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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 9,
  "verdict": "Implemented a matched dynamics benchmark using the standard rnn_small architecture and canonical train_model path, with a Farkas-certified reduction from 64 redundant interval halfspaces to 2 retained constraints. The mechanism signature confirmed zero full/reduced output disagreement and exact certificates, but the shielded system had substantially worse test MSE (0.0523780 vs 0.0001147401), with paired delta +0.0522633 and permutation p=0.0081. The geometric mechanism transferred, but it did not improve the independent neural task metric.",
  "metrics": {
    "baseline": "dynamics/rnn_small; 8-seed test MSE mean 0.0001147401, std 0.0000402690; baseline sweep selected lr=0.00665.",
    "idea": "dynamics/rnn_small with certified interval shield; 8-seed best test MSE mean 0.0523780, std 0.0088756; paired delta +0.0522633, 0/8 wins, permutation p=0.0081; 64 constraints reduced to 2 (3.125%)."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 bench_farkas.py",
  "files": [
    "bench_farkas.py",
    "bench_report.json",
    "bench_stdout.txt"
  ],
  "limitations": "The built-in dynamics track predicts a future pendulum angle rather than directly training a closed-loop policy, so this tests transfer of the safety projection rather than full multi-agent RL. Constraints were redundant scalar interval halfspaces, not heterogeneous obstacle geometry. End-to-end constraint-construction and solver timing were not benchmarked. The hard output clamp changes the supervised target range and caused the observed task-metric degradation.",
  "bench_report": {
    "bench_version": 1,
    "track": "dynamics",
    "model": "rnn_small",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.00665
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001
          },
          "mean": 0.0009722943
        },
        {
          "cfg": {
            "lr": 0.002
          },
          "mean": 0.0006509074
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.0004595853
        },
        {
          "cfg": {
            "lr": 0.004
          },
          "mean": 0.0003482927
        },
        {
          "cfg": {
            "lr": 0.005
          },
          "mean": 0.0002485937
        },
        {
          "cfg": {
            "lr": 0.00067
          },
          "mean": 0.0011799606
        },
        {
          "cfg": {
            "lr": 0.00134
          },
          "mean": 0.0008329209
        },
        {
          "cfg": {
            "lr": 0.00268
          },
          "mean": 0.0005083114
        },
        {
          "cfg": {
            "lr": 0.00402
          },
          "mean": 0.0003466854
        },
        {
          "cfg": {
            "lr": 0.00536
          },
          "mean": 0.0002244893
        },
        {
          "cfg": {
            "lr": 0.00665
          },
          "mean": 0.0001395188
        }
      ],
      "full": {
        "mean": 0.0001147401,
        "std": 4.0269e-05,
        "per_seed": [
          0.0001932993,
          0.000143844,
          8.01379e-05,
          0.0001407938,
          0.0001187587,
          8.25471e-05,
          6.3313e-05,
          9.52268e-05
        ],
        "n": 8
      }
    },
    "idea": {
      "mean": 0.0523780384,
      "std": 0.008875649,
      "per_seed": [
        0.041060634,
        0.058054667,
        0.0539846234,
        0.0682321563,
        0.0553050973,
        0.0380525403,
        0.0531917065,
        0.0511428826
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": 0.0522632983,
      "idea_wins": 0,
      "n_pairs": 8,
      "per_seed_diffs": [
        0.0408673346,
        0.0579108229,
        0.0539044855,
        0.0680913626,
        0.0551863386,
        0.0379699931,
        0.0531283936,
        0.0510476558
      ],
      "p_value": 0.0081,
      "mde": 0.007932782,
      "mde_rel_pct": 6913.6975,
      "verdict": "idea worse (significant)",
      "system_worked": false
    },
    "mechanism_signature": {
      "constraint_count_full": 64,
      "constraint_count_retained": 2,
      "retained_fraction": 0.03125,
      "certificate_max_residual": 0.0,
      "certificate_max_offset_violation": 0.0,
      "trained_test_samples": 400,
      "full_reduced_max_output_difference": 0.0,
      "full_reduced_decision_disagreement": 0.0,
      "predicted_zero_disagreement_observed": true,
      "confirmed": true
    }
  },
  "system_verdict": "partial",
  "practical_verdict": "harms",
  "mechanism_ok": 1,
  "system_judged": true
}