{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.001,
      "alpha": 0.7,
      "sigma": 0.035
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "alpha": 0.7,
          "sigma": 0.035
        },
        "mean": 0.8283906430006027
      },
      {
        "cfg": {
          "lr": 0.003,
          "alpha": 0.7,
          "sigma": 0.035
        },
        "mean": 0.8293724805116653
      },
      {
        "cfg": {
          "lr": 0.01,
          "alpha": 0.7,
          "sigma": 0.035
        },
        "mean": 0.8328554034233093
      }
    ],
    "full": {
      "mean": 0.787501223385334,
      "std": 0.06788976443931306,
      "per_seed": [
        0.8156408071517944,
        0.7547019720077515,
        0.8308971524238586,
        0.9123226404190063,
        0.7518438100814819,
        0.7541651725769043,
        0.8133183717727661,
        0.6671198606491089
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.7941433116793633,
    "std": 0.07100903064007838,
    "per_seed": [
      0.8096513748168945,
      0.803184986114502,
      0.8362289667129517,
      0.9341802597045898,
      0.7649334669113159,
      0.7608115077018738,
      0.7781288623809814,
      0.6660270690917969
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.006642088294029236,
    "idea_wins": 3,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.005989432334899902,
      0.04848301410675049,
      0.005331814289093018,
      0.021857619285583496,
      0.013089656829833984,
      0.006646335124969482,
      -0.03518950939178467,
      -0.0010927915573120117
    ],
    "p_value": 0.4855,
    "mde": 0.0199747259489214,
    "mde_rel_pct": 2.5364691959529213,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "idea_config": {
      "lr": 0.001,
      "alpha": 0.7,
      "sigma": 0.035
    },
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "alpha": 0.7,
          "sigma": 0.035
        },
        "result": {
          "mean": 0.7941433116793633,
          "std": 0.07100903064007838,
          "per_seed": [
            0.8096513748168945,
            0.803184986114502,
            0.8362289667129517,
            0.9341802597045898,
            0.7649334669113159,
            0.7608115077018738,
            0.7781288623809814,
            0.6660270690917969
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.003,
          "alpha": 0.7,
          "sigma": 0.035
        },
        "result": {
          "mean": 0.8040007650852203,
          "std": 0.07647255737581943,
          "per_seed": [
            0.8088628649711609,
            0.8104173541069031,
            0.8454757928848267,
            0.9598079919815063,
            0.7718257308006287,
            0.7834799289703369,
            0.7857349514961243,
            0.6664015054702759
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.01,
          "alpha": 0.7,
          "sigma": 0.035
        },
        "result": {
          "mean": 0.8066116720438004,
          "std": 0.07406785573886294,
          "per_seed": [
            0.811928391456604,
            0.8005879521369934,
            0.8522548079490662,
            0.9512794017791748,
            0.7587114572525024,
            0.7952184677124023,
            0.8118025064468384,
            0.6711103916168213
          ],
          "n": 8
        }
      }
    ],
    "sampler": "feedback pendulum rollout + Gaussian exploration + uniform reservoir",
    "mechanism_signature": {
      "prediction": "gradient sign predicts which bounded control increases model-predicted next angle",
      "observed_sign_agreement": 1.0,
      "predicted_threshold": 0.75,
      "confirmed": true
    },
    "protocol_note": "8 paired seeds; baseline and idea share rnn_small, Adam, epochs, batch, and lr union."
  }
}