{
  "bench_version": 1,
  "track": "pde_patch_consensus",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.001,
      "weight": 0.15,
      "epochs": 20,
      "lam": 0.002,
      "tau": 0.08
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "weight": 0.15,
          "epochs": 20,
          "lam": 0.002,
          "tau": 0.08
        },
        "mean": 0.3015064224600792
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight": 0.3,
          "epochs": 20,
          "lam": 0.002,
          "tau": 0.08
        },
        "mean": 0.3022902384400368
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight": 0.15,
          "epochs": 20,
          "lam": 0.002,
          "tau": 0.08
        },
        "mean": 0.3018767833709717
      }
    ],
    "full": {
      "mean": 0.2986701726913452,
      "std": 0.01948377339633572,
      "per_seed": [
        0.2805998921394348,
        0.3210130035877228,
        0.2944689989089966,
        0.3099437952041626,
        0.3145343065261841,
        0.2926834225654602,
        0.26018649339675903,
        0.3159314692020416
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.2986989840865135,
    "std": 0.01941700283178657,
    "per_seed": [
      0.28059789538383484,
      0.3210127651691437,
      0.29445162415504456,
      0.30993232131004333,
      0.31450358033180237,
      0.2926560342311859,
      0.2604662775993347,
      0.31597137451171875
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 2.8811395168304443e-05,
    "idea_wins": 6,
    "n_pairs": 8,
    "per_seed_diffs": [
      -1.996755599975586e-06,
      -2.384185791015625e-07,
      -1.7374753952026367e-05,
      -1.1473894119262695e-05,
      -3.072619438171387e-05,
      -2.7388334274291992e-05,
      0.0002797842025756836,
      3.9905309677124023e-05
    ],
    "p_value": 0.7982,
    "mde": 8.675913930736897e-05,
    "mde_rel_pct": 0.029048477966706267,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "weak residual integration plus support consensus should reduce noisy residual variability and increase regional support agreement",
    "observed_trained_models": {
      "baseline_pointwise_pde_rms_mean": 0.022820161539129913,
      "idea_pointwise_pde_rms_mean": 0.029661827720701694,
      "baseline_observation_rms_mean": 0.5462089078210038,
      "idea_observation_rms_mean": 0.5462374777264867,
      "idea_local_support_rate_mean": 0.0625,
      "idea_modal_terms_mean": 0.0
    },
    "confirmed": false
  },
  "custom_track": {
    "name": "pde_patch_consensus",
    "file": "pde_consensus_track.py",
    "domain": "pde"
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "weight": 0.15,
        "epochs": 20,
        "lam": 0.002,
        "tau": 0.08
      },
      "mean": 0.2986989840865135
    },
    {
      "cfg": {
        "lr": 0.003,
        "weight": 0.3,
        "epochs": 20,
        "lam": 0.002,
        "tau": 0.08
      },
      "mean": 0.2990812510251999
    },
    {
      "cfg": {
        "lr": 0.01,
        "weight": 0.15,
        "epochs": 20,
        "lam": 0.002,
        "tau": 0.08
      },
      "mean": 0.29942547529935837
    }
  ]
}