{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 16.10005497932434
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 11.262676000595093
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 7.429885745048523
      }
    ],
    "full": {
      "mean": 7.599956035614014,
      "std": 0.8051347687842139,
      "per_seed": [
        6.844658851623535,
        6.109804630279541,
        8.30047607421875,
        8.464603424072266,
        7.705488681793213,
        6.993262767791748,
        8.389989852905273,
        7.991364002227783
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 8.154384911060333,
    "std": 1.0389464855334478,
    "per_seed": [
      7.118060111999512,
      6.544161319732666,
      9.722457885742188,
      8.549818992614746,
      7.820003986358643,
      7.930368423461914,
      9.617923736572266,
      7.932284832000732
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.5544288754463196,
    "idea_wins": 1,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.27340126037597656,
      0.434356689453125,
      1.4219818115234375,
      0.08521556854248047,
      0.11451530456542969,
      0.937105655670166,
      1.2279338836669922,
      -0.05907917022705078
    ],
    "p_value": 0.0156,
    "mde": 0.4725954183814587,
    "mde_rel_pct": 6.218396740281628,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "track_justification": "ReLU hidden-axis pruning is structurally matched to the tabular MLP track; both systems use the identical trained mlp_tiny and optimizer budgets.",
  "pruning_fraction": 0.5,
  "idea_config": {
    "lr": 0.01
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "result": {
        "mean": 22.81420075893402,
        "std": 5.572511935733092,
        "per_seed": [
          23.423412322998047,
          15.931241035461426,
          33.59147262573242,
          17.00380516052246,
          26.614585876464844,
          17.325483322143555,
          25.237001419067383,
          23.38660430908203
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "result": {
        "mean": 14.472419738769531,
        "std": 2.867801864411425,
        "per_seed": [
          12.962059020996094,
          10.092577934265137,
          17.148317337036133,
          11.091870307922363,
          15.618391036987305,
          13.338394165039062,
          16.90511131286621,
          18.622636795043945
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01
      },
      "result": {
        "mean": 8.154384911060333,
        "std": 1.0389464855334478,
        "per_seed": [
          7.118060111999512,
          6.544161319732666,
          9.722457885742188,
          8.549818992614746,
          7.820003986358643,
          7.930368423461914,
          9.617923736572266,
          7.932284832000732
        ],
        "n": 8
      }
    }
  ],
  "parameter_fraction_estimate": 0.25,
  "mechanism_signature": {
    "prediction": "strictly one-sided selected ReLU axes are affine or zero on the test patch",
    "predicted_max_replacement_error": 0.0,
    "observed_max_replacement_error": 0.1555086076259613,
    "tested_one_sided_axes": 53,
    "downstream_norm_sum": 24.949480190873146,
    "confirmed": false
  }
}