{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 8.571802377700806
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 20.563005447387695
      },
      {
        "cfg": {
          "lr": 0.03
        },
        "mean": 20.28245759010315
      }
    ],
    "full": {
      "mean": 8.942538976669312,
      "std": 1.2011059504420323,
      "per_seed": [
        8.109341621398926,
        9.679099082946777,
        8.425871849060059,
        8.072896957397461,
        6.844796180725098,
        9.526346206665039,
        10.597946166992188,
        10.284013748168945
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 8.995229661464691,
    "std": 1.2122424602688344,
    "per_seed": [
      8.160211563110352,
      9.738099098205566,
      8.477083206176758,
      8.129450798034668,
      6.85977029800415,
      9.593474388122559,
      10.62648868560791,
      10.377259254455566
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.05269068479537964,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.05086994171142578,
      0.05900001525878906,
      0.05121135711669922,
      0.05655384063720703,
      0.014974117279052734,
      0.06712818145751953,
      0.028542518615722656,
      0.0932455062866211
    ],
    "p_value": 0.0081,
    "mde": 0.019784595139020266,
    "mde_rel_pct": 0.2212413632262314,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "predicted": 0.06620380758814955,
    "observed": 0.008275476713068709,
    "confirmed": true,
    "details": {
      "predicted": 0.06620380758814955,
      "observed": 0.008275476713068709,
      "observed_over_predicted": 0.12500001282535644,
      "mean_gradient_cosine": 0.9849408324128792,
      "mean_displacement_sq": 1.4717475092518306e-06,
      "mean_age": 0.4951171875,
      "max_age": 1,
      "confirmed": true,
      "definition": "trained tabular MLP: stale-vs-current partition gradient MSE compared with local L_hat^2 parameter displacement"
    }
  },
  "idea_trials": [
    {
      "cfg": {
        "lr": 0.003,
        "c": 2
      },
      "result": {
        "mean": 8.995229661464691,
        "std": 1.2122424602688344,
        "per_seed": [
          8.160211563110352,
          9.738099098205566,
          8.477083206176758,
          8.129450798034668,
          6.85977029800415,
          9.593474388122559,
          10.62648868560791,
          10.377259254455566
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003,
        "c": 2
      },
      "result": {
        "mean": 8.995229661464691,
        "std": 1.2122424602688344,
        "per_seed": [
          8.160211563110352,
          9.738099098205566,
          8.477083206176758,
          8.129450798034668,
          6.85977029800415,
          9.593474388122559,
          10.62648868560791,
          10.377259254455566
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.03,
        "c": 2
      },
      "result": {
        "mean": 24.871363401412964,
        "std": 9.356500961042444,
        "per_seed": [
          27.6580810546875,
          45.721439361572266,
          10.339054107666016,
          22.65554428100586,
          22.052181243896484,
          25.39988136291504,
          19.183732986450195,
          25.96099281311035
        ],
        "n": 8
      }
    }
  ],
  "custom_track": null
}