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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 10,
  "verdict": "Implemented the spectral burn-in/retrieval switch on the structurally matched built-in dynamics track using independently trained rnn_small systems, paired seeds, baseline learning-rate sweep, and the official report protocol. The trained latent contraction proxy had median 0.988, above the 0.94 threshold, causing 100% retrieval; retrieval was consistently worse than observer rollout. The idea lost significantly with delta_mean=+0.00476083 MSE and permutation p=0.0081.",
  "metrics": {
    "baseline": "Best lr=0.01; 8-seed mean MSE 0.0027758953.",
    "idea": "lr=0.01; 8-seed mean MSE 0.0075367271; retrieval rate 100%; median trained latent contraction proxy 0.9880073."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 bench_experiment.py",
  "files": [
    "bench_experiment.py",
    "bench_report.json"
  ],
  "limitations": "The built-in dynamics task uses independent pendulum windows rather than long online streams, so retrieval is a nearest final-hidden-state context fallback rather than a learned delay-window memory. The contraction estimate is a hidden-state norm-ratio proxy, not exact Jacobian-vector power iteration. FLOP and wall-clock speed were not measured. The final comparison used the baseline-selected learning rate; the report records the shared three-value learning-rate union.",
  "bench_report": {
    "bench_version": 1,
    "track": "dynamics",
    "model": "rnn_small",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.01
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001
          },
          "mean": 0.0214155072
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.0037718631
        },
        {
          "cfg": {
            "lr": 0.01
          },
          "mean": 0.0034299326
        }
      ],
      "full": {
        "mean": 0.0027758953,
        "std": 0.0017084856,
        "per_seed": [
          0.0014615225,
          0.0043342379,
          0.0012712624,
          0.0066527077,
          0.0020110509,
          0.0024756771,
          0.0018914248,
          0.0021092789
        ],
        "n": 8
      }
    },
    "idea": {
      "best_config": {
        "lr": 0.01
      },
      "mean": 0.0075367271,
      "std": 0.0020598695,
      "per_seed": [
        0.0065831174,
        0.0093688313,
        0.0070723458,
        0.0122070778,
        0.0064491755,
        0.0063437205,
        0.0068810042,
        0.0053885444
      ],
      "n": 8,
      "idea_grid": [
        {
          "lr": 0.001
        },
        {
          "lr": 0.003
        },
        {
          "lr": 0.01
        }
      ]
    },
    "comparison": {
      "delta_mean": 0.0047608318,
      "idea_wins": 0,
      "n_pairs": 8,
      "p_value": 0.0081,
      "verdict": "idea worse (significant)",
      "system_worked": false
    },
    "mechanism_signature": {
      "observed_median_r": 0.9880073,
      "observed_mean_switch_rate": 1.0,
      "confirmed": true
    }
  },
  "system_verdict": "partial",
  "practical_verdict": "harms",
  "mechanism_ok": 1,
  "system_judged": true
}