{
  "bench_version": 1,
  "track": "robust_cbf_pendulum_policy",
  "model": "shared_mlp_32",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 15,
      "barrier": false
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 15,
          "barrier": false
        },
        "mean": 0.021794200874865055
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 15,
          "barrier": false
        },
        "mean": 0.002334954886464402
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 15,
          "barrier": false
        },
        "mean": 0.0018331437022425234
      }
    ],
    "full": {
      "mean": 0.0019978795608039945,
      "std": 0.0005495084055684182,
      "per_seed": [
        0.0015628907131031156,
        0.0015461408765986562,
        0.0021467802580446005,
        0.0020767629612237215,
        0.0030877823010087013,
        0.0011752876453101635,
        0.0020312685519456863,
        0.0023561231791973114
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.002375210518948734,
    "std": 0.0007107137551610928,
    "per_seed": [
      0.0017161896685138345,
      0.002388743683695793,
      0.003441448090597987,
      0.002218520501628518,
      0.0035038175992667675,
      0.0017992532812058926,
      0.0024698558263480663,
      0.0014638555003330112
    ],
    "n": 8,
    "selection_sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 15,
          "barrier": true,
          "weight": 1.0
        },
        "mean": 0.03862802591174841
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 15,
          "barrier": true,
          "weight": 2.0
        },
        "mean": 0.0024412254861090332
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 15,
          "barrier": true,
          "weight": 4.0
        },
        "mean": 0.003327691287267953
      }
    ]
  },
  "comparison": {
    "delta_mean": 0.00037733095814473927,
    "idea_wins": 1,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.00015329895541071892,
      0.000842602807097137,
      0.0012946678325533867,
      0.0001417575404047966,
      0.0004160352982580662,
      0.0006239656358957291,
      0.00043858727440238,
      -0.0008922676788643003
    ],
    "p_value": 0.1407,
    "mde": 0.0005327468319021694,
    "mde_rel_pct": 26.665613000604466,
    "verdict": "no significant win",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": {
      "lower_bound": "epsilon - L_r delta",
      "delta": 0.0052734375
    },
    "observed_from_trained_models": {
      "min_residual_mean": -3.3228249847888947,
      "violation_fraction_mean": 0.2471875,
      "L_r_estimate_mean": 1.372166395187378,
      "bound_lower_mean": 0.07276396627537907,
      "n_models": 8
    },
    "confirmed": false
  },
  "custom_track": {
    "name": "barrier_certified_pendulum_policy",
    "file": "barrier_bench.py",
    "domain": "dynamics"
  }
}