{
  "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": 0.001,
          "weight_decay": 0.0001
        },
        "mean": 16.534404277801514
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001
        },
        "mean": 9.554428339004517
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0001
        },
        "mean": 7.10407030582428
      }
    ],
    "full": {
      "mean": 7.061818897724152,
      "std": 0.3679269493562873,
      "per_seed": [
        6.67182731628418,
        6.9647216796875,
        7.721733093261719,
        7.057999134063721,
        6.471690654754639,
        6.978625297546387,
        7.271554470062256,
        7.3563995361328125
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 178.17990684509277,
    "std": 9.629824242821801,
    "per_seed": [
      190.22879028320312,
      175.91212463378906,
      179.41261291503906,
      165.240966796875,
      190.38267517089844,
      169.86196899414062,
      167.13531494140625,
      187.26480102539062
    ],
    "n": 8,
    "signatures": [
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.33333323108538504,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.33333318546496393,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.3333331799108243,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.3333332577271232,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.3333332312105795,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.33333320043828085,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.3333332324274767,
        "degree": 0
      },
      {
        "q": 1.0,
        "predicted_tail": 1.0,
        "observed_tail": 0.333333177763843,
        "degree": 0
      }
    ],
    "cfg": {
      "lr": 0.006,
      "weight_decay": 0.0001
    }
  },
  "comparison": {
    "delta_mean": 171.11808794736862,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      183.55696296691895,
      168.94740295410156,
      171.69087982177734,
      158.18296766281128,
      183.9109845161438,
      162.88334369659424,
      159.863760471344,
      179.9084014892578
    ],
    "p_value": 0.0081,
    "mde": 8.726735703488881,
    "mde_rel_pct": 123.57631695003239,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "quantity": "trained held-out latent Hermite omitted-energy proxy",
    "predicted_mean_tail_scale": 1.0,
    "observed_mean_tail": 0.3333332120035596,
    "mean_q": 1.0,
    "degrees": [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    "confirmed": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "weight_decay": 0.0001
      },
      "mean": 224.16369247436523
    },
    {
      "cfg": {
        "lr": 0.003,
        "weight_decay": 0.0001
      },
      "mean": 204.7395420074463
    },
    {
      "cfg": {
        "lr": 0.006,
        "weight_decay": 0.0001
      },
      "mean": 178.17990684509277
    }
  ],
  "protocol": {
    "paired_seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ],
    "epochs": 18,
    "batch": 128,
    "baseline_grid": [
      {
        "lr": 0.001,
        "weight_decay": 0.0001
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0001
      },
      {
        "lr": 0.006,
        "weight_decay": 0.0001
      }
    ],
    "idea_grid": [
      {
        "lr": 0.001,
        "weight_decay": 0.0001
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0001
      },
      {
        "lr": 0.006,
        "weight_decay": 0.0001
      }
    ],
    "baseline_selection": "sweep_baseline on seeds 0..3, full reevaluation on 0..7"
  }
}