{
  "bench_version": 1,
  "track": "influence_graph_regression",
  "model": "custom_graph_message_net",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "kappa": 2.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "kappa": 2.0
        },
        "mean": 0.00361063884338364
      },
      {
        "cfg": {
          "lr": 0.003,
          "kappa": 2.0
        },
        "mean": 0.0033815143979154527
      },
      {
        "cfg": {
          "lr": 0.01,
          "kappa": 2.0
        },
        "mean": 0.0028661651886068285
      }
    ],
    "full": {
      "mean": 0.00277794455178082,
      "std": 0.0006137955939218627,
      "per_seed": [
        0.002771663246676326,
        0.001872004708275199,
        0.0030535804107785225,
        0.0037674123886972666,
        0.0020138039253652096,
        0.0023955816868692636,
        0.003390558995306492,
        0.0029589510522782803
      ],
      "n": 8
    }
  },
  "idea": {
    "cfg": {
      "lr": 0.01,
      "kappa": 1.0
    },
    "mean": 0.0063154193630907685,
    "std": 0.0032907033594589473,
    "per_seed": [
      0.005231841467320919,
      0.00240378943271935,
      0.007344594690948725,
      0.011935936287045479,
      0.003391814883798361,
      0.0029857298359274864,
      0.010524877347052097,
      0.006704770959913731
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.0035374748113099486,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0024601782206445932,
      0.0005317847244441509,
      0.004291014280170202,
      0.008168523898348212,
      0.0013780109584331512,
      0.0005901481490582228,
      0.0071343183517456055,
      0.0037458199076354504
    ],
    "p_value": 0.0081,
    "mde": 0.0024180377401689383,
    "mde_rel_pct": 87.04413263464309,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "trained unsaturated message gain tracks xi=kappa/(epsilon+a), and messages stay in [-1,1]",
    "predicted_mean_xi": 6.637609124183655,
    "observed_mean_gain": 6.413445591926575,
    "relative_gain_error": 0.03377172830238511,
    "mean_saturation_fraction": 0.8370833333333333,
    "max_bounded_message": 1.0,
    "per_seed": [
      {
        "slope_observed": 6.329771995544434,
        "xi_mean": 6.630519390106201,
        "sat_fraction": 0.8266666666666667,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.987293889262084
      },
      {
        "slope_observed": 6.746931552886963,
        "xi_mean": 6.751812934875488,
        "sat_fraction": 0.8341666666666666,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.9970302973674653
      },
      {
        "slope_observed": 6.167720794677734,
        "xi_mean": 6.424678802490234,
        "sat_fraction": 0.8333333333333334,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.992888837043883
      },
      {
        "slope_observed": 5.988704681396484,
        "xi_mean": 6.493659019470215,
        "sat_fraction": 0.82,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.9790514842755541
      },
      {
        "slope_observed": 6.530553817749023,
        "xi_mean": 6.727144718170166,
        "sat_fraction": 0.84,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.9836722707672215
      },
      {
        "slope_observed": 6.623795509338379,
        "xi_mean": 6.703503608703613,
        "sat_fraction": 0.8383333333333334,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.9891867545961321
      },
      {
        "slope_observed": 6.393836975097656,
        "xi_mean": 6.778685092926025,
        "sat_fraction": 0.8475,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.9773506801234949
      },
      {
        "slope_observed": 6.526249408721924,
        "xi_mean": 6.590869426727295,
        "sat_fraction": 0.8566666666666667,
        "bounded_max": 1.0,
        "corr_influence_xi": -0.936434300165755
      }
    ],
    "confirmed": true
  },
  "custom_track": {
    "name": "influence_graph_regression",
    "file": "graph_strategic_bench.py",
    "domain": "graph-nn"
  }
}