{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 18,
      "rho": 0.9,
      "k": 2
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 18,
          "rho": 0.9,
          "k": 2
        },
        "mean": 0.0026806407840922475
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 18,
          "rho": 0.9,
          "k": 2
        },
        "mean": 0.001453446806408465
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18,
          "rho": 0.9,
          "k": 2
        },
        "mean": 0.0007141287642298266
      }
    ],
    "full": {
      "mean": 0.0007108385761966929,
      "std": 0.00020260791778280052,
      "per_seed": [
        0.0008331689168699086,
        0.0007008879329077899,
        0.0006333848577924073,
        0.0008832181920297444,
        0.0010298240231350064,
        0.0005573644884862006,
        0.00032093568006530404,
        0.0007279245182871819
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.0006244764626899268,
    "std": 0.00017259395969689844,
    "per_seed": [
      0.0005345472018234432,
      0.0004471810825634748,
      0.0004362085019238293,
      0.0008414528565481305,
      0.00048033404164016247,
      0.0008765239617787302,
      0.0005815455224364996,
      0.0007980185328051448
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -8.636211350676604e-05,
    "idea_wins": 5,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0002986217150464654,
      -0.00025370685034431517,
      -0.00019717635586857796,
      -4.1765335481613874e-05,
      -0.000549489981494844,
      0.0003191594732925296,
      0.00026060984237119555,
      7.009401451796293e-05
    ],
    "p_value": 0.47205,
    "mde": 0.0002470609130160734,
    "mde_rel_pct": 34.75626130730844,
    "verdict": "no significant win",
    "system_worked": false
  },
  "sweep_parity": {
    "union_grid": [
      {
        "lr": 0.001,
        "epochs": 18,
        "rho": 0.9,
        "k": 2
      },
      {
        "lr": 0.003,
        "epochs": 18,
        "rho": 0.9,
        "k": 2
      },
      {
        "lr": 0.006,
        "epochs": 18,
        "rho": 0.9,
        "k": 2
      }
    ],
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 18,
          "rho": 0.9,
          "k": 2
        },
        "mean": 0.0019245385192334652
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 18,
          "rho": 0.9,
          "k": 2
        },
        "mean": 0.0012154859578004107
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18,
          "rho": 0.9,
          "k": 2
        },
        "mean": 0.0005648474107147194
      }
    ]
  },
  "adaptation": {
    "rho": 0.9,
    "k": 2,
    "probe_budget": "one batch per epoch"
  },
  "mechanism_signature": {
    "claim": "discounted probe gap is lower late than over training on trained dynamics models",
    "predicted_late_gap_less_than_mean": true,
    "observed_mean_gap": 0.0,
    "observed_late_gap": 0.0,
    "relative_change": 0.0,
    "trained_model_measurements": [
      {
        "seed": 0,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0005345472018234432
      },
      {
        "seed": 1,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0004471810825634748
      },
      {
        "seed": 2,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0004362085019238293
      },
      {
        "seed": 3,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0008414528565481305
      },
      {
        "seed": 4,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.00048033404164016247
      },
      {
        "seed": 5,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0008765239617787302
      },
      {
        "seed": 6,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0005815455224364996
      },
      {
        "seed": 7,
        "gap_mean": 0.0,
        "gap_last": 0.0,
        "final_lr": 0.006,
        "down_events": 0,
        "test_mse": 0.0007980185328051448
      }
    ],
    "confirmed": false
  }
}