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 101,
                  "final_iql": 106,
                  "ours_freecf": 104
                },
                "steps": {
                  "baseline": 659,
                  "final_iql": 157,
                  "ours_freecf": 136
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 192,
                  "final_iql": 190,
                  "ours_freecf": 183
                },
                "steps": {
                  "baseline": 336,
                  "final_iql": 207,
                  "ours_freecf": 850
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 202,
                  "final_iql": 198,
                  "ours_freecf": 196
                },
                "steps": {
                  "baseline": 253,
                  "final_iql": 577,
                  "ours_freecf": 271
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 215,
                  "final_iql": 219,
                  "ours_freecf": 214
                },
                "steps": {
                  "baseline": 302,
                  "final_iql": 105,
                  "ours_freecf": 128
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 233,
                  "final_iql": 236,
                  "ours_freecf": 229
                },
                "steps": {
                  "baseline": 477,
                  "final_iql": 116,
                  "ours_freecf": 234
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 242,
                  "final_iql": 252,
                  "ours_freecf": 241
                },
                "steps": {
                  "baseline": 326,
                  "final_iql": 511,
                  "ours_freecf": 349
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 265,
                  "final_iql": 256,
                  "ours_freecf": 266
                },
                "steps": {
                  "baseline": 362,
                  "final_iql": 252,
                  "ours_freecf": 306
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 270,
                  "final_iql": 282,
                  "ours_freecf": 283
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 496,
                  "ours_freecf": 95
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 292,
                  "final_iql": 297,
                  "ours_freecf": 296
                },
                "steps": {
                  "baseline": 357,
                  "final_iql": 190,
                  "ours_freecf": 236
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 311,
                  "final_iql": 313,
                  "ours_freecf": 304
                },
                "steps": {
                  "baseline": 826,
                  "final_iql": 305,
                  "ours_freecf": 236
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 326,
                  "final_iql": 316,
                  "ours_freecf": 325
                },
                "steps": {
                  "baseline": 380,
                  "final_iql": 805,
                  "ours_freecf": 507
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 343,
                  "final_iql": 342,
                  "ours_freecf": 336
                },
                "steps": {
                  "baseline": 203,
                  "final_iql": 107,
                  "ours_freecf": 175
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 354,
                  "final_iql": 358,
                  "ours_freecf": 355
                },
                "steps": {
                  "baseline": 414,
                  "final_iql": 118,
                  "ours_freecf": 374
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 368,
                  "final_iql": 367,
                  "ours_freecf": 360
                },
                "steps": {
                  "baseline": 846,
                  "final_iql": 179,
                  "ours_freecf": 246
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 377,
                  "final_iql": 383,
                  "ours_freecf": 387
                },
                "steps": {
                  "baseline": 281,
                  "final_iql": 291,
                  "ours_freecf": 541
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 398,
                  "final_iql": 404,
                  "ours_freecf": 395
                },
                "steps": {
                  "baseline": 522,
                  "final_iql": 206,
                  "ours_freecf": 107
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 411,
                  "final_iql": 416,
                  "ours_freecf": 408
                },
                "steps": {
                  "baseline": 461,
                  "final_iql": 218,
                  "ours_freecf": 374
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 434,
                  "final_iql": 423,
                  "ours_freecf": 425
                },
                "steps": {
                  "baseline": 407,
                  "final_iql": 833,
                  "ours_freecf": 850
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 444,
                  "final_iql": 448,
                  "ours_freecf": 445
                },
                "steps": {
                  "baseline": 645,
                  "final_iql": 243,
                  "ours_freecf": 850
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 451,
                  "final_iql": 461,
                  "ours_freecf": 456
                },
                "steps": {
                  "baseline": 569,
                  "final_iql": 399,
                  "ours_freecf": 243
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 476,
                  "final_iql": 472,
                  "ours_freecf": 465
                },
                "steps": {
                  "baseline": 203,
                  "final_iql": 621,
                  "ours_freecf": 323
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 480,
                  "final_iql": 494,
                  "ours_freecf": 487
                },
                "steps": {
                  "baseline": 626,
                  "final_iql": 542,
                  "ours_freecf": 299
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 498,
                  "final_iql": 506,
                  "ours_freecf": 507
                },
                "steps": {
                  "baseline": 819,
                  "final_iql": 304,
                  "ours_freecf": 315
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 520,
                  "final_iql": 514,
                  "ours_freecf": 510
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 280,
                  "ours_freecf": 350
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 525,
                  "final_iql": 530,
                  "ours_freecf": 535
                },
                "steps": {
                  "baseline": 377,
                  "final_iql": 278,
                  "ours_freecf": 134
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 551,
                  "final_iql": 554,
                  "ours_freecf": 542
                },
                "steps": {
                  "baseline": 319,
                  "final_iql": 182,
                  "ours_freecf": 240
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 560,
                  "final_iql": 566,
                  "ours_freecf": 558
                },
                "steps": {
                  "baseline": 583,
                  "final_iql": 382,
                  "ours_freecf": 347
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 574,
                  "final_iql": 573,
                  "ours_freecf": 576
                },
                "steps": {
                  "baseline": 459,
                  "final_iql": 328,
                  "ours_freecf": 224
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 592,
                  "final_iql": 593,
                  "ours_freecf": 590
                },
                "steps": {
                  "baseline": 246,
                  "final_iql": 116,
                  "ours_freecf": 530
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 609,
                  "final_iql": 613,
                  "ours_freecf": 611
                },
                "steps": {
                  "baseline": 115,
                  "final_iql": 335,
                  "ours_freecf": 485
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 620,
                  "final_iql": 617,
                  "ours_freecf": 616
                },
                "steps": {
                  "baseline": 463,
                  "final_iql": 460,
                  "ours_freecf": 607
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 636,
                  "final_iql": 640,
                  "ours_freecf": 639
                },
                "steps": {
                  "baseline": 172,
                  "final_iql": 163,
                  "ours_freecf": 392
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 646,
                  "final_iql": 648,
                  "ours_freecf": 647
                },
                "steps": {
                  "baseline": 173,
                  "final_iql": 167,
                  "ours_freecf": 96
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 669,
                  "final_iql": 660,
                  "ours_freecf": 661
                },
                "steps": {
                  "baseline": 338,
                  "final_iql": 284,
                  "ours_freecf": 328
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 682,
                  "final_iql": 677,
                  "ours_freecf": 689
                },
                "steps": {
                  "baseline": 128,
                  "final_iql": 360,
                  "ours_freecf": 462
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 692,
                  "final_iql": 699,
                  "ours_freecf": 695
                },
                "steps": {
                  "baseline": 154,
                  "final_iql": 431,
                  "ours_freecf": 554
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 710,
                  "final_iql": 707,
                  "ours_freecf": 708
                },
                "steps": {
                  "baseline": 142,
                  "final_iql": 755,
                  "ours_freecf": 179
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 730,
                  "final_iql": 727,
                  "ours_freecf": 728
                },
                "steps": {
                  "baseline": 346,
                  "final_iql": 433,
                  "ours_freecf": 653
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 745,
                  "final_iql": 739,
                  "ours_freecf": 740
                },
                "steps": {
                  "baseline": 212,
                  "final_iql": 179,
                  "ours_freecf": 715
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/routing_d2/2026-09-09/paired_round_outcomes.csv"
          }
        ],
        "R4": [
          {
            "label": "R4",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 112,
                  "final_iql": 113,
                  "ours_freecf": 109
                },
                "steps": {
                  "baseline": 207,
                  "final_iql": 355,
                  "ours_freecf": 310
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 118,
                  "final_iql": 114,
                  "ours_freecf": 116
                },
                "steps": {
                  "baseline": 208,
                  "final_iql": 494,
                  "ours_freecf": 411
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 124,
                  "final_iql": 122,
                  "ours_freecf": 121
                },
                "steps": {
                  "baseline": 577,
                  "final_iql": 205,
                  "ours_freecf": 285
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 127,
                  "final_iql": 129,
                  "ours_freecf": 131
                },
                "steps": {
                  "baseline": 639,
                  "final_iql": 850,
                  "ours_freecf": 436
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 136,
                  "final_iql": 132,
                  "ours_freecf": 133
                },
                "steps": {
                  "baseline": 503,
                  "final_iql": 348,
                  "ours_freecf": 295
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 140,
                  "final_iql": 139,
                  "ours_freecf": 143
                },
                "steps": {
                  "baseline": 658,
                  "final_iql": 109,
                  "ours_freecf": 299
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 147,
                  "final_iql": 145,
                  "ours_freecf": 146
                },
                "steps": {
                  "baseline": 664,
                  "final_iql": 247,
                  "ours_freecf": 630
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 150,
                  "final_iql": 153,
                  "ours_freecf": 151
                },
                "steps": {
                  "baseline": 172,
                  "final_iql": 650,
                  "ours_freecf": 401
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 161,
                  "final_iql": 159,
                  "ours_freecf": 158
                },
                "steps": {
                  "baseline": 364,
                  "final_iql": 344,
                  "ours_freecf": 344
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 163,
                  "final_iql": 164,
                  "ours_freecf": 167
                },
                "steps": {
                  "baseline": 838,
                  "final_iql": 311,
                  "ours_freecf": 828
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 168,
                  "final_iql": 172,
                  "ours_freecf": 171
                },
                "steps": {
                  "baseline": 395,
                  "final_iql": 351,
                  "ours_freecf": 646
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 176,
                  "final_iql": 179,
                  "ours_freecf": 177
                },
                "steps": {
                  "baseline": 185,
                  "final_iql": 130,
                  "ours_freecf": 116
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 191,
                  "final_iql": 187,
                  "ours_freecf": 186
                },
                "steps": {
                  "baseline": 476,
                  "final_iql": 311,
                  "ours_freecf": 717
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 200,
                  "final_iql": 201,
                  "ours_freecf": 208
                },
                "steps": {
                  "baseline": 507,
                  "final_iql": 327,
                  "ours_freecf": 252
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 224,
                  "final_iql": 222,
                  "ours_freecf": 212
                },
                "steps": {
                  "baseline": 562,
                  "final_iql": 243,
                  "ours_freecf": 676
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 231,
                  "final_iql": 239,
                  "ours_freecf": 230
                },
                "steps": {
                  "baseline": 576,
                  "final_iql": 506,
                  "ours_freecf": 210
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 250,
                  "final_iql": 253,
                  "ours_freecf": 245
                },
                "steps": {
                  "baseline": 364,
                  "final_iql": 433,
                  "ours_freecf": 585
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 269,
                  "final_iql": 255,
                  "ours_freecf": 263
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 243,
                  "ours_freecf": 283
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 276,
                  "final_iql": 281,
                  "ours_freecf": 284
                },
                "steps": {
                  "baseline": 566,
                  "final_iql": 705,
                  "ours_freecf": 445
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 285,
                  "final_iql": 293,
                  "ours_freecf": 294
                },
                "steps": {
                  "baseline": 254,
                  "final_iql": 334,
                  "ours_freecf": 483
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 309,
                  "final_iql": 310,
                  "ours_freecf": 314
                },
                "steps": {
                  "baseline": 506,
                  "final_iql": 429,
                  "ours_freecf": 298
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 321,
                  "final_iql": 322,
                  "ours_freecf": 315
                },
                "steps": {
                  "baseline": 426,
                  "final_iql": 641,
                  "ours_freecf": 472
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 340,
                  "final_iql": 344,
                  "ours_freecf": 334
                },
                "steps": {
                  "baseline": 240,
                  "final_iql": 850,
                  "ours_freecf": 379
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 350,
                  "final_iql": 347,
                  "ours_freecf": 353
                },
                "steps": {
                  "baseline": 337,
                  "final_iql": 220,
                  "ours_freecf": 589
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 371,
                  "final_iql": 363,
                  "ours_freecf": 361
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 266,
                  "ours_freecf": 287
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 382,
                  "final_iql": 386,
                  "ours_freecf": 384
                },
                "steps": {
                  "baseline": 537,
                  "final_iql": 427,
                  "ours_freecf": 283
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 393,
                  "final_iql": 401,
                  "ours_freecf": 400
                },
                "steps": {
                  "baseline": 380,
                  "final_iql": 511,
                  "ours_freecf": 154
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 412,
                  "final_iql": 415,
                  "ours_freecf": 419
                },
                "steps": {
                  "baseline": 309,
                  "final_iql": 850,
                  "ours_freecf": 557
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 429,
                  "final_iql": 431,
                  "ours_freecf": 428
                },
                "steps": {
                  "baseline": 753,
                  "final_iql": 222,
                  "ours_freecf": 850
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 438,
                  "final_iql": 443,
                  "ours_freecf": 446
                },
                "steps": {
                  "baseline": 545,
                  "final_iql": 353,
                  "ours_freecf": 373
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 463,
                  "final_iql": 454,
                  "ours_freecf": 462
                },
                "steps": {
                  "baseline": 404,
                  "final_iql": 185,
                  "ours_freecf": 295
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 479,
                  "final_iql": 468,
                  "ours_freecf": 471
                },
                "steps": {
                  "baseline": 302,
                  "final_iql": 121,
                  "ours_freecf": 285
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 488,
                  "final_iql": 493,
                  "ours_freecf": 489
                },
                "steps": {
                  "baseline": 577,
                  "final_iql": 504,
                  "ours_freecf": 433
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 509,
                  "final_iql": 503,
                  "ours_freecf": 501
                },
                "steps": {
                  "baseline": 654,
                  "final_iql": 240,
                  "ours_freecf": 291
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 524,
                  "final_iql": 522,
                  "ours_freecf": 517
                },
                "steps": {
                  "baseline": 263,
                  "final_iql": 850,
                  "ours_freecf": 620
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 532,
                  "final_iql": 527,
                  "ours_freecf": 538
                },
                "steps": {
                  "baseline": 449,
                  "final_iql": 673,
                  "ours_freecf": 269
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 548,
                  "final_iql": 543,
                  "ours_freecf": 550
                },
                "steps": {
                  "baseline": 723,
                  "final_iql": 356,
                  "ours_freecf": 684
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 567,
                  "final_iql": 556,
                  "ours_freecf": 555
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 636,
                  "ours_freecf": 284
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 578,
                  "final_iql": 582,
                  "ours_freecf": 584
                },
                "steps": {
                  "baseline": 576,
                  "final_iql": 143,
                  "ours_freecf": 231
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 595,
                  "final_iql": 589,
                  "ours_freecf": 594
                },
                "steps": {
                  "baseline": 333,
                  "final_iql": 644,
                  "ours_freecf": 850
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 604,
                  "final_iql": 610,
                  "ours_freecf": 600
                },
                "steps": {
                  "baseline": 708,
                  "final_iql": 345,
                  "ours_freecf": 517
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 628,
                  "final_iql": 619,
                  "ours_freecf": 623
                },
                "steps": {
                  "baseline": 317,
                  "final_iql": 317,
                  "ours_freecf": 258
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 642,
                  "final_iql": 644,
                  "ours_freecf": 631
                },
                "steps": {
                  "baseline": 233,
                  "final_iql": 542,
                  "ours_freecf": 626
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 653,
                  "final_iql": 649,
                  "ours_freecf": 650
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 586,
                  "ours_freecf": 447
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 673,
                  "final_iql": 664,
                  "ours_freecf": 665
                },
                "steps": {
                  "baseline": 359,
                  "final_iql": 456,
                  "ours_freecf": 850
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 683,
                  "final_iql": 681,
                  "ours_freecf": 686
                },
                "steps": {
                  "baseline": 140,
                  "final_iql": 199,
                  "ours_freecf": 332
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 691,
                  "final_iql": 703,
                  "ours_freecf": 697
                },
                "steps": {
                  "baseline": 599,
                  "final_iql": 510,
                  "ours_freecf": 540
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 713,
                  "final_iql": 705,
                  "ours_freecf": 706
                },
                "steps": {
                  "baseline": 277,
                  "final_iql": 150,
                  "ours_freecf": 570
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 723,
                  "final_iql": 734,
                  "ours_freecf": 733
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 355,
                  "ours_freecf": 505
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 741,
                  "final_iql": 736,
                  "ours_freecf": 748
                },
                "steps": {
                  "baseline": 513,
                  "final_iql": 198,
                  "ours_freecf": 850
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/routing_d2/2026-09-09/paired_round_outcomes.csv"
          }
        ],
        "R5": [
          {
            "label": "R5",
            "rows": [
              {
                "id": 0,
                "order": 1,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 110,
                  "final_iql": 111,
                  "ours_freecf": 108
                },
                "steps": {
                  "baseline": 657,
                  "final_iql": 311,
                  "ours_freecf": 411
                }
              },
              {
                "id": 1,
                "order": 2,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 115,
                  "final_iql": 119,
                  "ours_freecf": 117
                },
                "steps": {
                  "baseline": 249,
                  "final_iql": 492,
                  "ours_freecf": 127
                }
              },
              {
                "id": 2,
                "order": 3,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 123,
                  "final_iql": 120,
                  "ours_freecf": 125
                },
                "steps": {
                  "baseline": 625,
                  "final_iql": 139,
                  "ours_freecf": 241
                }
              },
              {
                "id": 3,
                "order": 4,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 130,
                  "final_iql": 126,
                  "ours_freecf": 128
                },
                "steps": {
                  "baseline": 324,
                  "final_iql": 647,
                  "ours_freecf": 230
                }
              },
              {
                "id": 4,
                "order": 5,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 135,
                  "final_iql": 137,
                  "ours_freecf": 134
                },
                "steps": {
                  "baseline": 816,
                  "final_iql": 275,
                  "ours_freecf": 332
                }
              },
              {
                "id": 5,
                "order": 6,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 138,
                  "final_iql": 141,
                  "ours_freecf": 142
                },
                "steps": {
                  "baseline": 430,
                  "final_iql": 225,
                  "ours_freecf": 243
                }
              },
              {
                "id": 6,
                "order": 7,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 144,
                  "final_iql": 149,
                  "ours_freecf": 148
                },
                "steps": {
                  "baseline": 387,
                  "final_iql": 301,
                  "ours_freecf": 278
                }
              },
              {
                "id": 7,
                "order": 8,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 154,
                  "final_iql": 152,
                  "ours_freecf": 155
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 436,
                  "ours_freecf": 478
                }
              },
              {
                "id": 8,
                "order": 9,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 160,
                  "final_iql": 156,
                  "ours_freecf": 157
                },
                "steps": {
                  "baseline": 252,
                  "final_iql": 355,
                  "ours_freecf": 333
                }
              },
              {
                "id": 9,
                "order": 10,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 162,
                  "final_iql": 166,
                  "ours_freecf": 165
                },
                "steps": {
                  "baseline": 321,
                  "final_iql": 103,
                  "ours_freecf": 114
                }
              },
              {
                "id": 10,
                "order": 11,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 170,
                  "final_iql": 173,
                  "ours_freecf": 169
                },
                "steps": {
                  "baseline": 554,
                  "final_iql": 504,
                  "ours_freecf": 685
                }
              },
              {
                "id": 11,
                "order": 12,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 178,
                  "final_iql": 175,
                  "ours_freecf": 174
                },
                "steps": {
                  "baseline": 150,
                  "final_iql": 168,
                  "ours_freecf": 293
                }
              },
              {
                "id": 12,
                "order": 13,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 180,
                  "final_iql": 181,
                  "ours_freecf": 188
                },
                "steps": {
                  "baseline": 354,
                  "final_iql": 223,
                  "ours_freecf": 238
                }
              },
              {
                "id": 13,
                "order": 14,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 206,
                  "final_iql": 209,
                  "ours_freecf": 207
                },
                "steps": {
                  "baseline": 409,
                  "final_iql": 470,
                  "ours_freecf": 240
                }
              },
              {
                "id": 14,
                "order": 15,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 210,
                  "final_iql": 220,
                  "ours_freecf": 221
                },
                "steps": {
                  "baseline": 236,
                  "final_iql": 446,
                  "ours_freecf": 786
                }
              },
              {
                "id": 15,
                "order": 16,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 227,
                  "final_iql": 226,
                  "ours_freecf": 238
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 648,
                  "ours_freecf": 175
                }
              },
              {
                "id": 16,
                "order": 17,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 246,
                  "final_iql": 251,
                  "ours_freecf": 247
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 662,
                  "ours_freecf": 472
                }
              },
              {
                "id": 17,
                "order": 18,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 257,
                  "final_iql": 260,
                  "ours_freecf": 258
                },
                "steps": {
                  "baseline": 431,
                  "final_iql": 258,
                  "ours_freecf": 332
                }
              },
              {
                "id": 18,
                "order": 19,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 279,
                  "final_iql": 271,
                  "ours_freecf": 274
                },
                "steps": {
                  "baseline": 500,
                  "final_iql": 117,
                  "ours_freecf": 138
                }
              },
              {
                "id": 19,
                "order": 20,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 299,
                  "final_iql": 298,
                  "ours_freecf": 291
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 779,
                  "ours_freecf": 235
                }
              },
              {
                "id": 20,
                "order": 21,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 305,
                  "final_iql": 302,
                  "ours_freecf": 303
                },
                "steps": {
                  "baseline": 717,
                  "final_iql": 392,
                  "ours_freecf": 749
                }
              },
              {
                "id": 21,
                "order": 22,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 327,
                  "final_iql": 328,
                  "ours_freecf": 323
                },
                "steps": {
                  "baseline": 850,
                  "final_iql": 544,
                  "ours_freecf": 590
                }
              },
              {
                "id": 22,
                "order": 23,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 331,
                  "final_iql": 332,
                  "ours_freecf": 341
                },
                "steps": {
                  "baseline": 399,
                  "final_iql": 439,
                  "ours_freecf": 119
                }
              },
              {
                "id": 23,
                "order": 24,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 352,
                  "final_iql": 349,
                  "ours_freecf": 356
                },
                "steps": {
                  "baseline": 276,
                  "final_iql": 157,
                  "ours_freecf": 583
                }
              },
              {
                "id": 24,
                "order": 25,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 365,
                  "final_iql": 372,
                  "ours_freecf": 374
                },
                "steps": {
                  "baseline": 812,
                  "final_iql": 153,
                  "ours_freecf": 833
                }
              },
              {
                "id": 25,
                "order": 26,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 378,
                  "final_iql": 389,
                  "ours_freecf": 380
                },
                "steps": {
                  "baseline": 649,
                  "final_iql": 340,
                  "ours_freecf": 696
                }
              },
              {
                "id": 26,
                "order": 27,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 391,
                  "final_iql": 396,
                  "ours_freecf": 397
                },
                "steps": {
                  "baseline": 703,
                  "final_iql": 583,
                  "ours_freecf": 535
                }
              },
              {
                "id": 27,
                "order": 28,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 407,
                  "final_iql": 417,
                  "ours_freecf": 409
                },
                "steps": {
                  "baseline": 474,
                  "final_iql": 362,
                  "ours_freecf": 115
                }
              },
              {
                "id": 28,
                "order": 29,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 424,
                  "final_iql": 430,
                  "ours_freecf": 426
                },
                "steps": {
                  "baseline": 468,
                  "final_iql": 523,
                  "ours_freecf": 496
                }
              },
              {
                "id": 29,
                "order": 30,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 447,
                  "final_iql": 436,
                  "ours_freecf": 437
                },
                "steps": {
                  "baseline": 304,
                  "final_iql": 217,
                  "ours_freecf": 208
                }
              },
              {
                "id": 30,
                "order": 31,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 455,
                  "final_iql": 464,
                  "ours_freecf": 457
                },
                "steps": {
                  "baseline": 205,
                  "final_iql": 258,
                  "ours_freecf": 328
                }
              },
              {
                "id": 31,
                "order": 32,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 470,
                  "final_iql": 473,
                  "ours_freecf": 474
                },
                "steps": {
                  "baseline": 422,
                  "final_iql": 314,
                  "ours_freecf": 301
                }
              },
              {
                "id": 32,
                "order": 33,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 485,
                  "final_iql": 490,
                  "ours_freecf": 491
                },
                "steps": {
                  "baseline": 509,
                  "final_iql": 283,
                  "ours_freecf": 380
                }
              },
              {
                "id": 33,
                "order": 34,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 505,
                  "final_iql": 500,
                  "ours_freecf": 495
                },
                "steps": {
                  "baseline": 499,
                  "final_iql": 150,
                  "ours_freecf": 850
                }
              },
              {
                "id": 34,
                "order": 35,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 519,
                  "final_iql": 513,
                  "ours_freecf": 521
                },
                "steps": {
                  "baseline": 573,
                  "final_iql": 181,
                  "ours_freecf": 850
                }
              },
              {
                "id": 35,
                "order": 36,
                "values": {
                  "baseline": "success",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 533,
                  "final_iql": 526,
                  "ours_freecf": 528
                },
                "steps": {
                  "baseline": 600,
                  "final_iql": 213,
                  "ours_freecf": 271
                }
              },
              {
                "id": 36,
                "order": 37,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 540,
                  "final_iql": 545,
                  "ours_freecf": 547
                },
                "steps": {
                  "baseline": 492,
                  "final_iql": 428,
                  "ours_freecf": 468
                }
              },
              {
                "id": 37,
                "order": 38,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "success",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 568,
                  "final_iql": 564,
                  "ours_freecf": 563
                },
                "steps": {
                  "baseline": 433,
                  "final_iql": 335,
                  "ours_freecf": 505
                }
              },
              {
                "id": 38,
                "order": 39,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 572,
                  "final_iql": 577,
                  "ours_freecf": 580
                },
                "steps": {
                  "baseline": 134,
                  "final_iql": 240,
                  "ours_freecf": 467
                }
              },
              {
                "id": 39,
                "order": 40,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 599,
                  "final_iql": 587,
                  "ours_freecf": 585
                },
                "steps": {
                  "baseline": 319,
                  "final_iql": 608,
                  "ours_freecf": 602
                }
              },
              {
                "id": 40,
                "order": 41,
                "values": {
                  "baseline": "failure",
                  "final_iql": "timeout",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 601,
                  "final_iql": 602,
                  "ours_freecf": 614
                },
                "steps": {
                  "baseline": 365,
                  "final_iql": 499,
                  "ours_freecf": 317
                }
              },
              {
                "id": 41,
                "order": 42,
                "values": {
                  "baseline": "success",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 629,
                  "final_iql": 624,
                  "ours_freecf": 615
                },
                "steps": {
                  "baseline": 502,
                  "final_iql": 188,
                  "ours_freecf": 440
                }
              },
              {
                "id": 42,
                "order": 43,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 637,
                  "final_iql": 643,
                  "ours_freecf": 635
                },
                "steps": {
                  "baseline": 517,
                  "final_iql": 108,
                  "ours_freecf": 289
                }
              },
              {
                "id": 43,
                "order": 44,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 656,
                  "final_iql": 658,
                  "ours_freecf": 652
                },
                "steps": {
                  "baseline": 187,
                  "final_iql": 625,
                  "ours_freecf": 155
                }
              },
              {
                "id": 44,
                "order": 45,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "timeout",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 670,
                  "final_iql": 667,
                  "ours_freecf": 668
                },
                "steps": {
                  "baseline": 614,
                  "final_iql": 550,
                  "ours_freecf": 748
                }
              },
              {
                "id": 45,
                "order": 46,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 685,
                  "final_iql": 680,
                  "ours_freecf": 684
                },
                "steps": {
                  "baseline": 162,
                  "final_iql": 167,
                  "ours_freecf": 258
                }
              },
              {
                "id": 46,
                "order": 47,
                "values": {
                  "baseline": "timeout",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 690,
                  "final_iql": 694,
                  "ours_freecf": 696
                },
                "steps": {
                  "baseline": 739,
                  "final_iql": 406,
                  "ours_freecf": 688
                }
              },
              {
                "id": 47,
                "order": 48,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "failure"
                },
                "episodes": {
                  "baseline": 711,
                  "final_iql": 714,
                  "ours_freecf": 712
                },
                "steps": {
                  "baseline": 825,
                  "final_iql": 578,
                  "ours_freecf": 102
                }
              },
              {
                "id": 48,
                "order": 49,
                "values": {
                  "baseline": "failure",
                  "final_iql": "failure",
                  "ours_freecf": "timeout"
                },
                "episodes": {
                  "baseline": 721,
                  "final_iql": 720,
                  "ours_freecf": 725
                },
                "steps": {
                  "baseline": 718,
                  "final_iql": 407,
                  "ours_freecf": 805
                }
              },
              {
                "id": 49,
                "order": 50,
                "values": {
                  "baseline": "failure",
                  "final_iql": "success",
                  "ours_freecf": "success"
                },
                "episodes": {
                  "baseline": 738,
                  "final_iql": 735,
                  "ours_freecf": 746
                },
                "steps": {
                  "baseline": 589,
                  "final_iql": 230,
                  "ours_freecf": 200
                }
              }
            ],
            "columns": [
              {
                "key": "baseline",
                "label": "HG-DAgger"
              },
              {
                "key": "final_iql",
                "label": "HiL-IDQL + Mulligan"
              },
              {
                "key": "ours_freecf",
                "label": "HG-DAgger + Mulligan"
              }
            ],
            "source": "paper/data/routing_d2/2026-09-09/paired_round_outcomes.csv"
          }
        ]
      }
    }
  ],
  "videos": [
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R0",
      "label": "Actor comparison",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r0/marker_d2_r0_baseline_vs_ours_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r0_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R1",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r1_eval/marker_d2_r1_checkpoint100000_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r1_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R2",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r2_eval/marker_d2_r2_checkpoint100000_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r2_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R2",
      "label": "Three-policy comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r2_eval/marker_d2_r2_checkpoint100000_3arm_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r2_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R2",
      "label": "Actor and critic comparison",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/final_dp_vs_iql_eval/marker_d2_final_dp_vs_iql_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r2_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R3",
      "label": "Three-policy comparison",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r3_eval_trio/marker_d2_r3_trio_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r3_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R4",
      "label": "Three-policy comparison",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r4_eval/marker_d2_r4_trio_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r4_eval.md"
    },
    {
      "task": "marker_d2",
      "title": "Insert marker",
      "round": "R5",
      "label": "Repeated evaluation \u00b7 selected critic",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/marker_d2/r5_repeat_eval/marker_d2_r5_repeat_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/marker_d2_r5_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R0",
      "label": "Actor comparison",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/r0/square_d2_r0_baseline_vs_ours_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r0_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R1",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/r1_eval/square_d2_r1_checkpoint100000_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r1_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R2",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/r2_eval/square_d2_r2_checkpoint100000_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r2_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R3",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/r3_eval/square_d2_r3_checkpoint100000_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r3_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R3",
      "label": "Actor and critic comparison \u00b7 first 50 starts",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/final_dp_vs_iql_eval/square_d2_final_dp_vs_iql_front50_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r3_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R3",
      "label": "Three-policy comparison \u00b7 second 50 starts",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/final_trio_eval/square_d2_final_trio_back50_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r3_eval.md"
    },
    {
      "task": "square_d2",
      "title": "Thread nut",
      "round": "R4",
      "label": "Actor comparison",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/square_d2/r4_eval/square_d2_r4_quad_rollouts_side_by_side.mp4",
      "source": "experiments/tracking/01b_real_world/square_d2_r4_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R0",
      "label": "Actor comparison \u00b7 75k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r0/routing_d1_r0_twoarm_rollouts_side_by_side_checkpoint_75000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r0_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R0",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r0/routing_d1_r0_twoarm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r0_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R1",
      "label": "Actor comparison \u00b7 75k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r1/routing_d1_r1_twoarm_rollouts_side_by_side_checkpoint_75000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r1_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R2",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r2/routing_d1_r2_twoarm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r2_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R3",
      "label": "Actor comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r3/routing_d1_r3_twoarm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r3_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R4",
      "label": "Three-policy comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r4/routing_d1_r4_threearm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r4_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R5",
      "label": "Three-policy comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r5/routing_d1_r5_threearm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r5_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R6",
      "label": "Three-policy comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r6/routing_d1_r6_threearm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r6_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R7",
      "label": "Three-policy comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r7/routing_d1_r7_threearm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r7_eval.md"
    },
    {
      "task": "routing_d1",
      "title": "Route cable \u00b7 earlier campaign",
      "round": "R8",
      "label": "Three-policy comparison \u00b7 100k checkpoint",
      "url": "https://ankile-sir-trackers.s3.us-west-2.amazonaws.com/data-artifacts/plots/tracking/01b_real_world/routing_d1/r8/routing_d1_r8_threearm_rollouts_side_by_side_checkpoint_100000.mp4",
      "source": "experiments/tracking/01b_real_world/routing_d1_r8_eval.md"
    }
  ],
  "cf": {
    "dataset": "ankile/real01b-marker-d2-blind-dagger-r1-ef25cov25",
    "revision": "b55cb90ac866f87281d3d5a77dc377e06c9bf9a9",
    "episodes": [
      0,
      1
    ],
    "manifest_idx": 0,
    "first_policy_seconds": 5.6,
    "duration": [
      26.6,
      15.533333333333333
    ],
    "control": [
      {
        "start": 0,
        "end": 5.6,
        "source": "Policy"
      },
      {
        "start": 5.6,
        "end": 8.066666666666666,
        "source": "Human"
      },
      {
        "start": 8.066666666666666,
        "end": 26.6,
        "source": "Policy"
      }
    ]
  },
  "colors": {
    "baseline": "#888888",
    "actor": "#17becf",
    "critic": "#9467bd"
  },
  "failure_distribution": {
    "successes": [
      1,
      5,
      15,
      16,
      16,
      17,
      18,
      19,
      20,
      25,
      26,
      27,
      28,
      29,
      29,
      30,
      33,
      34,
      35,
      44,
      46,
      46,
      47,
      48,
      48,
      48,
      48,
      48,
      48,
      49,
      49,
      49,
      49,
      49,
      49,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50,
      50
    ],
    "trials_per_group": 50,
    "source": "paper/appendix/simulation/inputs.json",
    "evidence": "Digitized counts from the archived plot, single seed; original per-rollout identities were not recovered."
  },
  "simulation_source": "paper/data/paper_context_2026-08-24/01a/baselines/partial_headline.csv; seven methods, five seeds per point. The later success-BC comparator is not included in this frozen input.",
  "simulation": [
    {
      "key": "sq_d0",
      "title": "Square-Narrow",
      "points": [
        {
          "round": "R0",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.731225,
          "lo": 0.7065871293915998,
          "hi": 0.7558628706084002,
          "seeds": [
            {
              "seed": 1,
              "value": 0.71525
            },
            {
              "seed": 2,
              "value": 0.7411249999999999
            },
            {
              "seed": 3,
              "value": 0.75275
            },
            {
              "seed": 4,
              "value": 0.741375
            },
            {
              "seed": 5,
              "value": 0.705625
            }
          ]
        },
        {
          "round": "R1",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.84855,
          "lo": 0.815842956670675,
          "hi": 0.8812570433293251,
          "seeds": [
            {
              "seed": 1,
              "value": 0.809875
            },
            {
              "seed": 2,
              "value": 0.8652500000000001
            },
            {
              "seed": 3,
              "value": 0.8340000000000001
            },
            {
              "seed": 4,
              "value": 0.8590000000000001
            },
            {
              "seed": 5,
              "value": 0.8746250000000001
            }
          ]
        },
        {
          "round": "R2",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.9178499999999999,
          "lo": 0.9076378325604809,
          "hi": 0.928062167439519,
          "seeds": [
            {
              "seed": 1,
              "value": 0.912
            },
            {
              "seed": 2,
              "value": 0.921875
            },
            {
              "seed": 3,
              "value": 0.924625
            },
            {
              "seed": 4,
              "value": 0.924375
            },
            {
              "seed": 5,
              "value": 0.906375
            }
          ]
        },
        {
          "round": "R3",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.9390000000000001,
          "lo": 0.9238050654803717,
          "hi": 0.9541949345196284,
          "seeds": [
            {
              "seed": 1,
              "value": 0.9309999999999999
            },
            {
              "seed": 2,
              "value": 0.95075
            },
            {
              "seed": 3,
              "value": 0.9216249999999999
            },
            {
              "seed": 4,
              "value": 0.94475
            },
            {
              "seed": 5,
              "value": 0.946875
            }
          ]
        },
        {
          "round": "R0",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.7062250000000001,
          "lo": 0.6728405926628818,
          "hi": 0.7396094073371184,
          "seeds": [
            {
              "seed": 1,
              "value": 0.6821250000000001
            },
            {
              "seed": 2,
              "value": 0.726
            },
            {
              "seed": 3,
              "value": 0.729375
            },
            {
              "seed": 4,
              "value": 0.721375
            },
            {
              "seed": 5,
              "value": 0.6722499999999999
            }
          ]
        },
        {
          "round": "R1",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.854325,
          "lo": 0.8225906378038762,
          "hi": 0.8860593621961238,
          "seeds": [
            {
              "seed": 1,
              "value": 0.81325
            },
            {
              "seed": 2,
              "value": 0.872125
            },
            {
              "seed": 3,
              "value": 0.845625
            },
            {
              "seed": 4,
              "value": 0.873625
            },
            {
              "seed": 5,
              "value": 0.867
            }
          ]
        },
        {
          "round": "R2",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.9228999999999999,
          "lo": 0.9134441508450963,
          "hi": 0.9323558491549035,
          "seeds": [
            {
              "seed": 1,
              "value": 0.914375
            },
            {
              "seed": 2,
              "value": 0.919125
            },
            {
              "seed": 3,
              "value": 0.92
            },
            {
              "seed": 4,
              "value": 0.93375
            },
            {
              "seed": 5,
              "value": 0.9272499999999999
            }
          ]
        },
        {
          "round": "R3",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.9435499999999999,
          "lo": 0.9294428820106624,
          "hi": 0.9576571179893374,
          "seeds": [
            {
              "seed": 1,
              "value": 0.9365000000000001
            },
            {
              "seed": 2,
              "value": 0.9541249999999999
            },
            {
              "seed": 3,
              "value": 0.9275
            },
            {
              "seed": 4,
              "value": 0.94675
            },
            {
              "seed": 5,
              "value": 0.9528749999999999
            }
          ]
        },
        {
          "round": "R0",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.8150000000000001,
          "lo": 0.7902668369997665,
          "hi": 0.8397331630002336,
          "seeds": [
            {
              "seed": 1,
              "value": 0.7803749999999999
            },
            {
              "seed": 2,
              "value": 0.8283750000000001
            },
            {
              "seed": 3,
              "value": 0.82125
            },
            {
              "seed": 4,
              "value": 0.8278749999999999
            },
            {
              "seed": 5,
              "value": 0.8171250000000001
            }
          ]
        },
        {
          "round": "R1",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.9338000000000001,
          "lo": 0.9177097130968362,
          "hi": 0.9498902869031639,
          "seeds": [
            {
              "seed": 1,
              "value": 0.9440000000000001
            },
            {
              "seed": 2,
              "value": 0.919875
            },
            {
              "seed": 3,
              "value": 0.929625
            },
            {
              "seed": 4,
              "value": 0.925
            },
            {
              "seed": 5,
              "value": 0.9505
            }
          ]
        },
        {
          "round": "R2",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.9539250000000001,
          "lo": 0.945717592753602,
          "hi": 0.9621324072463983,
          "seeds": [
            {
              "seed": 1,
              "value": 0.95825
            },
            {
              "seed": 2,
              "value": 0.960875
            },
            {
              "seed": 3,
              "value": 0.948125
            },
            {
              "seed": 4,
              "value": 0.956625
            },
            {
              "seed": 5,
              "value": 0.94575
            }
          ]
        },
        {
          "round": "R3",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.9568249999999999,
          "lo": 0.948132243454698,
          "hi": 0.9655177565453018,
          "seeds": [
            {
              "seed": 1,
              "value": 0.945375
            },
            {
              "seed": 2,
              "value": 0.96375
            },
            {
              "seed": 3,
              "value": 0.9584999999999999
            },
            {
              "seed": 4,
              "value": 0.956
            },
            {
              "seed": 5,
              "value": 0.9605
            }
          ]
        },
        {
          "round": "R0",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.794975,
          "lo": 0.7637038810930508,
          "hi": 0.8262461189069492,
          "seeds": [
            {
              "seed": 1,
              "value": 0.761875
            },
            {
              "seed": 2,
              "value": 0.82625
            },
            {
              "seed": 3,
              "value": 0.796375
            },
            {
              "seed": 4,
              "value": 0.810375
            },
            {
              "seed": 5,
              "value": 0.78
            }
          ]
        },
        {
          "round": "R1",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.93395,
          "lo": 0.9194040208623648,
          "hi": 0.9484959791376351,
          "seeds": [
            {
              "seed": 1,
              "value": 0.9455
            },
            {
              "seed": 2,
              "value": 0.91925
            },
            {
              "seed": 3,
              "value": 0.9265000000000001
            },
            {
              "seed": 4,
              "value": 0.932625
            },
            {
              "seed": 5,
              "value": 0.945875
            }
          ]
        },
        {
          "round": "R2",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.95415,
          "lo": 0.9441361366995089,
          "hi": 0.9641638633004912,
          "seeds": [
            {
              "seed": 1,
              "value": 0.960125
            },
            {
              "seed": 2,
              "value": 0.9590000000000001
            },
            {
              "seed": 3,
              "value": 0.948125
            },
            {
              "seed": 4,
              "value": 0.9605
            },
            {
              "seed": 5,
              "value": 0.943
            }
          ]
        },
        {
          "round": "R3",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.96305,
          "lo": 0.9547571855914234,
          "hi": 0.9713428144085765,
          "seeds": [
            {
              "seed": 1,
              "value": 0.95375
            },
            {
              "seed": 2,
              "value": 0.96875
            },
            {
              "seed": 3,
              "value": 0.95825
            },
            {
              "seed": 4,
              "value": 0.9665
            },
            {
              "seed": 5,
              "value": 0.968
            }
          ]
        },
        {
          "round": "R0",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.7062250000000001,
          "lo": 0.6728405926628818,
          "hi": 0.7396094073371184,
          "seeds": [
            {
              "seed": 1,
              "value": 0.6821250000000001
            },
            {
              "seed": 2,
              "value": 0.726
            },
            {
              "seed": 3,
              "value": 0.729375
            },
            {
              "seed": 4,
              "value": 0.721375
            },
            {
              "seed": 5,
              "value": 0.6722499999999999
            }
          ]
        },
        {
          "round": "R1",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.6813999999999999,
          "lo": 0.6586731813771993,
          "hi": 0.7041268186228005,
          "seeds": [
            {
              "seed": 1,
              "value": 0.66525
            },
            {
              "seed": 2,
              "value": 0.675375
            },
            {
              "seed": 3,
              "value": 0.7128749999999999
            },
            {
              "seed": 4,
              "value": 0.674625
            },
            {
              "seed": 5,
              "value": 0.678875
            }
          ]
        },
        {
          "round": "R2",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.6462,
          "lo": 0.6325123614622883,
          "hi": 0.6598876385377117,
          "seeds": [
            {
              "seed": 1,
              "value": 0.653
            },
            {
              "seed": 2,
              "value": 0.649125
            },
            {
              "seed": 3,
              "value": 0.6267499999999999
            },
            {
              "seed": 4,
              "value": 0.649375
            },
            {
              "seed": 5,
              "value": 0.65275
            }
          ]
        },
        {
          "round": "R3",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.646375,
          "lo": 0.6317743070195974,
          "hi": 0.6609756929804027,
          "seeds": [
            {
              "seed": 1,
              "value": 0.632
            },
            {
              "seed": 2,
              "value": 0.6361249999999999
            },
            {
              "seed": 3,
              "value": 0.657625
            },
            {
              "seed": 4,
              "value": 0.6495000000000001
            },
            {
              "seed": 5,
              "value": 0.6566249999999999
            }
          ]
        },
        {
          "round": "R0",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.7062250000000001,
          "lo": 0.6728405926628818,
          "hi": 0.7396094073371184,
          "seeds": [
            {
              "seed": 1,
              "value": 0.6821250000000001
            },
            {
              "seed": 2,
              "value": 0.726
            },
            {
              "seed": 3,
              "value": 0.729375
            },
            {
              "seed": 4,
              "value": 0.721375
            },
            {
              "seed": 5,
              "value": 0.6722499999999999
            }
          ]
        },
        {
          "round": "R1",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.729825,
          "lo": 0.7036788776093877,
          "hi": 0.7559711223906121,
          "seeds": [
            {
              "seed": 1,
              "value": 0.7025
            },
            {
              "seed": 2,
              "value": 0.7165
            },
            {
              "seed": 3,
              "value": 0.730375
            },
            {
              "seed": 4,
              "value": 0.745125
            },
            {
              "seed": 5,
              "value": 0.7546250000000001
            }
          ]
        },
        {
          "round": "R2",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.714175,
          "lo": 0.6919445760178426,
          "hi": 0.7364054239821574,
          "seeds": [
            {
              "seed": 1,
              "value": 0.710125
            },
            {
              "seed": 2,
              "value": 0.691
            },
            {
              "seed": 3,
              "value": 0.7165
            },
            {
              "seed": 4,
              "value": 0.741
            },
            {
              "seed": 5,
              "value": 0.7122499999999999
            }
          ]
        },
        {
          "round": "R3",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.72255,
          "lo": 0.7071649801104264,
          "hi": 0.7379350198895737,
          "seeds": [
            {
              "seed": 1,
              "value": 0.7352500000000001
            },
            {
              "seed": 2,
              "value": 0.710875
            },
            {
              "seed": 3,
              "value": 0.7178749999999999
            },
            {
              "seed": 4,
              "value": 0.712375
            },
            {
              "seed": 5,
              "value": 0.736375
            }
          ]
        },
        {
          "round": "R0",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.7062250000000001,
          "lo": 0.6728405926628818,
          "hi": 0.7396094073371184,
          "seeds": [
            {
              "seed": 1,
              "value": 0.6821250000000001
            },
            {
              "seed": 2,
              "value": 0.726
            },
            {
              "seed": 3,
              "value": 0.729375
            },
            {
              "seed": 4,
              "value": 0.721375
            },
            {
              "seed": 5,
              "value": 0.6722499999999999
            }
          ]
        },
        {
          "round": "R1",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.740325,
          "lo": 0.6980672740530893,
          "hi": 0.7825827259469107,
          "seeds": [
            {
              "seed": 1,
              "value": 0.76075
            },
            {
              "seed": 2,
              "value": 0.72425
            },
            {
              "seed": 3,
              "value": 0.687625
            },
            {
              "seed": 4,
              "value": 0.762125
            },
            {
              "seed": 5,
              "value": 0.766875
            }
          ]
        },
        {
          "round": "R2",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.78865,
          "lo": 0.766613907295217,
          "hi": 0.810686092704783,
          "seeds": [
            {
              "seed": 1,
              "value": 0.7985
            },
            {
              "seed": 2,
              "value": 0.79475
            },
            {
              "seed": 3,
              "value": 0.8095
            },
            {
              "seed": 4,
              "value": 0.772875
            },
            {
              "seed": 5,
              "value": 0.767625
            }
          ]
        },
        {
          "round": "R3",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.796125,
          "lo": 0.7758143860274773,
          "hi": 0.8164356139725226,
          "seeds": [
            {
              "seed": 1,
              "value": 0.784
            },
            {
              "seed": 2,
              "value": 0.79375
            },
            {
              "seed": 3,
              "value": 0.820375
            },
            {
              "seed": 4,
              "value": 0.803125
            },
            {
              "seed": 5,
              "value": 0.779375
            }
          ]
        }
      ]
    },
    {
      "key": "sq_d1",
      "title": "Square-Broad",
      "points": [
        {
          "round": "R0",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.5089197999999999,
          "lo": 0.4867591402063748,
          "hi": 0.5310804597936251,
          "seeds": [
            {
              "seed": 1,
              "value": 0.500933
            },
            {
              "seed": 2,
              "value": 0.5364
            },
            {
              "seed": 3,
              "value": 0.48960000000000004
            },
            {
              "seed": 4,
              "value": 0.5152329999999999
            },
            {
              "seed": 5,
              "value": 0.502433
            }
          ]
        },
        {
          "round": "R1",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.6438733999999999,
          "lo": 0.6381981225181023,
          "hi": 0.6495486774818976,
          "seeds": [
            {
              "seed": 1,
              "value": 0.645633
            },
            {
              "seed": 2,
              "value": 0.6471330000000001
            },
            {
              "seed": 3,
              "value": 0.6461669999999999
            },
            {
              "seed": 4,
              "value": 0.635867
            },
            {
              "seed": 5,
              "value": 0.644567
            }
          ]
        },
        {
          "round": "R2",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.7107202000000001,
          "lo": 0.6787382867442845,
          "hi": 0.7427021132557158,
          "seeds": [
            {
              "seed": 1,
              "value": 0.718367
            },
            {
              "seed": 2,
              "value": 0.7427330000000001
            },
            {
              "seed": 3,
              "value": 0.715167
            },
            {
              "seed": 4,
              "value": 0.671667
            },
            {
              "seed": 5,
              "value": 0.7056669999999999
            }
          ]
        },
        {
          "round": "R3",
          "arm": "human_baseline_n1",
          "label": "HG-DAgger",
          "color": "#888888",
          "autonomous": false,
          "n": 5,
          "value": 0.7845866,
          "lo": 0.7353739293204433,
          "hi": 0.8337992706795567,
          "seeds": [
            {
              "seed": 1,
              "value": 0.8295669999999999
            },
            {
              "seed": 2,
              "value": 0.802733
            },
            {
              "seed": 3,
              "value": 0.7827
            },
            {
              "seed": 4,
              "value": 0.7219329999999999
            },
            {
              "seed": 5,
              "value": 0.7859999999999999
            }
          ]
        },
        {
          "round": "R0",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.4909466,
          "lo": 0.4696831936736522,
          "hi": 0.5122100063263478,
          "seeds": [
            {
              "seed": 1,
              "value": 0.488467
            },
            {
              "seed": 2,
              "value": 0.518333
            },
            {
              "seed": 3,
              "value": 0.470833
            },
            {
              "seed": 4,
              "value": 0.4879
            },
            {
              "seed": 5,
              "value": 0.4892
            }
          ]
        },
        {
          "round": "R1",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.6343932000000001,
          "lo": 0.6290366052860215,
          "hi": 0.6397497947139787,
          "seeds": [
            {
              "seed": 1,
              "value": 0.630533
            },
            {
              "seed": 2,
              "value": 0.6357
            },
            {
              "seed": 3,
              "value": 0.6403329999999999
            },
            {
              "seed": 4,
              "value": 0.6297999999999999
            },
            {
              "seed": 5,
              "value": 0.6356
            }
          ]
        },
        {
          "round": "R2",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.7051732,
          "lo": 0.6762503104530879,
          "hi": 0.734096089546912,
          "seeds": [
            {
              "seed": 1,
              "value": 0.7097
            },
            {
              "seed": 2,
              "value": 0.729933
            },
            {
              "seed": 3,
              "value": 0.709733
            },
            {
              "seed": 4,
              "value": 0.666533
            },
            {
              "seed": 5,
              "value": 0.709967
            }
          ]
        },
        {
          "round": "R3",
          "arm": "human_baseline_n32",
          "label": "HiL-IDQL",
          "color": "#5a5a5a",
          "autonomous": false,
          "n": 5,
          "value": 0.7858536,
          "lo": 0.7417885926280566,
          "hi": 0.8299186073719435,
          "seeds": [
            {
              "seed": 1,
              "value": 0.8315670000000001
            },
            {
              "seed": 2,
              "value": 0.794567
            },
            {
              "seed": 3,
              "value": 0.785067
            },
            {
              "seed": 4,
              "value": 0.7322669999999999
            },
            {
              "seed": 5,
              "value": 0.7857999999999999
            }
          ]
        },
        {
          "round": "R0",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.5422534,
          "lo": 0.5266801985367454,
          "hi": 0.5578266014632546,
          "seeds": [
            {
              "seed": 1,
              "value": 0.5474669999999999
            },
            {
              "seed": 2,
              "value": 0.526933
            },
            {
              "seed": 3,
              "value": 0.546567
            },
            {
              "seed": 4,
              "value": 0.532267
            },
            {
              "seed": 5,
              "value": 0.558033
            }
          ]
        },
        {
          "round": "R1",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.7284131999999999,
          "lo": 0.7077349805157783,
          "hi": 0.7490914194842214,
          "seeds": [
            {
              "seed": 1,
              "value": 0.719833
            },
            {
              "seed": 2,
              "value": 0.7577330000000001
            },
            {
              "seed": 3,
              "value": 0.7190000000000001
            },
            {
              "seed": 4,
              "value": 0.719333
            },
            {
              "seed": 5,
              "value": 0.7261669999999999
            }
          ]
        },
        {
          "round": "R2",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.8215197999999999,
          "lo": 0.8169334402243136,
          "hi": 0.8261061597756862,
          "seeds": [
            {
              "seed": 1,
              "value": 0.822133
            },
            {
              "seed": 2,
              "value": 0.8276330000000001
            },
            {
              "seed": 3,
              "value": 0.818233
            },
            {
              "seed": 4,
              "value": 0.820033
            },
            {
              "seed": 5,
              "value": 0.8195669999999999
            }
          ]
        },
        {
          "round": "R3",
          "arm": "ours_n1",
          "label": "HG-DAgger+Mulligan",
          "color": "#17becf",
          "autonomous": false,
          "n": 5,
          "value": 0.8603066,
          "lo": 0.8379034057001122,
          "hi": 0.8827097942998878,
          "seeds": [
            {
              "seed": 1,
              "value": 0.851567
            },
            {
              "seed": 2,
              "value": 0.8518330000000001
            },
            {
              "seed": 3,
              "value": 0.8909
            },
            {
              "seed": 4,
              "value": 0.8616330000000001
            },
            {
              "seed": 5,
              "value": 0.8456
            }
          ]
        },
        {
          "round": "R0",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.5253798,
          "lo": 0.5018404324045921,
          "hi": 0.5489191675954078,
          "seeds": [
            {
              "seed": 1,
              "value": 0.5204
            },
            {
              "seed": 2,
              "value": 0.5049
            },
            {
              "seed": 3,
              "value": 0.526833
            },
            {
              "seed": 4,
              "value": 0.518633
            },
            {
              "seed": 5,
              "value": 0.556133
            }
          ]
        },
        {
          "round": "R1",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.7167465999999999,
          "lo": 0.6947318832249529,
          "hi": 0.7387613167750469,
          "seeds": [
            {
              "seed": 1,
              "value": 0.704233
            },
            {
              "seed": 2,
              "value": 0.748067
            },
            {
              "seed": 3,
              "value": 0.709433
            },
            {
              "seed": 4,
              "value": 0.7106
            },
            {
              "seed": 5,
              "value": 0.7114
            }
          ]
        },
        {
          "round": "R2",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.8247932,
          "lo": 0.8188031355123528,
          "hi": 0.8307832644876472,
          "seeds": [
            {
              "seed": 1,
              "value": 0.820333
            },
            {
              "seed": 2,
              "value": 0.8327
            },
            {
              "seed": 3,
              "value": 0.8245669999999999
            },
            {
              "seed": 4,
              "value": 0.8215330000000001
            },
            {
              "seed": 5,
              "value": 0.824833
            }
          ]
        },
        {
          "round": "R3",
          "arm": "ours_n32",
          "label": "HiL-IDQL+Mulligan",
          "color": "#9467bd",
          "autonomous": false,
          "n": 5,
          "value": 0.8628798,
          "lo": 0.8406100568252698,
          "hi": 0.8851495431747302,
          "seeds": [
            {
              "seed": 1,
              "value": 0.854733
            },
            {
              "seed": 2,
              "value": 0.853433
            },
            {
              "seed": 3,
              "value": 0.894333
            },
            {
              "seed": 4,
              "value": 0.8607330000000001
            },
            {
              "seed": 5,
              "value": 0.8511669999999999
            }
          ]
        },
        {
          "round": "R0",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.4909466,
          "lo": 0.4696831936736522,
          "hi": 0.5122100063263478,
          "seeds": [
            {
              "seed": 1,
              "value": 0.488467
            },
            {
              "seed": 2,
              "value": 0.518333
            },
            {
              "seed": 3,
              "value": 0.470833
            },
            {
              "seed": 4,
              "value": 0.4879
            },
            {
              "seed": 5,
              "value": 0.4892
            }
          ]
        },
        {
          "round": "R1",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.49315320000000007,
          "lo": 0.4743726553778152,
          "hi": 0.5119337446221849,
          "seeds": [
            {
              "seed": 1,
              "value": 0.487433
            },
            {
              "seed": 2,
              "value": 0.474833
            },
            {
              "seed": 3,
              "value": 0.4868
            },
            {
              "seed": 4,
              "value": 0.503633
            },
            {
              "seed": 5,
              "value": 0.5130669999999999
            }
          ]
        },
        {
          "round": "R2",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.48368,
          "lo": 0.4811901342464224,
          "hi": 0.4861698657535776,
          "seeds": [
            {
              "seed": 1,
              "value": 0.485733
            },
            {
              "seed": 2,
              "value": 0.481833
            },
            {
              "seed": 3,
              "value": 0.484067
            },
            {
              "seed": 4,
              "value": 0.481367
            },
            {
              "seed": 5,
              "value": 0.4854
            }
          ]
        },
        {
          "round": "R3",
          "arm": "auto_plain_il_n1",
          "label": "Autonomous IL",
          "color": "#d4a017",
          "autonomous": true,
          "n": 5,
          "value": 0.46905339999999995,
          "lo": 0.4359547761167607,
          "hi": 0.5021520238832392,
          "seeds": [
            {
              "seed": 1,
              "value": 0.434133
            },
            {
              "seed": 2,
              "value": 0.448167
            },
            {
              "seed": 3,
              "value": 0.4914
            },
            {
              "seed": 4,
              "value": 0.493767
            },
            {
              "seed": 5,
              "value": 0.4778
            }
          ]
        },
        {
          "round": "R0",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.4909466,
          "lo": 0.4696831936736522,
          "hi": 0.5122100063263478,
          "seeds": [
            {
              "seed": 1,
              "value": 0.488467
            },
            {
              "seed": 2,
              "value": 0.518333
            },
            {
              "seed": 3,
              "value": 0.470833
            },
            {
              "seed": 4,
              "value": 0.4879
            },
            {
              "seed": 5,
              "value": 0.4892
            }
          ]
        },
        {
          "round": "R1",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.49205319999999997,
          "lo": 0.47812901047800976,
          "hi": 0.5059773895219902,
          "seeds": [
            {
              "seed": 1,
              "value": 0.5039
            },
            {
              "seed": 2,
              "value": 0.48523299999999997
            },
            {
              "seed": 3,
              "value": 0.504
            },
            {
              "seed": 4,
              "value": 0.479733
            },
            {
              "seed": 5,
              "value": 0.4874
            }
          ]
        },
        {
          "round": "R2",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.5158666000000001,
          "lo": 0.4892863662679896,
          "hi": 0.5424468337320105,
          "seeds": [
            {
              "seed": 1,
              "value": 0.479633
            },
            {
              "seed": 2,
              "value": 0.517167
            },
            {
              "seed": 3,
              "value": 0.5235
            },
            {
              "seed": 4,
              "value": 0.5229
            },
            {
              "seed": 5,
              "value": 0.536133
            }
          ]
        },
        {
          "round": "R3",
          "arm": "auto_filtered_bc_n1",
          "label": "Filtered BC",
          "color": "#e76f51",
          "autonomous": true,
          "n": 5,
          "value": 0.5274136,
          "lo": 0.5128094138805861,
          "hi": 0.542017786119414,
          "seeds": [
            {
              "seed": 1,
              "value": 0.5363669999999999
            },
            {
              "seed": 2,
              "value": 0.527167
            },
            {
              "seed": 3,
              "value": 0.516667
            },
            {
              "seed": 4,
              "value": 0.5151
            },
            {
              "seed": 5,
              "value": 0.541767
            }
          ]
        },
        {
          "round": "R0",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.4909466,
          "lo": 0.4696831936736522,
          "hi": 0.5122100063263478,
          "seeds": [
            {
              "seed": 1,
              "value": 0.488467
            },
            {
              "seed": 2,
              "value": 0.518333
            },
            {
              "seed": 3,
              "value": 0.470833
            },
            {
              "seed": 4,
              "value": 0.4879
            },
            {
              "seed": 5,
              "value": 0.4892
            }
          ]
        },
        {
          "round": "R1",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.5511,
          "lo": 0.5190618664517593,
          "hi": 0.5831381335482407,
          "seeds": [
            {
              "seed": 1,
              "value": 0.5241
            },
            {
              "seed": 2,
              "value": 0.528767
            },
            {
              "seed": 3,
              "value": 0.587933
            },
            {
              "seed": 4,
              "value": 0.556833
            },
            {
              "seed": 5,
              "value": 0.557867
            }
          ]
        },
        {
          "round": "R2",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.5757666,
          "lo": 0.5391026070566377,
          "hi": 0.6124305929433623,
          "seeds": [
            {
              "seed": 1,
              "value": 0.557833
            },
            {
              "seed": 2,
              "value": 0.555667
            },
            {
              "seed": 3,
              "value": 0.5604330000000001
            },
            {
              "seed": 4,
              "value": 0.625933
            },
            {
              "seed": 5,
              "value": 0.578967
            }
          ]
        },
        {
          "round": "R3",
          "arm": "auto_iql_n32",
          "label": "Batch-online IDQL",
          "color": "#8c564b",
          "autonomous": true,
          "n": 5,
          "value": 0.5861402,
          "lo": 0.5684077057993665,
          "hi": 0.6038726942006335,
          "seeds": [
            {
              "seed": 1,
              "value": 0.575767
            },
            {
              "seed": 2,
              "value": 0.6062
            },
            {
              "seed": 3,
              "value": 0.5821999999999999
            },
            {
              "seed": 4,
              "value": 0.571567
            },
            {
              "seed": 5,
              "value": 0.594967
            }
          ]
        }
      ]
    }
  ]
}
