# Стенд-проверка (stage-2) · промт оператора:

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 9,
  "verdict": "Implemented the Adaptive Zonotope Safety Shield on the structurally matched official dynamics track using rnn_small, online residual center/radius updates, and a reachable-set training penalty. Test MSE decreased slightly from 0.0027758953 to 0.0026812993, but the paired permutation test was non-significant (p=0.58435), so the benchmark criterion for a win was not met. The mechanism signature was not confirmed because the learned radius was very large and all reachable intervals were unsafe.",
  "metrics": {
    "baseline": "lr=0.01, 10 epochs; mean test MSE=0.0027758953, std=0.0017084856",
    "idea": "lr=0.01, shield_lambda=0.06, 10 epochs; mean test MSE=0.0026812993, std=0.000926?; paired delta=-0.0000945959, 4/8 wins, p=0.58435",
    "math": "1000 affine zonotope cases; containment disagreements=0; maximum sampled support gap=0.0",
    "mechanism": "Held-out residual coverage=1.0, learned radius q=3.66355, unsafe reachable-interval rate=1.0, confirmed=false"
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 stage2_bench.py",
  "files": [
    "stage2_bench.py",
    "bench_report.json",
    "bench_stdout.txt"
  ],
  "limitations": "Only the official supervised dynamics benchmark was tested. PPO, online action-time shielding, closed-loop multi-step rollouts, rejection rates, safety violations over episodes, Jacobian estimation, disturbance shifts, and computational overhead were not tested. The implementation uses a differentiable reachable-angle penalty as a training proxy rather than a deployed action-time shield.",
  "bench_report": {
    "bench_version": 1,
    "track": "dynamics",
    "model": "rnn_small",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.01,
        "epochs": 10
      },
      "full_mean": 0.002775895278318785,
      "full_std": 0.0017084856346187775
    },
    "idea": {
      "best_cfg": {
        "lr": 0.01,
        "epochs": 10,
        "shield_lambda": 0.06
      },
      "mean": 0.0026812993455678225
    },
    "comparison": {
      "delta_mean": -9.459593275096267e-05,
      "idea_wins": 4,
      "n_pairs": 8,
      "p_value": 0.58435,
      "verdict": "no significant win",
      "system_worked": false
    },
    "mechanism_signature": {
      "heldout_residual_coverage": 1.0,
      "observed_residual_center": 1.96993350982666e-05,
      "observed_residual_radius_q": 3.6635516929626464,
      "unsafe_point_prediction_rate": 0.06,
      "unsafe_reachable_interval_rate": 1.0,
      "confirmed": false
    },
    "math_check": {
      "cases": 1000,
      "containment_disagreements": 0,
      "max_sample_support_gap": 0.0
    }
  },
  "system_verdict": "failed",
  "practical_verdict": "no_effect",
  "mechanism_ok": 0,
  "system_judged": true
}