{
  "bench_version": 1,
  "track": "relational_dynamics",
  "model": "pair_temporal_mlp",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.8927807062864304
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.8921257555484772
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.8923652321100235
      }
    ],
    "full": {
      "mean": 0.9345984682440758,
      "std": 0.08055134979477402,
      "per_seed": [
        0.946091890335083,
        0.782263457775116,
        0.9252486824989319,
        0.9148989915847778,
        1.0442157983779907,
        1.0487204790115356,
        0.8793458342552185,
        0.9360026121139526
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.014908512006513774,
    "std": 0.0029079161802027706,
    "per_seed": [
      0.012118596583604813,
      0.013483788818120956,
      0.013024883344769478,
      0.01563272811472416,
      0.011209259741008282,
      0.017514415085315704,
      0.015654947608709335,
      0.020629476755857468
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.919689956237562,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.9339732937514782,
      -0.768779668956995,
      -0.9122237991541624,
      -0.8992662634700537,
      -1.0330065386369824,
      -1.03120606392622,
      -0.8636908866465092,
      -0.9153731353580952
    ],
    "p_value": 0.0081,
    "mde": 0.0719854515760221,
    "mde_rel_pct": 7.702286492216108,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "custom_track": {
    "name": "relational_dynamics",
    "file": "relational_dynamics_track.py",
    "domain": "dynamics"
  },
  "idea_config": {
    "lr": 0.01
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "result": {
        "mean": 0.6230705045163631,
        "std": 0.134810917972084,
        "per_seed": [
          0.7404102087020874,
          0.42426830530166626,
          0.6833330392837524,
          0.4215412437915802,
          0.5891903042793274,
          0.7319473028182983,
          0.5875273942947388,
          0.8063462376594543
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "result": {
        "mean": 0.09541938733309507,
        "std": 0.014735930247991384,
        "per_seed": [
          0.10757716745138168,
          0.07397669553756714,
          0.07694181054830551,
          0.0862903743982315,
          0.09326057136058807,
          0.11803340911865234,
          0.10881876945495605,
          0.09845630079507828
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01
      },
      "result": {
        "mean": 0.014908512006513774,
        "std": 0.0029079161802027706,
        "per_seed": [
          0.012118596583604813,
          0.013483788818120956,
          0.013024883344769478,
          0.01563272811472416,
          0.011209259741008282,
          0.017514415085315704,
          0.015654947608709335,
          0.020629476755857468
        ],
        "n": 8
      }
    }
  ],
  "math_check": {
    "inactive_retention_max_abs_error": 0.0,
    "gru_outputs_finite": true,
    "retention_exact": true
  },
  "mechanism_signature": {
    "prediction": "persistent pair state should reduce reactivation error after early evidence is masked",
    "baseline_reactivation_mse": 0.9345984682440758,
    "idea_reactivation_mse": 0.3951987475156784,
    "observed_ratio_idea_over_baseline": 0.4228540501015137,
    "confirmed": true
  }
}