{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0
        },
        "mean": 0.001414267288055271
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.0008843674877425656
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "mean": 0.0005579828139161691
      }
    ],
    "full": {
      "mean": 0.0005214317206991836,
      "std": 7.105061588211062e-05,
      "per_seed": [
        0.0005374288302846253,
        0.00047665066085755825,
        0.0005716764717362821,
        0.0006461752927862108,
        0.0005541553255170584,
        0.0004454980371519923,
        0.00040709308814257383,
        0.0005327760591171682
      ],
      "n": 8
    }
  },
  "idea": {
    "best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0
        },
        "mean": 0.0013487355754477903,
        "std": 0.0004249648894380296,
        "per_seed": [
          0.0011989021440967917,
          0.0010821575997397304,
          0.0014545865124091506,
          0.0019255068618804216,
          0.0007581147947348654,
          0.0009458610438741744,
          0.0013719621347263455,
          0.002052793512120843
        ],
        "n": 8
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.0008453956179437228,
        "std": 0.00020597588608945252,
        "per_seed": [
          0.00080592290032655,
          0.0006897490820847452,
          0.0008771982393227518,
          0.0011676604626700282,
          0.0006385938613675535,
          0.0006526323850266635,
          0.0007422250346280634,
          0.0011891829781234264
        ],
        "n": 8
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "mean": 0.0005217095131229144,
        "std": 7.135342401294591e-05,
        "per_seed": [
          0.0005381343653425574,
          0.0004766805504914373,
          0.000572634453419596,
          0.0006471937522292137,
          0.0005527037428691983,
          0.0004458390176296234,
          0.00040668679866939783,
          0.0005338034243322909
        ],
        "n": 8
      }
    ],
    "per_seed": [
      0.0005381343653425574,
      0.0004766805504914373,
      0.000572634453419596,
      0.0006471937522292137,
      0.0005527037428691983,
      0.0004458390176296234,
      0.00040668679866939783,
      0.0005338034243322909
    ],
    "mean": 0.0005217095131229144,
    "std": 7.135342401294591e-05,
    "n": 8
  },
  "comparison": {
    "delta_mean": 2.777924237307161e-07,
    "idea_wins": 2,
    "n_pairs": 8,
    "per_seed_diffs": [
      7.055350579321384e-07,
      2.9889633879065514e-08,
      9.579816833138466e-07,
      1.0184594430029392e-06,
      -1.4515826478600502e-06,
      3.4098047763109207e-07,
      -4.062894731760025e-07,
      1.0273652151226997e-06
    ],
    "p_value": 0.39955,
    "mde": 7.262117301089291e-07,
    "mde_rel_pct": 0.13927264132208098,
    "verdict": "no measurable effect",
    "system_worked": false,
    "paired": {
      "baseline_at_idea_cfg": {
        "mean": 0.0005214317206991836,
        "std": 7.105061588211062e-05,
        "per_seed": [
          0.0005374288302846253,
          0.00047665066085755825,
          0.0005716764717362821,
          0.0006461752927862108,
          0.0005541553255170584,
          0.0004454980371519923,
          0.00040709308814257383,
          0.0005327760591171682
        ],
        "n": 8
      },
      "deltas_idea_minus_baseline": [
        7.055350579321384e-07,
        2.9889633879065514e-08,
        9.579816833138466e-07,
        1.0184594430029392e-06,
        -1.4515826478600502e-06,
        3.4098047763109207e-07,
        -4.062894731760025e-07,
        1.0273652151226997e-06
      ],
      "pvalue": 0.39955
    }
  },
  "paired": {
    "baseline_at_idea_cfg": {
      "mean": 0.0005214317206991836,
      "std": 7.105061588211062e-05,
      "per_seed": [
        0.0005374288302846253,
        0.00047665066085755825,
        0.0005716764717362821,
        0.0006461752927862108,
        0.0005541553255170584,
        0.0004454980371519923,
        0.00040709308814257383,
        0.0005327760591171682
      ],
      "n": 8
    },
    "deltas_idea_minus_baseline": [
      7.055350579321384e-07,
      2.9889633879065514e-08,
      9.579816833138466e-07,
      1.0184594430029392e-06,
      -1.4515826478600502e-06,
      3.4098047763109207e-07,
      -4.062894731760025e-07,
      1.0273652151226997e-06
    ],
    "pvalue": 0.39955
  },
  "protocol": {
    "epochs": 24,
    "batch": 128,
    "n_seeds": 8,
    "loss": "MSE plus OT monotonicity and displacement penalties"
  },
  "mechanism_signature": {
    "prediction": "OT monotonicity predicts positive terminal-angle Jacobian",
    "idea": {
      "predicted_monotone_fraction": 1.0,
      "observed_monotone_fraction": 1.0,
      "observed_mean_terminal_angle_jacobian": 0.24786332249641418,
      "confirmed": true
    },
    "baseline": {
      "predicted_monotone_fraction": 1.0,
      "observed_monotone_fraction": 1.0,
      "observed_mean_terminal_angle_jacobian": 0.2478588968515396,
      "confirmed": true
    },
    "confirmed": true
  }
}