{
  "bench_version": 1,
  "track": "constrained_two_agent_dynamics",
  "model": "custom_gru_cell",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 12,
      "hidden": 32,
      "wd": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0
        },
        "mean": 0.0322869922965765
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0
        },
        "mean": 0.012963124550879002
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0
        },
        "mean": 0.0070766935823485255
      }
    ],
    "full": {
      "mean": 0.006266987067647278,
      "std": 0.0012038076406143412,
      "per_seed": [
        0.0054755136370658875,
        0.008236748166382313,
        0.007714319974184036,
        0.006880192551761866,
        0.005664798431098461,
        0.006498826202005148,
        0.004625890403985977,
        0.005039607174694538
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.024705890100449324,
    "std": 0.008283505340451159,
    "per_seed": [
      0.01789645291864872,
      0.03382120281457901,
      0.017041007056832314,
      0.02942308597266674,
      0.03449169918894768,
      0.03302520141005516,
      0.012732679024338722,
      0.019215792417526245
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.018438903032802045,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.012420939281582832,
      0.025584454648196697,
      0.009326687082648277,
      0.022542893420904875,
      0.028826900757849216,
      0.026526375208050013,
      0.008106788620352745,
      0.014176185242831707
    ],
    "p_value": 0.0081,
    "mde": 0.0069627855763603015,
    "mde_rel_pct": 111.10260004053649,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "custom_track": {
      "name": "constrained_two_agent_dynamics",
      "file": "bench/custom_tracks/constrained_two_agent_dynamics.py",
      "domain": "dynamics"
    },
    "mechanism_signature": {
      "predicted_rms": 2.836034980191471e-07,
      "observed_rms": 2.836034980191471e-07,
      "confirmed": true,
      "note": "prediction is zero path disagreement only when conservative; this learned scalar field was measured directly"
    },
    "idea_trials": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.01,
          "K": 3
        },
        "result": {
          "mean": 0.45704858377575874,
          "std": 0.10490055843604634,
          "per_seed": [
            0.3964577615261078,
            0.5977270007133484,
            0.37981122732162476,
            0.45022860169410706,
            0.5956597328186035,
            0.5277622938156128,
            0.27294501662254333,
            0.4357970356941223
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.05,
          "K": 5
        },
        "result": {
          "mean": 0.457201711833477,
          "std": 0.1048935001658233,
          "per_seed": [
            0.3966236412525177,
            0.5978873372077942,
            0.3799804449081421,
            0.45041248202323914,
            0.5957075357437134,
            0.5278149843215942,
            0.27297601103782654,
            0.4362112581729889
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.2,
          "K": 7
        },
        "result": {
          "mean": 0.45794062316417694,
          "std": 0.1048035662894998,
          "per_seed": [
            0.3975609242916107,
            0.5985288619995117,
            0.3805820643901825,
            0.4510311186313629,
            0.5958411693572998,
            0.5279558300971985,
            0.2731569707393646,
            0.43886804580688477
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.01,
          "K": 3
        },
        "result": {
          "mean": 0.10495583922602236,
          "std": 0.06396028545593932,
          "per_seed": [
            0.05165071412920952,
            0.2026720494031906,
            0.04937386140227318,
            0.07717829197645187,
            0.18805915117263794,
            0.15454889833927155,
            0.02122720517218113,
            0.0949365422129631
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.05,
          "K": 5
        },
        "result": {
          "mean": 0.10538749303668737,
          "std": 0.06388145594067134,
          "per_seed": [
            0.05256393551826477,
            0.2028532475233078,
            0.050049472600221634,
            0.07778554409742355,
            0.18824990093708038,
            0.1546095907688141,
            0.020773518830537796,
            0.09621473401784897
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.2,
          "K": 7
        },
        "result": {
          "mean": 0.10764682595618069,
          "std": 0.06333663433666077,
          "per_seed": [
            0.05678858980536461,
            0.20373065769672394,
            0.053114570677280426,
            0.08071713894605637,
            0.189082533121109,
            0.1552448719739914,
            0.020189819857478142,
            0.10230642557144165
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.01,
          "K": 3
        },
        "result": {
          "mean": 0.05755363428033888,
          "std": 0.01782041693525763,
          "per_seed": [
            0.050933968275785446,
            0.06813938170671463,
            0.034426964819431305,
            0.07328452914953232,
            0.07746168226003647,
            0.07605248689651489,
            0.028837481513619423,
            0.051292579621076584
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.05,
          "K": 5
        },
        "result": {
          "mean": 0.04705770337022841,
          "std": 0.016346008984626046,
          "per_seed": [
            0.03983130306005478,
            0.05912895128130913,
            0.026205483824014664,
            0.0593021921813488,
            0.0660790354013443,
            0.0639730915427208,
            0.021240977570414543,
            0.04070059210062027
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12,
          "hidden": 32,
          "wd": 0.0,
          "lam": 0.2,
          "K": 7
        },
        "result": {
          "mean": 0.024705890100449324,
          "std": 0.008283505340451159,
          "per_seed": [
            0.01789645291864872,
            0.03382120281457901,
            0.017041007056832314,
            0.02942308597266674,
            0.03449169918894768,
            0.03302520141005516,
            0.012732679024338722,
            0.019215792417526245
          ],
          "n": 8
        }
      }
    ]
  }
}