{
  "bench_version": 1,
  "track": "tabular",
  "model": "masked_mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "epochs": 4,
      "mask_count": 20
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 4,
          "mask_count": 20
        },
        "mean": 233.01842498779297
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 4,
          "mask_count": 20
        },
        "mean": 228.20503997802734
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 4,
          "mask_count": 20
        },
        "mean": 191.4046401977539
      }
    ],
    "full": {
      "mean": 185.9184112548828,
      "std": 13.31649292644178,
      "per_seed": [
        211.56298828125,
        186.1365509033203,
        195.3025665283203,
        172.616455078125,
        170.3512420654297,
        193.65509033203125,
        172.0006561279297,
        185.72174072265625
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 208.20309448242188,
    "std": 13.805027643998322,
    "per_seed": [
      226.8892364501953,
      212.61376953125,
      219.84451293945312,
      193.2020263671875,
      220.1836700439453,
      202.975341796875,
      183.25924682617188,
      206.65695190429688
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 22.284683227539062,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      15.326248168945312,
      26.477218627929688,
      24.541946411132812,
      20.5855712890625,
      49.832427978515625,
      9.32025146484375,
      11.258590698242188,
      20.935211181640625
    ],
    "p_value": 0.0081,
    "mde": 10.597026350103498,
    "mde_rel_pct": 5.699826218703871,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "epochs": 4,
        "mask_count": 1,
        "canonical": true
      },
      "mean": 232.431640625
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 4,
        "mask_count": 1,
        "canonical": true
      },
      "mean": 228.43239402770996
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 4,
        "mask_count": 1,
        "canonical": true
      },
      "mean": 208.20309448242188
    }
  ],
  "runtime_sec": 36.57714536000003,
  "track_justification": "Tabular is the built-in architecture/regularization-adjacent track; the experiment directly operates on exchangeable hidden channels and structured pruning masks.",
  "mask_definition": "retain k=3 of six first-layer hidden channels; exact S_6 symmetry represented by channel permutations.",
  "mechanism_signature": {
    "predicted_orbits": 1,
    "observed_candidate_masks": 20,
    "predicted_evaluation_reduction": 20,
    "observed_evaluation_reduction": 20,
    "trained_model_mask_spread": [
      {
        "seed": 0,
        "mask_metric_std": 18.708847715759166,
        "mask_metric_range": 73.77125549316406
      },
      {
        "seed": 1,
        "mask_metric_std": 11.349517459757626,
        "mask_metric_range": 53.40818786621094
      },
      {
        "seed": 2,
        "mask_metric_std": 13.9794193204962,
        "mask_metric_range": 43.052520751953125
      },
      {
        "seed": 3,
        "mask_metric_std": 9.279172900445374,
        "mask_metric_range": 36.04695129394531
      },
      {
        "seed": 4,
        "mask_metric_std": 14.554493291709218,
        "mask_metric_range": 54.18971252441406
      },
      {
        "seed": 5,
        "mask_metric_std": 12.235878564511857,
        "mask_metric_range": 44.35304260253906
      },
      {
        "seed": 6,
        "mask_metric_std": 12.367370327709848,
        "mask_metric_range": 58.37591552734375
      },
      {
        "seed": 7,
        "mask_metric_std": 18.78608365872588,
        "mask_metric_range": 67.00553894042969
      }
    ],
    "observed_nonzero_spread_seeds": 8,
    "confirmed": false,
    "note": "The exact reduction is structural; finite independently trained masked models can differ because optimization noise breaks numerical equality."
  }
}