{
  "bench_version": 1,
  "track": "poisson_boundary",
  "model": "scalar_potential_backbone",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.03
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.12233347818255424
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.05105730285868049
      },
      {
        "cfg": {
          "lr": 0.03
        },
        "mean": 0.009451728663407266
      }
    ],
    "full": {
      "mean": 0.01093649520771578,
      "std": 0.003025037049171694,
      "per_seed": [
        0.00799343828111887,
        0.006817351561039686,
        0.010449049063026905,
        0.012547075748443604,
        0.008240480907261372,
        0.011241904459893703,
        0.01626167818903923,
        0.013940983451902866
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.03724087378941476,
    "std": 0.012178382868521676,
    "per_seed": [
      0.030537452548742294,
      0.06148594617843628,
      0.022630251944065094,
      0.05179433524608612,
      0.032382115721702576,
      0.02730206958949566,
      0.03700961917638779,
      0.0347851999104023
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.026304378581698984,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.022544014267623425,
      0.05466859461739659,
      0.012181202881038189,
      0.03924725949764252,
      0.024141634814441204,
      0.016060165129601955,
      0.020747940987348557,
      0.02084421645849943
    ],
    "p_value": 0.0081,
    "mde": 0.01163752387239483,
    "mde_rel_pct": 106.40999379933409,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "stage1_prediction": "d squared equals zero for the learned potential gradient",
    "baseline_gradient_curl_rms": 1.36577753551137e-07,
    "predicted_gradient_curl_rms": 0.0,
    "observed_gradient_curl_rms": 1.154990201257533e-07,
    "n_probe": 128,
    "confirmed": true,
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.003
        },
        "result": {
          "mean": 0.11393675301223993,
          "std": 0.01067011604185375,
          "per_seed": [
            0.11674976348876953,
            0.11242678761482239,
            0.09828850626945496,
            0.12337931990623474,
            0.13426120579242706,
            0.11549603939056396,
            0.10730288922786713,
            0.1035895124077797
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "result": {
          "mean": 0.08499461971223354,
          "std": 0.00870385202148945,
          "per_seed": [
            0.07853147387504578,
            0.0928913876414299,
            0.07291875034570694,
            0.09869463741779327,
            0.09521957486867905,
            0.08183202892541885,
            0.08108515292406082,
            0.07878395169973373
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.03
        },
        "result": {
          "mean": 0.03724087378941476,
          "std": 0.012178382868521676,
          "per_seed": [
            0.030537452548742294,
            0.06148594617843628,
            0.022630251944065094,
            0.05179433524608612,
            0.032382115721702576,
            0.02730206958949566,
            0.03700961917638779,
            0.0347851999104023
          ],
          "n": 8
        }
      }
    ],
    "math_check": {
      "nilpotence_max_abs": 0.0,
      "derivative_identity_max_abs": 0.0
    }
  },
  "math_check": {
    "nilpotence_max_abs": 0.0,
    "derivative_identity_max_abs": 0.0
  },
  "idea_selected_cfg": {
    "lr": 0.03
  }
}