{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny_pooling_mvp",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003,
      "epochs": 12,
      "batch": 128
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "epochs": 12,
          "batch": 128
        },
        "mean": 1.030422881245613
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "batch": 128
        },
        "mean": 1.0044431388378143
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12,
          "batch": 128
        },
        "mean": 1.0057344734668732
      }
    ],
    "full": {
      "mean": 1.0108022689819336,
      "std": 0.09233493114632767,
      "per_seed": [
        1.135109543800354,
        0.8252689242362976,
        1.0580546855926514,
        0.9993394017219543,
        1.0295724868774414,
        1.0314586162567139,
        1.09066903591156,
        0.9169454574584961
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 1.0283051505684853,
    "std": 0.09182080119670853,
    "per_seed": [
      1.1634190082550049,
      0.8420974612236023,
      1.050006628036499,
      1.0190545320510864,
      1.0613138675689697,
      1.0465973615646362,
      1.1009020805358887,
      0.9430502653121948
    ],
    "n": 8,
    "selected_cfg": {
      "lr": 0.006,
      "epochs": 12,
      "batch": 128
    }
  },
  "comparison": {
    "delta_mean": 0.017502881586551666,
    "idea_wins": 1,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.02830946445465088,
      0.016828536987304688,
      -0.008048057556152344,
      0.01971513032913208,
      0.03174138069152832,
      0.015138745307922363,
      0.010233044624328613,
      0.02610480785369873
    ],
    "p_value": 0.0163,
    "mde": 0.010529986179047253,
    "mde_rel_pct": 1.0417454038417338,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.0015,
        "epochs": 12,
        "batch": 128
      },
      "mean": 1.091338686645031,
      "std": 0.09665476674907689,
      "per_seed": [
        1.2205655574798584,
        0.9110400080680847,
        1.1126540899276733,
        1.0519979000091553,
        1.12910795211792,
        1.1222410202026367,
        1.1943774223327637,
        0.9887255430221558
      ]
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 12,
        "batch": 128
      },
      "mean": 1.075037308037281,
      "std": 0.09951274952114578,
      "per_seed": [
        1.2106199264526367,
        0.8868147134780884,
        1.1060532331466675,
        1.03895902633667,
        1.1129647493362427,
        1.103129506111145,
        1.173069715499878,
        0.9686875939369202
      ]
    },
    {
      "cfg": {
        "lr": 0.006,
        "epochs": 12,
        "batch": 128
      },
      "mean": 1.0283051505684853,
      "std": 0.09182080119670853,
      "per_seed": [
        1.1634190082550049,
        0.8420974612236023,
        1.050006628036499,
        1.0190545320510864,
        1.0613138675689697,
        1.0465973615646362,
        1.1009020805358887,
        0.9430502653121948
      ]
    }
  ],
  "selection_seeds": [
    0,
    1,
    2,
    3
  ],
  "epochs": 12,
  "batch": 128,
  "parameter_counts": {
    "baseline": 321,
    "idea": 337
  },
  "structural_match": "sequence-level window forecasting with token-set pooling",
  "mechanism_signature": {
    "quantity": "trained probe D_hat versus independent 1D Wasserstein-1",
    "predicted": "D_hat <= W1 for every pair; positive geometric association",
    "observed_mean_D_hat": 0.027728637424297632,
    "observed_mean_W1": 0.31382585523523404,
    "mean_ratio_D_hat_over_W1": 0.09807194932021986,
    "pearson_correlation": 0.12651039453842908,
    "violation_fraction": 0.0,
    "confirmed": false
  }
}