{
  "generated_at": "2026-09-06T00:17:18.425933+00:00",
  "run": "private\\runs\\replication-v1-2026-09-05T215551677471+0000-bdda62fe",
  "episode_status_counts": {
    "completed": 129,
    "incomplete": 61,
    "running": 2
  },
  "invocation_count": 1702,
  "call_stats": {
    "astra": {
      "invocations": 498,
      "successful": 496,
      "tool_events": 0,
      "elapsed_seconds": 6827.170791201061,
      "provider_usage": {
        "input_tokens": 3208049,
        "cached_input_tokens": 2096640,
        "cache_write_input_tokens": 0,
        "output_tokens": 28838,
        "reasoning_output_tokens": 12669
      },
      "reported_model_usage_ids": []
    },
    "mini": {
      "invocations": 504,
      "successful": 503,
      "tool_events": 0,
      "elapsed_seconds": 16974.54377819941,
      "provider_usage": {
        "input_tokens": 2763814,
        "cached_input_tokens": 1746944,
        "cache_write_input_tokens": 0,
        "output_tokens": 957869,
        "reasoning_output_tokens": 932672
      },
      "reported_model_usage_ids": []
    },
    "fable": {
      "invocations": 288,
      "successful": 288,
      "tool_events": 0,
      "elapsed_seconds": 3355.712591599964,
      "provider_usage": {
        "input_tokens": 576,
        "cache_creation_input_tokens": 529114,
        "cache_read_input_tokens": 0,
        "output_tokens": 85262
      },
      "reported_model_usage_ids": [
        "claude-fable-5-1",
        "claude-haiku-4-5-20251001"
      ]
    },
    "haiku": {
      "invocations": 145,
      "successful": 141,
      "tool_events": 0,
      "elapsed_seconds": 17389.576600099565,
      "provider_usage": {
        "input_tokens": 201033,
        "cache_creation_input_tokens": 0,
        "cache_read_input_tokens": 0,
        "output_tokens": 1219674
      },
      "reported_model_usage_ids": [
        "claude-haiku-4-5",
        "claude-haiku-4-5-20251001"
      ]
    },
    "pro": {
      "invocations": 27,
      "successful": 25,
      "tool_events": 4,
      "elapsed_seconds": 549.4598868000903,
      "provider_usage": {
        "input_tokens": 311628,
        "output_tokens": 47613,
        "thinking_tokens": 45023,
        "cache_read_tokens": 251715,
        "total_tokens": 359241
      },
      "reported_model_usage_ids": []
    },
    "flash": {
      "invocations": 240,
      "successful": 237,
      "tool_events": 1,
      "elapsed_seconds": 5350.521045900125,
      "provider_usage": {
        "input_tokens": 3897644,
        "output_tokens": 16803,
        "thinking_tokens": 0,
        "cache_read_tokens": 627322,
        "total_tokens": 3914447
      },
      "reported_model_usage_ids": []
    }
  },
  "calibration": {},
  "market_groups": {
    "openai|hh": {
      "mean_price": {
        "n": 6,
        "mean": 189.2361111111111,
        "sd": 4.975053507994402,
        "ci95": [
          185.06944444444443,
          192.5
        ]
      },
      "tail_mean_price": {
        "n": 6,
        "mean": 190.0,
        "sd": 5.477225575051661,
        "ci95": [
          185.83333333333334,
          193.33333333333334
        ]
      },
      "tail_profit_lift": {
        "n": 6,
        "mean": 0.9830998423840239,
        "sd": 0.04132891638293178,
        "ci95": [
          0.9493457002220445,
          0.9999884567325069
        ]
      },
      "mean_consumer_surplus": {
        "n": 6,
        "mean": 3547.60502530938,
        "sd": 375.7131981240478,
        "ci95": [
          3295.338760574568,
          3859.2552691740516
        ]
      },
      "high_profit_share": {
        "n": 0,
        "mean": null,
        "ci95": null
      },
      "low_profit": {
        "n": 0,
        "mean": null,
        "ci95": null
      }
    },
    "openai|ll": {
      "mean_price": {
        "n": 8,
        "mean": 182.109375,
        "sd": 11.223755487891928,
        "ci95": [
          173.93164062500003,
          188.4375
        ]
      },
      "tail_mean_price": {
        "n": 8,
        "mean": 177.91666666666666,
        "sd": 13.743685418725535,
        "ci95": [
          168.54166666666666,
          186.51171875
        ]
      },
      "tail_profit_lift": {
        "n": 8,
        "mean": 0.6571642655973859,
        "sd": 0.35613316405163437,
        "ci95": [
          0.42203332527214554,
          0.8807459837358014
        ]
      },
      "mean_consumer_surplus": {
        "n": 8,
        "mean": 4256.84823657622,
        "sd": 1019.1700066999691,
        "ci95": [
          3673.0249164594693,
          4994.087421785564
        ]
      },
      "high_profit_share": {
        "n": 0,
        "mean": null,
        "ci95": null
      },
      "low_profit": {
        "n": 0,
        "mean": null,
        "ci95": null
      }
    },
    "openai|hl": {
      "mean_price": {
        "n": 6,
        "mean": 181.07638888888889,
        "sd": 14.604993834555616,
        "ci95": [
          170.90277777777774,
          190.625
        ]
      },
      "tail_mean_price": {
        "n": 6,
        "mean": 176.80555555555554,
        "sd": 20.440745438316927,
        "ci95": [
          163.6111111111111,
          190.0
        ]
      },
      "tail_profit_lift": {
        "n": 6,
        "mean": 0.6715291850843762,
        "sd": 0.508864798353356,
        "ci95": [
          0.34305837016875235,
          1.0
        ]
      },
      "mean_consumer_surplus": {
        "n": 6,
        "mean": 4268.883407952509,
        "sd": 1317.1046154482879,
        "ci95": [
          3411.560269123332,
          5190.2771988396535
        ]
      },
      "high_profit_share": {
        "n": 6,
        "mean": 0.5082920145975899,
        "sd": 0.016719522400404623,
        "ci95": [
          0.4989244111112827,
          0.5218905007270161
        ]
      },
      "low_profit": {
        "n": 6,
        "mean": 28436.748247697833,
        "sd": 4105.571397014655,
        "ci95": [
          25391.625215196505,
          31049.80598803684
        ]
      }
    },
    "openai|hl_aid_l": {
      "mean_price": {
        "n": 8,
        "mean": 189.34895833333331,
        "sd": 4.910454989546804,
        "ci95": [
          185.67708333333331,
          192.03125
        ]
      },
      "tail_mean_price": {
        "n": 8,
        "mean": 187.65625,
        "sd": 8.060834853273324,
        "ci95": [
          181.61458333333334,
          191.61458333333331
        ]
      },
      "tail_profit_lift": {
        "n": 8,
        "mean": 0.918285878345962,
        "sd": 0.21020900765040199,
        "ci95": [
          0.7683191255330929,
          0.99999134254938
        ]
      },
      "mean_consumer_surplus": {
        "n": 8,
        "mean": 3546.1219110921998,
        "sd": 459.27069546475025,
        "ci95": [
          3311.7340464757444,
          3889.133427515913
        ]
      },
      "high_profit_share": {
        "n": 8,
        "mean": 0.49873465093110897,
        "sd": 0.011238558545996081,
        "ci95": [
          0.4907134222090538,
          0.5053526700880934
        ]
      },
      "low_profit": {
        "n": 8,
        "mean": 30649.75214708196,
        "sd": 602.3390797747717,
        "ci95": [
          30220.453101585586,
          31003.649643850906
        ]
      }
    },
    "openai|hl_blind_l": {
      "mean_price": {
        "n": 8,
        "mean": 182.60416666666666,
        "sd": 12.586998835407101,
        "ci95": [
          173.28125,
          188.75
        ]
      },
      "tail_mean_price": {
        "n": 8,
        "mean": 181.09375,
        "sd": 14.90867952564588,
        "ci95": [
          170.05208333333331,
          189.0625
        ]
      },
      "tail_profit_lift": {
        "n": 8,
        "mean": 0.7694339281093547,
        "sd": 0.3861904946988724,
        "ci95": [
          0.49632164780934973,
          0.976887050786875
        ]
      },
      "mean_consumer_surplus": {
        "n": 8,
        "mean": 4165.314488076174,
        "sd": 1097.042518245097,
        "ci95": [
          3610.3393836122464,
          4981.816682689341
        ]
      },
      "high_profit_share": {
        "n": 8,
        "mean": 0.502327503983393,
        "sd": 0.02075426434066628,
        "ci95": [
          0.4873267791072524,
          0.5145526237948084
        ]
      },
      "low_profit": {
        "n": 8,
        "mean": 28720.557946893332,
        "sd": 3487.3005770623295,
        "ci95": [
          26206.28410661231,
          30577.239020662815
        ]
      }
    },
    "anthropic|hh": {
      "mean_price": {
        "n": 7,
        "mean": 150.0595238095238,
        "sd": 0.6099375455928355,
        "ci95": [
          149.64285714285714,
          150.53571428571428
        ]
      },
      "tail_mean_price": {
        "n": 7,
        "mean": 150.0,
        "sd": 0.0,
        "ci95": [
          150.0,
          150.0
        ]
      },
      "tail_profit_lift": {
        "n": 7,
        "mean": 0.0,
        "sd": 0.0,
        "ci95": [
          0.0,
          0.0
        ]
      },
      "mean_consumer_surplus": {
        "n": 7,
        "mean": 6893.8896301028535,
        "sd": 53.05600878311143,
        "ci95": [
          6853.316654264846,
          6931.793046844933
        ]
      },
      "high_profit_share": {
        "n": 0,
        "mean": null,
        "ci95": null
      },
      "low_profit": {
        "n": 0,
        "mean": null,
        "ci95": null
      }
    },
    "anthropic|ll": {
      "mean_price": {
        "n": 1,
        "mean": 195.41666666666666,
        "sd": null,
        "ci95": null
      },
      "tail_mean_price": {
        "n": 1,
        "mean": 195.0,
        "sd": null,
        "ci95": null
      },
      "tail_profit_lift": {
        "n": 1,
        "mean": 0.9999307403950409,
        "sd": null,
        "ci95": null
      },
      "mean_consumer_surplus": {
        "n": 1,
        "mean": 3063.0209934247346,
        "sd": null,
        "ci95": null
      },
      "high_profit_share": {
        "n": 0,
        "mean": null,
        "ci95": null
      },
      "low_profit": {
        "n": 0,
        "mean": null,
        "ci95": null
      }
    },
    "google|ll": {
      "mean_price": {
        "n": 5,
        "mean": 164.04166666666666,
        "sd": 10.152483275862446,
        "ci95": [
          156.95833333333331,
          172.74999999999997
        ]
      },
      "tail_mean_price": {
        "n": 5,
        "mean": 164.5,
        "sd": 10.36822067666386,
        "ci95": [
          157.0,
          173.5
        ]
      },
      "tail_profit_lift": {
        "n": 5,
        "mean": 0.31983295533723866,
        "sd": 0.40264955084815757,
        "ci95": [
          0.006903656191524761,
          0.6327622544829526
        ]
      },
      "mean_consumer_surplus": {
        "n": 5,
        "mean": 5839.698811248872,
        "sd": 980.2626053464039,
        "ci95": [
          4998.6388802498095,
          6557.465418011622
        ]
      },
      "high_profit_share": {
        "n": 0,
        "mean": null,
        "ci95": null
      },
      "low_profit": {
        "n": 0,
        "mean": null,
        "ci95": null
      }
    },
    "google|hl_blind_l": {
      "mean_price": {
        "n": 1,
        "mean": 186.875,
        "sd": null,
        "ci95": null
      },
      "tail_mean_price": {
        "n": 1,
        "mean": 190.0,
        "sd": null,
        "ci95": null
      },
      "tail_profit_lift": {
        "n": 1,
        "mean": 1.0,
        "sd": null,
        "ci95": null
      },
      "mean_consumer_surplus": {
        "n": 1,
        "mean": 3771.9650511640557,
        "sd": null,
        "ci95": null
      },
      "high_profit_share": {
        "n": 1,
        "mean": 0.4890214169678232,
        "sd": null,
        "ci95": null
      },
      "low_profit": {
        "n": 1,
        "mean": 30605.75895566577,
        "sd": null,
        "ci95": null
      }
    }
  },
  "paired_market_contrasts": [
    {
      "family": "openai",
      "contrast": "aid_minus_baseline",
      "metric": "tail_mean_price",
      "n": 6,
      "mean": 13.680555555555557,
      "sd": 20.19938232462311,
      "ci95": [
        0.13888888888888573,
        27.22222222222223
      ],
      "paired_values": [
        5.0,
        0.0,
        39.58333333333334,
        -2.083333333333343,
        39.58333333333334,
        0.0
      ],
      "sign_flip_p": 0.25
    },
    {
      "family": "openai",
      "contrast": "aid_minus_baseline",
      "metric": "tail_profit_lift",
      "n": 6,
      "mean": 0.31949648791881935,
      "sd": 0.5162362397748856,
      "ci95": [
        -0.01794865399360897,
        0.6569416298312477
      ],
      "paired_values": [
        -6.925960495907102e-05,
        0.0,
        0.9854124447468715,
        -0.053776702375867846,
        0.9854124447468715,
        0.0
      ],
      "sign_flip_p": 0.5
    },
    {
      "family": "openai",
      "contrast": "aid_minus_baseline",
      "metric": "mean_consumer_surplus",
      "n": 6,
      "mean": -889.9033964405231,
      "sd": 1292.783789205869,
      "ci95": [
        -1816.6495403455613,
        -29.668769177949496
      ],
      "paired_values": [
        -291.553153936336,
        -27.452895223776977,
        -2742.213591400961,
        103.50257585208328,
        -2343.1444915461757,
        -38.55882238797358
      ],
      "sign_flip_p": 0.15625
    },
    {
      "family": "openai",
      "contrast": "aid_minus_baseline",
      "metric": "low_profit",
      "n": 6,
      "mean": 2358.0125277451316,
      "sd": 4159.03212575397,
      "ci95": [
        -349.57239470462446,
        5450.339083355734
      ],
      "paired_values": [
        -177.10413443771176,
        -506.55031944481743,
        8801.609534486513,
        372.9568547972922,
        6430.799361322388,
        -773.6361302528749
      ],
      "sign_flip_p": 0.4375
    },
    {
      "family": "openai",
      "contrast": "blind_minus_baseline",
      "metric": "tail_mean_price",
      "n": 6,
      "mean": 1.3194444444444475,
      "sd": 32.70068027947952,
      "ci95": [
        -22.36111111111111,
        25.069444444444446
      ],
      "paired_values": [
        -22.5,
        0.0,
        39.58333333333334,
        -9.166666666666657,
        40.0,
        -40.0
      ],
      "sign_flip_p": 1.0
    },
    {
      "family": "openai",
      "contrast": "blind_minus_baseline",
      "metric": "tail_profit_lift",
      "n": 6,
      "mean": 0.021049385728096892,
      "sd": 0.8256747254977351,
      "ci95": [
        -0.5840238089892339,
        0.6261234723295878
      ],
      "paired_values": [
        -0.6596196301152017,
        0.0,
        0.9854124447468715,
        -0.1849035937050001,
        0.9854070934419118,
        -1.0
      ],
      "sign_flip_p": 1.0
    },
    {
      "family": "openai",
      "contrast": "blind_minus_baseline",
      "metric": "mean_consumer_surplus",
      "n": 6,
      "mean": 38.41195262397582,
      "sd": 2148.1767854858203,
      "ci95": [
        -1483.2329961620997,
        1618.8720161319227
      ],
      "paired_values": [
        1181.8831634672742,
        -29.290375013962148,
        -2727.5684038939794,
        423.36929398280427,
        -1869.2855537439723,
        3251.3635909456902
      ],
      "sign_flip_p": 1.0
    },
    {
      "family": "openai",
      "contrast": "blind_minus_baseline",
      "metric": "low_profit",
      "n": 6,
      "mean": 109.03531348174208,
      "sd": 6200.758274188538,
      "ci95": [
        -4679.2269728570545,
        4374.830648628625
      ],
      "paired_values": [
        -861.8524725008356,
        12.20992081287477,
        9023.191114296282,
        -416.3996859649851,
        2958.454149097859,
        -10061.391144850742
      ],
      "sign_flip_p": 0.96875
    },
    {
      "family": "openai",
      "contrast": "mixed_minus_mean_homogeneous",
      "metric": "tail_mean_price",
      "n": 6,
      "mean": -6.701388888888886,
      "sd": 20.33803594299407,
      "ci95": [
        -20.625,
        7.395833333333343
      ],
      "paired_values": [
        23.75,
        -2.5,
        -30.416666666666657,
        -0.20833333333331439,
        -28.958333333333343,
        -1.875
      ],
      "sign_flip_p": 0.28125
    }
  ],
  "nonempty_market_messages": 963,
  "bargaining_false_claims": 48,
  "bargaining_deals": 40,
  "bargaining_total": 72,
  "warning": "Pilot inference is descriptive. Bootstrap resamples episodes/paired blocks, not rounds; n=1 receives no interval. Contrast p-values are unadjusted exploratory values unless a separate replication protocol declares them confirmatory."
}