{
  "bench_version": 1,
  "track": "multi_agent_critic_compatibility",
  "model": "smooth_mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "mean": 0.06973899155855179
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.027223403099924326
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "mean": 0.017718153772875667
      }
    ],
    "full": {
      "mean": 0.01805280230473727,
      "std": 0.003010278601654062,
      "per_seed": [
        0.013723039999604225,
        0.01541468221694231,
        0.020424267277121544,
        0.021310625597834587,
        0.02256813645362854,
        0.015233941376209259,
        0.01891121082007885,
        0.016836514696478844
      ],
      "n": 8
    },
    "union_grid": [
      {
        "lr": 0.001,
        "weight_decay": 0.0
      },
      {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      {
        "lr": 0.006,
        "weight_decay": 0.0
      }
    ]
  },
  "idea": {
    "mean": 0.014739889767952263,
    "std": 0.002197491715824413,
    "per_seed": [
      0.012573308311402798,
      0.013758777640759945,
      0.017280390486121178,
      0.018282605335116386,
      0.013562905602157116,
      0.011569413356482983,
      0.01632225140929222,
      0.01456946600228548
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.0033129125367850065,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0011497316882014275,
      -0.0016559045761823654,
      -0.003143876791000366,
      -0.0030280202627182007,
      -0.009005230851471424,
      -0.0036645280197262764,
      -0.0025889594107866287,
      -0.002267048694193363
    ],
    "p_value": 0.0081,
    "mde": 0.0020403039006823757,
    "mde_rel_pct": 11.30186807699642,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "prediction": "compatibility penalty lowers trained-NN cross-partial residual; task MSE may trade off against fit",
    "baseline_mean_residual": 0.22950219362974167,
    "idea_mean_residual": 0.055686311796307564,
    "predicted_vs_observed": {
      "predicted_direction": "lower residual",
      "observed_direction": "lower residual"
    },
    "confirmed": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "lambda": 0.0
      },
      "mean": 0.06973899155855179
    },
    {
      "cfg": {
        "lr": 0.001,
        "lambda": 0.01
      },
      "mean": 0.0697520337998867
    },
    {
      "cfg": {
        "lr": 0.001,
        "lambda": 0.05
      },
      "mean": 0.06980521325021982
    },
    {
      "cfg": {
        "lr": 0.003,
        "lambda": 0.0
      },
      "mean": 0.027223403099924326
    },
    {
      "cfg": {
        "lr": 0.003,
        "lambda": 0.01
      },
      "mean": 0.026897789910435677
    },
    {
      "cfg": {
        "lr": 0.003,
        "lambda": 0.05
      },
      "mean": 0.026794631499797106
    },
    {
      "cfg": {
        "lr": 0.006,
        "lambda": 0.0
      },
      "mean": 0.017718153772875667
    },
    {
      "cfg": {
        "lr": 0.006,
        "lambda": 0.01
      },
      "mean": 0.016406191745772958
    },
    {
      "cfg": {
        "lr": 0.006,
        "lambda": 0.05
      },
      "mean": 0.015473770443350077
    }
  ],
  "custom_track": {
    "name": "multi_agent_critic_compatibility",
    "file": "compat_track.py",
    "domain": "dynamics/control"
  },
  "runtime_sec": 103.8862133026123
}