{
  "bench_version": 1,
  "track": "tabular",
  "model": "two_branch_mlp",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.3566400483250618
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.27394459396600723
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.23046058416366577
      }
    ],
    "full": {
      "mean": 0.23951114527881145,
      "std": 0.04028734767167621,
      "per_seed": [
        0.1893874704837799,
        0.2472962588071823,
        0.2523687779903412,
        0.23278982937335968,
        0.1838403344154358,
        0.25920143723487854,
        0.3209288716316223,
        0.2302761822938919
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.3616223409771919,
    "std": 0.09797382371900515,
    "per_seed": [
      0.28693538904190063,
      0.2831035852432251,
      0.28846070170402527,
      0.3903844356536865,
      0.3120247721672058,
      0.30676016211509705,
      0.5750100016593933,
      0.4502996802330017
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.12211119569838047,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.09754791855812073,
      0.035807326436042786,
      0.03609192371368408,
      0.15759460628032684,
      0.12818443775177002,
      0.047558724880218506,
      0.254081130027771,
      0.2200234979391098
    ],
    "p_value": 0.0081,
    "mde": 0.0701771215456511,
    "mde_rel_pct": 29.300148627304555,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "result": {
        "mean": 0.3616223409771919,
        "std": 0.09797382371900515,
        "per_seed": [
          0.28693538904190063,
          0.2831035852432251,
          0.28846070170402527,
          0.3903844356536865,
          0.3120247721672058,
          0.30676016211509705,
          0.5750100016593933,
          0.4502996802330017
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "result": {
        "mean": 0.36999374255537987,
        "std": 0.07516870461499706,
        "per_seed": [
          0.3048875033855438,
          0.31957462430000305,
          0.36907637119293213,
          0.3171716332435608,
          0.3382593095302582,
          0.3245992958545685,
          0.5264177322387695,
          0.45996347069740295
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01
      },
      "result": {
        "mean": 5.468297071754932,
        "std": 6.81639231650195,
        "per_seed": [
          0.36661669611930847,
          1.333353877067566,
          0.3249545991420746,
          2.7228331565856934,
          13.045344352722168,
          20.14182472229004,
          4.995171546936035,
          0.8162776231765747
        ],
        "n": 8
      }
    }
  ],
  "track_justification": "Optimizer intervention: official bench assigns optimizer ideas to tabular; both systems use the same branch-swap symmetric MLP and differ only in the update rule.",
  "mechanism_signature": {
    "prediction": "branch-swap parity separates even and odd gradient energy",
    "trained_model_gradient_norms_plus": 0.0739268725739474,
    "trained_model_gradient_norms_minus": 0.05150565393582205,
    "ratio_minus_over_plus": 0.6967108460270031,
    "confirmed": true
  }
}