{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003,
      "beta2": 0.999
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0003,
          "beta2": 0.99
        },
        "mean": 219.74071502685547
      },
      {
        "cfg": {
          "lr": 0.001,
          "beta2": 0.99
        },
        "mean": 133.59764099121094
      },
      {
        "cfg": {
          "lr": 0.003,
          "beta2": 0.999
        },
        "mean": 16.845557928085327
      }
    ],
    "full": {
      "mean": 17.666198015213013,
      "std": 2.17622036048186,
      "per_seed": [
        17.691715240478516,
        14.373583793640137,
        20.163808822631836,
        15.15312385559082,
        18.178590774536133,
        15.800971031188965,
        19.925329208374023,
        20.042461395263672
      ],
      "n": 8
    }
  },
  "idea": {
    "per_seed": [
      15.087238311767578,
      12.6608247756958,
      16.30777359008789,
      14.145133972167969,
      15.023676872253418,
      15.424975395202637,
      17.59527587890625,
      18.863933563232422
    ],
    "mean": 15.638604044914246,
    "best_cfg": {
      "lr": 0.003,
      "beta2": 0.999,
      "metric_beta": -0.5
    },
    "nearby_settings": [
      {
        "cfg": {
          "lr": 0.0003,
          "beta2": 0.99,
          "metric_beta": -0.5
        },
        "mean": 216.299165725708
      },
      {
        "cfg": {
          "lr": 0.001,
          "beta2": 0.99,
          "metric_beta": -0.5
        },
        "mean": 81.73757028579712
      },
      {
        "cfg": {
          "lr": 0.003,
          "beta2": 0.999,
          "metric_beta": -0.5
        },
        "mean": 15.638604044914246
      }
    ]
  },
  "comparison": {
    "delta_mean": -2.027593970298767,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -2.6044769287109375,
      -1.712759017944336,
      -3.8560352325439453,
      -1.0079898834228516,
      -3.154913902282715,
      -0.3759956359863281,
      -2.3300533294677734,
      -1.17852783203125
    ],
    "p_value": 0.0081,
    "mde": 0.9805142418858956,
    "mde_rel_pct": 5.550227847788975,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "predicted": "m decreases as observed v increases (inverse-variance metric)",
    "observed_metric_mean": 3.7805249429075047,
    "observed_log_metric_vs_negative_log_variance_corr": 0.8070462500798509,
    "baseline_final_train_loss": 17.63215286254883,
    "idea_final_train_loss": 15.715824356079102,
    "max_constraint_violation": 0.0,
    "confirmed": true
  },
  "protocol_note": "Baseline and idea use identical tabular task, mlp_tiny architecture, 12 epochs, batch 128, and the same lr union; baseline Adam beta2 was swept."
}