{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 18
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "epochs": 18
        },
        "mean": 16.413997888565063
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 18
        },
        "mean": 13.256237506866455
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18
        },
        "mean": 10.138120174407959
      }
    ],
    "full": {
      "mean": 10.593586206436157,
      "std": 1.1860413365771312,
      "per_seed": [
        9.266413688659668,
        10.942156791687012,
        10.532804489135742,
        9.811105728149414,
        9.271466255187988,
        10.483624458312988,
        11.298463821411133,
        13.142654418945312
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 24.50470805168152,
    "std": 1.4738344415396776,
    "per_seed": [
      25.35301971435547,
      24.542402267456055,
      26.259077072143555,
      22.042612075805664,
      22.800880432128906,
      25.55665397644043,
      23.438636779785156,
      26.044382095336914
    ],
    "n": 8,
    "best_cfg": {
      "lr": 0.003,
      "epochs": 18
    },
    "settings": [
      {
        "cfg": {
          "lr": 0.0015,
          "epochs": 18
        },
        "mean": 48.017033100128174
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 18
        },
        "mean": 24.50470805168152
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18
        },
        "mean": 24.52953600883484
      }
    ]
  },
  "comparison": {
    "delta_mean": 13.911121845245361,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      16.0866060256958,
      13.600245475769043,
      15.726272583007812,
      12.23150634765625,
      13.529414176940918,
      15.073029518127441,
      12.140172958374023,
      12.901727676391602
    ],
    "p_value": 0.0081,
    "mde": 1.2874798773006364,
    "mde_rel_pct": 12.153390289290563,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "track_choice": "Friedman#1 is the built-in regression track and matches the idea's high-dimensional regression setting.",
  "custom_track": null,
  "parameter_counts": {
    "baseline": 4929,
    "idea": 7076
  },
  "mechanism_signature": {
    "definition": "trained accumulator behavior on tabular test predictions",
    "predicted": "context is transmitted unchanged and output corrections accumulate additively",
    "observed_mean_delta_norms": [
      0.9999635517597198,
      0.9999598488211632
    ],
    "observed_final_accumulator_norm": 2.128704696893692,
    "observed_prediction_std": 0.06401639571413398,
    "quantitative_tolerance": "nonzero branch corrections and finite accumulated state",
    "confirmed": true
  }
}