{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "config": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "results": [
          30.65192222595215,
          26.219579696655273,
          21.692813873291016,
          23.84225082397461
        ],
        "mean": 25.60164165496826
      },
      {
        "config": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "results": [
          13.522106170654297,
          14.461689949035645,
          14.807339668273926,
          12.651887893676758
        ],
        "mean": 13.860755920410156
      },
      {
        "config": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "results": [
          10.067484855651855,
          12.066851615905762,
          9.622394561767578,
          10.014313697814941
        ],
        "mean": 10.442761182785034
      },
      {
        "config": {
          "lr": 0.003,
          "weight_decay": 0.0001
        },
        "results": [
          13.528329849243164,
          14.431048393249512,
          14.758162498474121,
          12.640395164489746
        ],
        "mean": 13.839483976364136
      }
    ],
    "full": {
      "mean": 10.930935978889465,
      "std": 1.3983305692789296,
      "per_seed": [
        10.067484855651855,
        12.066851615905762,
        9.622394561767578,
        10.014313697814941,
        8.787652015686035,
        11.810267448425293,
        12.032318115234375,
        13.046205520629883
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 10.996043920516968,
    "std": 1.169447967118747,
    "per_seed": [
      9.497220993041992,
      12.14220142364502,
      11.333624839782715,
      9.796889305114746,
      9.323980331420898,
      11.6688232421875,
      11.8473482131958,
      12.35826301574707
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.06510794162750244,
    "idea_wins": 5,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.5702638626098633,
      0.07534980773925781,
      1.7112302780151367,
      -0.2174243927001953,
      0.5363283157348633,
      -0.14144420623779297,
      -0.18496990203857422,
      -0.6879425048828125
    ],
    "p_value": 0.8863,
    "mde": 0.6389629457421157,
    "mde_rel_pct": 5.845455018455167,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "quantity": "mean squared action error to quadratic proximal teacher on held-out states",
    "predicted": "proximal objective should reduce teacher-action mismatch",
    "observed_note": "computed from trained models on benchmark-derived perturbations; full values recorded below",
    "baseline_best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0
    },
    "idea_best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0
    },
    "confirmed": false
  },
  "idea_sweep": [
    {
      "config": {
        "lr": 0.001,
        "weight_decay": 0.0
      },
      "full": {
        "mean": 25.094110250473022,
        "std": 4.455265918443395,
        "per_seed": [
          27.867267608642578,
          23.728221893310547,
          22.022008895874023,
          23.82248878479004,
          17.760637283325195,
          31.66156578063965,
          22.79692268371582,
          31.093769073486328
        ],
        "n": 8
      },
      "mean": 25.094110250473022
    },
    {
      "config": {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      "full": {
        "mean": 14.121166110038757,
        "std": 1.3397338959449183,
        "per_seed": [
          13.135297775268555,
          14.45909309387207,
          14.704912185668945,
          12.331259727478027,
          12.489986419677734,
          13.940347671508789,
          15.557445526123047,
          16.35098648071289
        ],
        "n": 8
      },
      "mean": 14.121166110038757
    },
    {
      "config": {
        "lr": 0.006,
        "weight_decay": 0.0
      },
      "full": {
        "mean": 10.996043920516968,
        "std": 1.169447967118747,
        "per_seed": [
          9.497220993041992,
          12.14220142364502,
          11.333624839782715,
          9.796889305114746,
          9.323980331420898,
          11.6688232421875,
          11.8473482131958,
          12.35826301574707
        ],
        "n": 8
      },
      "mean": 10.996043920516968
    }
  ],
  "protocol": {
    "paired_seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ],
    "epochs": 18,
    "batch": 128,
    "grid_union": [
      {
        "lr": 0.001,
        "weight_decay": 0.0
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      {
        "lr": 0.006,
        "weight_decay": 0.0
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0001
      }
    ],
    "structural_match": "tabular: loss/regularization intervention"
  }
}