{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "weight_decay": 0.0001
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "mean": 0.001864717691205442
      },
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0001
        },
        "mean": 0.0018400110420770943
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.0010901302302954718
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001
        },
        "mean": 0.0010647484887158498
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0
        },
        "mean": 0.0006186682076076977
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0001
        },
        "mean": 0.0005735916565754451
      }
    ],
    "full": {
      "mean": 0.0005480735380842816,
      "std": 0.00014996990905603093,
      "per_seed": [
        0.00046045987983234227,
        0.0004709371132776141,
        0.0004756892449222505,
        0.0008872803882695735,
        0.0004885699599981308,
        0.00037048623198643327,
        0.0006456486880779266,
        0.0005855167983099818
      ],
      "n": 8
    },
    "idea_grid": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0001,
          "lambda": 0.05
        },
        "mean": 0.0018400110420770943
      },
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0001,
          "lambda": 0.15
        },
        "mean": 0.0018400110420770943
      },
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0001,
          "lambda": 0.3
        },
        "mean": 0.0018400110420770943
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001,
          "lambda": 0.05
        },
        "mean": 0.0010647484887158498
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001,
          "lambda": 0.15
        },
        "mean": 0.0010647484887158498
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001,
          "lambda": 0.3
        },
        "mean": 0.0010647484887158498
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0001,
          "lambda": 0.05
        },
        "mean": 0.0005735916565754451
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0001,
          "lambda": 0.15
        },
        "mean": 0.0005735916565754451
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0001,
          "lambda": 0.3
        },
        "mean": 0.0005735916565754451
      }
    ]
  },
  "idea": {
    "mean": 0.0005480735380842816,
    "std": 0.00014996990905603093,
    "per_seed": [
      0.00046045987983234227,
      0.0004709371132776141,
      0.0004756892449222505,
      0.0008872803882695735,
      0.0004885699599981308,
      0.00037048623198643327,
      0.0006456486880779266,
      0.0005855167983099818
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.0,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0
    ],
    "p_value": 1.0,
    "mde": 0.0,
    "mde_rel_pct": 0.0,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "adding the interval-zonotope loss should change the trained model task metric",
    "observed_nn": {
      "baseline_mean_test_mse": 0.0005480735380842816,
      "idea_mean_test_mse": 0.0005480735380842816,
      "observed_delta": 0.0,
      "best_cfg": {
        "lr": 0.01,
        "weight_decay": 0.0001,
        "lambda": 0.05
      }
    },
    "toy_numeric_check": {
      "max_radius_recurrence_error": 1.6653345369377348e-16,
      "confirmed": true
    },
    "confirmed": false,
    "note": "The arithmetic radius recurrence is exact, but this does not establish the mechanism on the trained benchmark models."
  }
}