{
  "observed_at_utc": "2026-10-12T20:48:25.786892+00:00",
  "status": "interim_incomplete_cohort",
  "source_commit": "612145f915d524d75c600f14db763544272e1d83",
  "planned_profiles": 155,
  "completed_profiles": 16,
  "note": "Dated snapshot; do not interpret completion-conditioned means or single seeds as method rankings. Gradient diagnostics measure sampled actor terms, not true on-policy gradient bias.",
  "profiles": [
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "cer",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.0,
      "sum_satisfaction": 0.0,
      "train_seconds": 2348.343902438879,
      "eval_seconds": 27.33870017528534,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "b62afe5b7c116b79540a59fe9740c7fb8eb4a34e1c902551e5fb234efc8ee269"
    },
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "corrected",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.0,
      "sum_satisfaction": 0.0,
      "train_seconds": 2395.0265142917633,
      "eval_seconds": 26.90594481676817,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "e3374098e6942c775c4677402b388d5c12a84a146f72b9f0188e52fc4739f441"
    },
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "critic_only",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.0,
      "sum_satisfaction": 0.0,
      "train_seconds": 2676.3229393586516,
      "eval_seconds": 26.736789748072624,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "d8d29ac42b087737c66fa17f8326e80c71002c877e824434e2e3f62a21d7597a"
    },
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "no_cer",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.024,
          "successes": 24,
          "lower": 0.0,
          "upper": 0.08752521581540601,
          "threshold": 0.9,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.024,
          "successes": 24,
          "lower": 0.0,
          "upper": 0.08752521581540601,
          "threshold": 0.9,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.024,
      "sum_satisfaction": 0.048,
      "train_seconds": 1836.63276027143,
      "eval_seconds": 29.287711679935455,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "ef03b5ac51edcb14801f7abdfa26a0b312a84840962bb6a69213e703c8315d84"
    },
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "rm_shaping",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 1.0,
          "successes": 1000,
          "lower": 0.936474784184594,
          "upper": 1.0,
          "threshold": 0.9,
          "certified": true
        },
        "player_1": {
          "p_hat": 1.0,
          "successes": 1000,
          "lower": 0.936474784184594,
          "upper": 1.0,
          "threshold": 0.9,
          "certified": true
        }
      },
      "jointly_certified": true,
      "minimum_satisfaction": 1.0,
      "sum_satisfaction": 2.0,
      "train_seconds": 1722.5220955237746,
      "eval_seconds": 29.976837791502476,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "d3c4533ed6879034eab86daa8f6073526a0837651308b89957ec5e4834deac80"
    },
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "cer",
      "seed": 101,
      "per_agent": {
        "player_0": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.0,
      "sum_satisfaction": 0.0,
      "train_seconds": 2618.05798882246,
      "eval_seconds": 27.688456535339355,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "df5de9dcb54d5e5cb7edfacc4a4c248ba629c60570e73e198cd326bf53e7f1ce"
    },
    {
      "case": "stag_hunt",
      "learner": "pr2_ippo",
      "mode": "no_cer",
      "seed": 101,
      "per_agent": {
        "player_0": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.063525215815406,
          "threshold": 0.9,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.0,
      "sum_satisfaction": 0.0,
      "train_seconds": 1659.571686834097,
      "eval_seconds": 28.07329823076725,
      "family_size": 40,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "ae01df9e8858ae35369b47e8c024fe508198bfe3671a7c710eddbddb783d43de"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "cer",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.924,
          "successes": 924,
          "lower": 0.8623522001222181,
          "upper": 0.985647799877782,
          "threshold": 0.25,
          "certified": true
        },
        "player_1": {
          "p_hat": 0.064,
          "successes": 64,
          "lower": 0.002352200122218144,
          "upper": 0.12564779987778185,
          "threshold": 0.2,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.064,
      "sum_satisfaction": 0.988,
      "train_seconds": 6484.838539218064,
      "eval_seconds": 1562.658158404287,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "67bac5921c5eb40534304434c29bc495f88e3bdfd3bde3c1333bdf267c3e092c"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "corrected",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.229,
          "successes": 229,
          "lower": 0.16735220012221816,
          "upper": 0.2906477998777819,
          "threshold": 0.25,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.733,
          "successes": 733,
          "lower": 0.6713522001222181,
          "upper": 0.7946477998777819,
          "threshold": 0.2,
          "certified": true
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.229,
      "sum_satisfaction": 0.962,
      "train_seconds": 6508.442820666358,
      "eval_seconds": 1577.5301396562718,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "64f460919ff6439b7913bdea3cae9679d2c920ccbb628cff99fd7716000f1cb7"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "critic_only",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.0,
          "successes": 0,
          "lower": 0.0,
          "upper": 0.06164779987778186,
          "threshold": 0.25,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.999,
          "successes": 999,
          "lower": 0.9373522001222181,
          "upper": 1.0,
          "threshold": 0.2,
          "certified": true
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.0,
      "sum_satisfaction": 0.999,
      "train_seconds": 6465.878381901886,
      "eval_seconds": 1556.0090998131782,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "76a4b52de70af1890d6774661c60c137647e5886e371e36ad9a79ba870454d71"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "no_cer",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.807,
          "successes": 807,
          "lower": 0.7453522001222181,
          "upper": 0.868647799877782,
          "threshold": 0.25,
          "certified": true
        },
        "player_1": {
          "p_hat": 0.178,
          "successes": 178,
          "lower": 0.11635220012221814,
          "upper": 0.23964779987778184,
          "threshold": 0.2,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.178,
      "sum_satisfaction": 0.9850000000000001,
      "train_seconds": 6974.16438806802,
      "eval_seconds": 1755.403563410975,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "c49d60c44c0c4325a01b1ba04e3259f6c605f006ff6ced6ca2c00f805d9b66cf"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "rm_shaping",
      "seed": 100,
      "per_agent": {
        "player_0": {
          "p_hat": 0.59,
          "successes": 590,
          "lower": 0.5283522001222181,
          "upper": 0.6516477998777819,
          "threshold": 0.25,
          "certified": true
        },
        "player_1": {
          "p_hat": 0.366,
          "successes": 366,
          "lower": 0.30435220012221814,
          "upper": 0.42764779987778184,
          "threshold": 0.2,
          "certified": true
        }
      },
      "jointly_certified": true,
      "minimum_satisfaction": 0.366,
      "sum_satisfaction": 0.956,
      "train_seconds": 6312.894241899252,
      "eval_seconds": 1738.4824618026614,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "ec17be375f0a5c6f8d2be94cce449654166bdf2ea253d13cb2fe02f0f74eea85"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "cer",
      "seed": 101,
      "per_agent": {
        "player_0": {
          "p_hat": 0.054,
          "successes": 54,
          "lower": 0.0,
          "upper": 0.11564779987778186,
          "threshold": 0.25,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.707,
          "successes": 707,
          "lower": 0.6453522001222181,
          "upper": 0.7686477998777819,
          "threshold": 0.2,
          "certified": true
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.054,
      "sum_satisfaction": 0.761,
      "train_seconds": 6366.937688797712,
      "eval_seconds": 1565.1352970525622,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "a2041a2a673d0ec38650010eace66d19c528cba9f46682a7405e87c4e7290ae1"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "corrected",
      "seed": 101,
      "per_agent": {
        "player_0": {
          "p_hat": 0.923,
          "successes": 923,
          "lower": 0.8613522001222181,
          "upper": 0.984647799877782,
          "threshold": 0.25,
          "certified": true
        },
        "player_1": {
          "p_hat": 0.031,
          "successes": 31,
          "lower": 0.0,
          "upper": 0.09264779987778185,
          "threshold": 0.2,
          "certified": false
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.031,
      "sum_satisfaction": 0.9540000000000001,
      "train_seconds": 6656.766051992774,
      "eval_seconds": 1683.6616984456778,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "2fb7312282e79ac9c94c0135365d00c02f02e37cbef06289962be403c6581fd9"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "critic_only",
      "seed": 101,
      "per_agent": {
        "player_0": {
          "p_hat": 0.22,
          "successes": 220,
          "lower": 0.15835220012221815,
          "upper": 0.2816477998777819,
          "threshold": 0.25,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.54,
          "successes": 540,
          "lower": 0.4783522001222182,
          "upper": 0.6016477998777819,
          "threshold": 0.2,
          "certified": true
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.22,
      "sum_satisfaction": 0.76,
      "train_seconds": 6402.205967985094,
      "eval_seconds": 1645.9447301477194,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "53e6accc86fd69798f46fa724e15e7257d6d34c57e7408b73c0390b3c1c87909"
    },
    {
      "case": "territory",
      "learner": "ippo",
      "mode": "no_cer",
      "seed": 101,
      "per_agent": {
        "player_0": {
          "p_hat": 0.274,
          "successes": 274,
          "lower": 0.21235220012221817,
          "upper": 0.33564779987778187,
          "threshold": 0.25,
          "certified": false
        },
        "player_1": {
          "p_hat": 0.709,
          "successes": 709,
          "lower": 0.6473522001222181,
          "upper": 0.7706477998777819,
          "threshold": 0.2,
          "certified": true
        }
      },
      "jointly_certified": false,
      "minimum_satisfaction": 0.274,
      "sum_satisfaction": 0.983,
      "train_seconds": 6031.014965467155,
      "eval_seconds": 1628.2661053091288,
      "family_size": 25,
      "source_commit": "612145f915d524d75c600f14db763544272e1d83",
      "configuration_fingerprint": "f8102db830461df35d69ed769441bbb9def8fff5530e7fd3c263dcf7624c1202"
    }
  ],
  "seed100_gradient_diagnostics": {
    "territory/cer": {
      "player_0": {
        "log_rho_rms_max": 0.00033490557689219713,
        "rho_ess_fraction_min": 0.9999998807907104,
        "rho_mean_min": 0.9999025464057922,
        "valid_gradient_windows": 40,
        "negative_cosine_windows": 1,
        "mean_gradient_cosine": 0.7244439624249935,
        "median_factual_gradient_norm": 0.33339475095272064,
        "median_synthetic_gradient_norm": 0.28090696036815643
      },
      "player_1": {
        "log_rho_rms_max": 0.00039664009818807244,
        "rho_ess_fraction_min": 0.9999999403953552,
        "rho_mean_min": 0.9999028444290161,
        "valid_gradient_windows": 40,
        "negative_cosine_windows": 5,
        "mean_gradient_cosine": 0.6186660774052143,
        "median_factual_gradient_norm": 0.2849724292755127,
        "median_synthetic_gradient_norm": 0.18465226143598557
      }
    },
    "territory/critic_only": {
      "player_0": {
        "log_rho_rms_max": 0.0004005683003924787,
        "rho_ess_fraction_min": 0.9999999403953552,
        "rho_mean_min": 0.9998756647109985,
        "valid_gradient_windows": 40,
        "negative_cosine_windows": 2,
        "mean_gradient_cosine": 0.7243207825347782,
        "median_factual_gradient_norm": 0.35115566849708557,
        "median_synthetic_gradient_norm": 0.23569093644618988
      },
      "player_1": {
        "log_rho_rms_max": 0.0002633355325087905,
        "rho_ess_fraction_min": 0.9999999403953552,
        "rho_mean_min": 0.9999421834945679,
        "valid_gradient_windows": 40,
        "negative_cosine_windows": 5,
        "mean_gradient_cosine": 0.6237334773177281,
        "median_factual_gradient_norm": 0.24749091267585754,
        "median_synthetic_gradient_norm": 0.1683749556541443
      }
    },
    "territory/corrected": {
      "player_0": {
        "log_rho_rms_max": 0.00036970636574551463,
        "rho_ess_fraction_min": 0.9999999403953552,
        "rho_mean_min": 0.9999157190322876,
        "valid_gradient_windows": 40,
        "negative_cosine_windows": 3,
        "mean_gradient_cosine": 0.62949272794649,
        "median_factual_gradient_norm": 0.3629699796438217,
        "median_synthetic_gradient_norm": 0.23002073913812637
      },
      "player_1": {
        "log_rho_rms_max": 0.0008784960955381393,
        "rho_ess_fraction_min": 0.9999997615814209,
        "rho_mean_min": 0.9997113943099976,
        "valid_gradient_windows": 40,
        "negative_cosine_windows": 5,
        "mean_gradient_cosine": 0.5480744427535683,
        "median_factual_gradient_norm": 0.33823955059051514,
        "median_synthetic_gradient_norm": 0.21164736151695251
      }
    },
    "stag_hunt/cer": {
      "player_0": {
        "log_rho_rms_max": 0.15051770210266113,
        "rho_ess_fraction_min": 0.9932689070701599,
        "rho_mean_min": 0.9892470240592957,
        "valid_gradient_windows": 98,
        "negative_cosine_windows": 95,
        "mean_gradient_cosine": -0.8033459679204591,
        "median_factual_gradient_norm": 1.038113559559406e-07,
        "median_synthetic_gradient_norm": 3.0117459637324373e-09
      },
      "player_1": {
        "log_rho_rms_max": 0.03386971354484558,
        "rho_ess_fraction_min": 0.9992316961288452,
        "rho_mean_min": 0.9976394176483154,
        "valid_gradient_windows": 98,
        "negative_cosine_windows": 69,
        "mean_gradient_cosine": -0.36429667746534156,
        "median_factual_gradient_norm": 2.7512603537616087e-06,
        "median_synthetic_gradient_norm": 7.618074562287802e-07
      }
    },
    "stag_hunt/critic_only": {
      "player_0": {
        "log_rho_rms_max": 0.102165587246418,
        "rho_ess_fraction_min": 0.9984212517738342,
        "rho_mean_min": 0.996391236782074,
        "valid_gradient_windows": 98,
        "negative_cosine_windows": 6,
        "mean_gradient_cosine": 0.4158083141914436,
        "median_factual_gradient_norm": 7.557182257755812e-08,
        "median_synthetic_gradient_norm": 0.0004905850510112941
      },
      "player_1": {
        "log_rho_rms_max": 1.1170936822891235,
        "rho_ess_fraction_min": 0.9342811703681946,
        "rho_mean_min": 0.9112690687179565,
        "valid_gradient_windows": 98,
        "negative_cosine_windows": 29,
        "mean_gradient_cosine": 0.1422496987696813,
        "median_factual_gradient_norm": 6.205406407389091e-06,
        "median_synthetic_gradient_norm": 0.001971251331269741
      }
    },
    "stag_hunt/corrected": {
      "player_0": {
        "log_rho_rms_max": 0.28135836124420166,
        "rho_ess_fraction_min": 0.98870450258255,
        "rho_mean_min": 0.9832658767700195,
        "valid_gradient_windows": 98,
        "negative_cosine_windows": 94,
        "mean_gradient_cosine": -0.7262520717114819,
        "median_factual_gradient_norm": 3.826568644171857e-07,
        "median_synthetic_gradient_norm": 6.779456995786859e-09
      },
      "player_1": {
        "log_rho_rms_max": 0.0188610777258873,
        "rho_ess_fraction_min": 0.9999138116836548,
        "rho_mean_min": 0.998934268951416,
        "valid_gradient_windows": 98,
        "negative_cosine_windows": 17,
        "mean_gradient_cosine": 0.5435470897628336,
        "median_factual_gradient_norm": 1.1678928899527818e-06,
        "median_synthetic_gradient_norm": 3.918318647322394e-08
      }
    }
  },
  "local_raw_snapshot_sha256": "0a3dc6e0ea71603fda388978bdd7c843849b822d0cf2d6d4b754a9b406a171c2",
  "local_progress_snapshot_sha256": "fad2960c2436bfa51177d7fda7cf15987133dc40e8ceab97bbd6f74a2e3685f4",
  "recorded_at_utc": "2026-10-12T20:55:35.479689+00:00",
  "diagnostics_observed_at_utc": "2026-10-12T20:53:32.470263+00:00"
}