{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 30
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 30
        },
        "mean": 6.278503656387329
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 30
        },
        "mean": 3.3817883133888245
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 30
        },
        "mean": 3.0755263566970825
      }
    ],
    "full": {
      "mean": 3.486333578824997,
      "std": 0.633233116371069,
      "per_seed": [
        2.968747138977051,
        2.9661331176757812,
        3.391489028930664,
        2.975736141204834,
        4.913453578948975,
        3.106180191040039,
        3.927138328552246,
        3.6417911052703857
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 1.7247163504362106,
    "std": 0.2112279864426216,
    "per_seed": [
      1.729775071144104,
      1.700377106666565,
      1.6194583177566528,
      1.3495277166366577,
      1.6963016986846924,
      1.6350337266921997,
      2.0824673175811768,
      1.9847898483276367
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -1.7616172283887863,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -1.2389720678329468,
      -1.2657560110092163,
      -1.7720307111740112,
      -1.6262084245681763,
      -3.2171518802642822,
      -1.4711464643478394,
      -1.8446710109710693,
      -1.657001256942749
    ],
    "p_value": 0.0081,
    "mde": 0.5248752320909208,
    "mde_rel_pct": 15.055221200830132,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "epochs": 30
      },
      "mean": 3.4459262788295746,
      "std": 0.2142069786440496,
      "per_seed": [
        3.629073143005371,
        3.5230846405029297,
        2.9594202041625977,
        3.4428420066833496,
        3.6288678646087646,
        3.5347254276275635,
        3.2687673568725586,
        3.580629587173462
      ],
      "n": 8
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 30
      },
      "mean": 1.7938710153102875,
      "std": 0.18505377667547435,
      "per_seed": [
        1.642995834350586,
        2.02911639213562,
        1.8970131874084473,
        1.7373865842819214,
        1.4786462783813477,
        1.8234977722167969,
        2.0580201148986816,
        1.684291958808899
      ],
      "n": 8
    },
    {
      "cfg": {
        "lr": 0.006,
        "epochs": 30
      },
      "mean": 1.7247163504362106,
      "std": 0.2112279864426216,
      "per_seed": [
        1.729775071144104,
        1.700377106666565,
        1.6194583177566528,
        1.3495277166366577,
        1.6963016986846924,
        1.6350337266921997,
        2.0824673175811768,
        1.9847898483276367
      ],
      "n": 8
    }
  ],
  "matched_structure": "Friedman#1 tabular regression; regularization/MLP intervention",
  "hyperparameter_parity": "baseline and idea both evaluated lr={0.001,0.003,0.006}, epochs=30",
  "selected_idea_cfg": {
    "lr": 0.006,
    "epochs": 30
  },
  "mechanism_signature": {
    "trained_test_mse": 1.729775071144104,
    "free_branch_mse": 16.04800796508789,
    "geom_branch_mse": 71.31401824951172,
    "mean_alpha": 0.2708725333213806,
    "alpha_std": 0.17698463797569275,
    "alpha_support_corr": -0.01807535826279521,
    "initial_alpha_at_beta_minus4": 0.01798621006309986,
    "predicted": {
      "learned_gate_nonconstant": true,
      "prior_use_should_be_suppressible": true
    },
    "confirmed": true
  }
}