{
  "bench_version": 1,
  "track": "poisson_boundary",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "boundary_weight": 1.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "boundary_weight": 1.0
        },
        "mean": 0.010570373153313994
      },
      {
        "cfg": {
          "lr": 0.001,
          "boundary_weight": 10.0
        },
        "mean": 0.014104659901931882
      },
      {
        "cfg": {
          "lr": 0.001,
          "boundary_weight": 30.0
        },
        "mean": 0.05715882801450789
      },
      {
        "cfg": {
          "lr": 0.003,
          "boundary_weight": 1.0
        },
        "mean": 0.008062692591920495
      },
      {
        "cfg": {
          "lr": 0.003,
          "boundary_weight": 10.0
        },
        "mean": 0.010542358737438917
      },
      {
        "cfg": {
          "lr": 0.003,
          "boundary_weight": 30.0
        },
        "mean": 0.014223965117707849
      },
      {
        "cfg": {
          "lr": 0.01,
          "boundary_weight": 1.0
        },
        "mean": 0.007657136651687324
      },
      {
        "cfg": {
          "lr": 0.01,
          "boundary_weight": 10.0
        },
        "mean": 0.01242852327413857
      },
      {
        "cfg": {
          "lr": 0.01,
          "boundary_weight": 30.0
        },
        "mean": 0.04939912143163383
      }
    ],
    "full": {
      "mean": 0.007044873433187604,
      "std": 0.00100136969136606,
      "per_seed": [
        0.006205223500728607,
        0.00873982161283493,
        0.008036286570131779,
        0.00764721492305398,
        0.005511410068720579,
        0.006294506136327982,
        0.0072539327666163445,
        0.00667059188708663
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.006475340866018087,
    "std": 0.0010829860742993793,
    "per_seed": [
      0.005347711965441704,
      0.007960012182593346,
      0.00744650699198246,
      0.006636394187808037,
      0.004956180229783058,
      0.005183100700378418,
      0.007344032172113657,
      0.006928788498044014
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.0005695325671695173,
    "idea_wins": 6,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0008575115352869034,
      -0.0007798094302415848,
      -0.0005897795781493187,
      -0.001010820735245943,
      -0.000555229838937521,
      -0.001111405435949564,
      9.009940549731255e-05,
      0.0002581966109573841
    ],
    "p_value": 0.0317,
    "mde": 0.0004164460873821372,
    "mde_rel_pct": 5.911335261472642,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "custom_track": {
    "name": "poisson_boundary",
    "file": "fractional_dirichlet_track.py",
    "domain": "pde"
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "lambda_g": 0.0
      },
      "mean": 0.013011600589379668
    },
    {
      "cfg": {
        "lr": 0.003,
        "lambda_g": 0.001
      },
      "mean": 0.008521844982169569
    },
    {
      "cfg": {
        "lr": 0.01,
        "lambda_g": 0.01
      },
      "mean": 0.0068476563319563866
    }
  ],
  "protocol": {
    "epochs": 35,
    "batch": 128,
    "a": 0.75,
    "s": 0.1,
    "delta": 1e-05,
    "paired_seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ]
  },
  "runtime_seconds": 58.30213451385498,
  "mechanism_signature": {
    "quantity": "median |u| at d=0.02 divided by median |u| at d=0.10 on trained models",
    "predicted_idea_ratio": 0.2990697562442441,
    "predicted_baseline_ratio": "not constrained (free output with boundary penalty)",
    "observed_idea": 0.302967306501504,
    "observed_baseline": 0.37791017847441105,
    "confirmed": true
  }
}