{
  "bench_version": 1,
  "track": "poisson_dirichlet",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "mean": 0.0014014299667906016
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.00047322634054580703
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0
        },
        "mean": 0.00023210687140817754
      }
    ],
    "full": {
      "mean": 0.00022453273413702846,
      "std": 2.826627803497815e-05,
      "per_seed": [
        0.00021784205455332994,
        0.00023001956287771463,
        0.00027551333187147975,
        0.00020505253633018583,
        0.00025107755209319293,
        0.0002373710594838485,
        0.00019424316997174174,
        0.0001851426059147343
      ],
      "n": 8
    },
    "idea_union_trials": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "mean": 0.00744940631557256
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.002477104659192264
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0
        },
        "mean": 0.0007909908308647573
      }
    ]
  },
  "idea": {
    "mean": 0.0007747690397081897,
    "std": 0.00018247493264257159,
    "per_seed": [
      0.0009708237485028803,
      0.0005817511701025069,
      0.0010273662628605962,
      0.0005840221419930458,
      0.0007391659892164171,
      0.0005464869318529963,
      0.0009673092281445861,
      0.0007812268449924886
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.0005502363055711612,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0007529816939495504,
      0.00035173160722479224,
      0.0007518529309891164,
      0.00037896960566286,
      0.00048808843712322414,
      0.00030911587236914784,
      0.0007730660581728444,
      0.0005960842390777543
    ],
    "p_value": 0.0081,
    "mde": 0.00016245867586821579,
    "mde_rel_pct": 72.3541164243206,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "selection": "best of shared 3-point LR/weight-decay grid on seeds 0-3",
    "idea_best_cfg": {
      "lr": 0.01,
      "weight_decay": 0.0
    },
    "prediction": "nullspace decoder should make C u exactly zero while ambient output violates endpoints",
    "predicted_boundary_residual_idea": 0.0,
    "observed_boundary_residual_idea_max": 0.0,
    "observed_boundary_residual_baseline_max": 0.02415449172258377,
    "observed_boundary_residual_baseline_mean": 0.00435631675645709,
    "observed_boundary_residual_idea_mean": 0.0,
    "ratio_baseline_to_idea_max": 24154490880.0,
    "confirmed": true,
    "trained_models": true
  },
  "custom_track": {
    "name": "poisson_dirichlet",
    "file": "/home/maxwelhelp/all/math2nn/bench/custom_tracks/poisson_dirichlet.py",
    "domain": "pde",
    "reason": "built-in custom PDE track has fixed-grid field outputs and homogeneous Dirichlet constraints"
  },
  "protocol": {
    "epochs": 20,
    "batch": 128,
    "seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ],
    "grid": [
      {
        "lr": 0.001,
        "weight_decay": 0.0
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      {
        "lr": 0.01,
        "weight_decay": 0.0
      }
    ]
  }
}