{
  "bench_version": 1,
  "track": "cycle_parity_graph",
  "model": "graphnet",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003,
      "epochs": 12
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 12
        },
        "mean": 0.3074999889358878
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12
        },
        "mean": 0.2012499978300184
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12
        },
        "mean": 0.2162499960977584
      }
    ],
    "full": {
      "mean": 0.20874999731313437,
      "std": 0.20704392538301097,
      "per_seed": [
        0.0,
        0.28999999165534973,
        0.5,
        0.014999999664723873,
        0.5,
        0.32499998807907104,
        0.0,
        0.03999999910593033
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.0,
    "std": 0.0,
    "per_seed": [
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.20874999731313437,
    "idea_wins": 6,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0,
      -0.28999999165534973,
      -0.5,
      -0.014999999664723873,
      -0.5,
      -0.32499998807907104,
      0.0,
      -0.03999999910593033
    ],
    "p_value": 0.0312,
    "mde": 0.18507366186801333,
    "mde_rel_pct": 88.65804275455608,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "math_checks": {
      "odd_degree_max_residual": 0.0,
      "parity": [
        {
          "edges": 1,
          "max_error": 0
        },
        {
          "edges": 2,
          "max_error": 0
        },
        {
          "edges": 3,
          "max_error": 0
        },
        {
          "edges": 4,
          "max_error": 0
        },
        {
          "edges": 5,
          "max_error": 0
        },
        {
          "edges": 6,
          "max_error": 0
        },
        {
          "edges": 7,
          "max_error": 0
        },
        {
          "edges": 8,
          "max_error": 0
        }
      ],
      "wedge_energy": {
        "predicted": 24,
        "observed": 23.964393615722656,
        "ratio": 0.9985164006551107
      }
    },
    "prediction": "odd incident degree is annihilated exactly at NN scale",
    "predicted_max_residual": 0.0,
    "observed_max_residual": 0.0,
    "confirmed": true,
    "n_observations": 24
  },
  "custom_track": {
    "name": "cycle_parity_graph",
    "file": "bench_fermionic.py",
    "domain": "graph-nn"
  }
}