{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 18,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "epochs": 18,
          "weight_decay": 0.0
        },
        "mean": 0.009193785954266787
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 18,
          "weight_decay": 0.0
        },
        "mean": 0.0050034308223985136
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18,
          "weight_decay": 0.0
        },
        "mean": 0.002262153459014371
      }
    ],
    "full": {
      "mean": 0.001892383472295478,
      "std": 0.0005824768770598943,
      "per_seed": [
        0.0016680180560797453,
        0.0018032685620710254,
        0.002757444279268384,
        0.0028198829386383295,
        0.0014833298046141863,
        0.0013202878180891275,
        0.0011803944362327456,
        0.0021064418833702803
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.0024836512457113713,
    "std": 0.0007913986756607849,
    "per_seed": [
      0.0018633758882060647,
      0.002772978274151683,
      0.003546620486304164,
      0.003868584055453539,
      0.00169182859826833,
      0.001610392238944769,
      0.002222771057859063,
      0.002292659366503358
    ],
    "n": 8,
    "best_cfg": {
      "lr": 0.006,
      "epochs": 18,
      "weight_decay": 0.0,
      "q": 0.25,
      "noise": 0.02
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18,
          "weight_decay": 0.0,
          "q": 0.25,
          "noise": 0.02
        },
        "mean": 0.0024836512457113713
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18,
          "weight_decay": 0.0,
          "q": 0.5,
          "noise": 0.02
        },
        "mean": 0.0025042231136467308
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18,
          "weight_decay": 0.0,
          "q": 0.75,
          "noise": 0.02
        },
        "mean": 0.0025412623363081366
      }
    ],
    "selected_cfg": {
      "lr": 0.006,
      "epochs": 18,
      "weight_decay": 0.0,
      "q": 0.25,
      "noise": 0.02
    }
  },
  "comparison": {
    "delta_mean": 0.0005912677734158933,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0001953578321263194,
      0.0009697097120806575,
      0.00078917620703578,
      0.0010487011168152094,
      0.0002084987936541438,
      0.00029010442085564137,
      0.0010423766216263175,
      0.00018621748313307762
    ],
    "p_value": 0.0081,
    "mde": 0.000339375496055173,
    "mde_rel_pct": 17.933759252478964,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "dissipative chiral latent dynamics should remain stable and reduce local perturbation response",
    "trained_model_observation": {
      "baseline": {
        "perturbation": 0.01,
        "response_rms": 8.569472265662625e-05,
        "output_rms": 0.1667313128709793
      },
      "idea": {
        "perturbation": 0.01,
        "response_rms": 8.628764771856368e-05,
        "output_rms": 0.16530634462833405
      }
    },
    "predicted_response_ratio": "<= 1.0",
    "observed_response_ratio": 1.0069190264772103,
    "confirmed": false
  },
  "structural_match": "dynamics: stability/control and multi-step pendulum rollout"
}