{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0001
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0
        },
        "mean": 16.004083156585693
      },
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0001
        },
        "mean": 16.01387643814087
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 12.535736083984375
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001
        },
        "mean": 12.430302143096924
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "mean": 9.091599702835083
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0001
        },
        "mean": 8.875346541404724
      }
    ],
    "full": {
      "mean": 9.257637917995453,
      "std": 0.7946203059794043,
      "per_seed": [
        9.313394546508789,
        7.957194805145264,
        8.725268363952637,
        9.505528450012207,
        8.830371856689453,
        9.170703887939453,
        10.88531494140625,
        9.67332649230957
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 10.167674660682678,
    "std": 1.8586175283157877,
    "per_seed": [
      12.230741500854492,
      8.306159973144531,
      8.560102462768555,
      9.36517333984375,
      8.156329154968262,
      9.683719635009766,
      13.33909797668457,
      11.7000732421875
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.9100367426872253,
    "idea_wins": 3,
    "n_pairs": 8,
    "per_seed_diffs": [
      2.917346954345703,
      0.3489651679992676,
      -0.16516590118408203,
      -0.14035511016845703,
      -0.6740427017211914,
      0.5130157470703125,
      2.4537830352783203,
      2.0267467498779297
    ],
    "p_value": 0.129,
    "mde": 1.1351211014956983,
    "mde_rel_pct": 12.261454936460563,
    "verdict": "no significant win",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.006,
        "rho": 0.12,
        "beta": 0.85,
        "epochs": 12,
        "K": 6
      },
      "mean": 9.615544319152832
    },
    {
      "cfg": {
        "lr": 0.0015,
        "rho": 0.12,
        "beta": 0.85,
        "epochs": 12,
        "K": 6
      },
      "mean": 15.944299936294556
    },
    {
      "cfg": {
        "lr": 0.006,
        "rho": 0.12,
        "beta": 0.85,
        "epochs": 12,
        "K": 6
      },
      "mean": 9.615544319152832
    }
  ],
  "track_justification": "Optimizer intervention matches tabular MLP training; both systems share architecture and data.",
  "budget": {
    "epochs": 12,
    "batch": 64,
    "candidates_per_epoch": 6,
    "seeds": 8
  },
  "mechanism_signature": {
    "predicted": "utility-|z| covariance should determine q update direction",
    "observed_note": "trained-model candidate losses and DG q updates were collected during each run",
    "predicted_vs_observed": "see per-seed trained metrics; no fixed quantitative tolerance claimed",
    "confirmed": false
  }
}