{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "mean": 16.985830068588257
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 11.592020750045776
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0
        },
        "mean": 7.1914142370224
      }
    ],
    "full": {
      "mean": 7.462258458137512,
      "std": 0.633509839885441,
      "per_seed": [
        6.857808589935303,
        7.703956604003906,
        7.029021263122559,
        7.174870491027832,
        6.467283725738525,
        7.960057258605957,
        8.130547523498535,
        8.37452220916748
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 7.855136156082153,
    "std": 0.8610502821731341,
    "per_seed": [
      7.060885906219482,
      8.29471206665039,
      7.688426494598389,
      7.102557182312012,
      6.474584579467773,
      9.063955307006836,
      8.353429794311523,
      8.80253791809082
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.3928776979446411,
    "idea_wins": 1,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.2030773162841797,
      0.5907554626464844,
      0.6594052314758301,
      -0.07231330871582031,
      0.007300853729248047,
      1.103898048400879,
      0.22288227081298828,
      0.42801570892333984
    ],
    "p_value": 0.0235,
    "mde": 0.3233736709994596,
    "mde_rel_pct": 4.333455787058997,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "idea_config": {
      "lr": 0.01,
      "tail_weight": 4.0
    },
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "tail_weight": 4.0
        },
        "result": {
          "mean": 22.177693843841553,
          "std": 0.9958955479883927,
          "per_seed": [
            22.019962310791016,
            20.866891860961914,
            22.155040740966797,
            23.668880462646484
          ],
          "n": 4
        }
      },
      {
        "cfg": {
          "lr": 0.003,
          "tail_weight": 4.0
        },
        "result": {
          "mean": 11.351011991500854,
          "std": 0.7376803433578396,
          "per_seed": [
            10.290882110595703,
            11.659903526306152,
            12.307673454284668,
            11.145588874816895
          ],
          "n": 4
        }
      },
      {
        "cfg": {
          "lr": 0.01,
          "tail_weight": 4.0
        },
        "result": {
          "mean": 7.536645412445068,
          "std": 0.5031108845030456,
          "per_seed": [
            7.060885906219482,
            8.29471206665039,
            7.688426494598389,
            7.102557182312012
          ],
          "n": 4
        }
      }
    ],
    "mechanism_signature": {
      "prediction": "tail residual correction should preferentially reduce upper-tail prediction error relative to global error",
      "baseline_behavior": {
        "global_mse": 7.462258815765381,
        "tail_mse": 14.653417646884918,
        "tail_to_global": 1.9636705196993307,
        "cvar_abs_error": 2.055535450577737
      },
      "idea_behavior": {
        "global_mse": 7.855136334896088,
        "tail_mse": 8.973360180854797,
        "tail_to_global": 1.1423557527564545,
        "cvar_abs_error": 0.8575644314289099
      },
      "predicted_tail_focus": true,
      "observed_tail_to_global_ratio_change": -0.8213147669428762,
      "confirmed": true
    }
  },
  "protocol_notes": {
    "epochs": 24,
    "batch": 128,
    "baseline_grid": [
      {
        "lr": 0.001,
        "weight_decay": 0.0
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      {
        "lr": 0.01,
        "weight_decay": 0.0
      }
    ],
    "idea_grid": [
      {
        "lr": 0.001,
        "tail_weight": 4.0
      },
      {
        "lr": 0.003,
        "tail_weight": 4.0
      },
      {
        "lr": 0.01,
        "tail_weight": 4.0
      }
    ],
    "intervention": "same mlp_tiny trained with global-MSE warmup followed by upper-tail weighted residual correction"
  }
}