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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 9,
  "verdict": "The registered built-in dynamics track was run with 8 paired seeds, a tuned baseline sweep, and a parity-matched idea sweep. The monotone system had lower mean MSE, but the paired permutation test was not significant (p=0.56675; 4/8 wins), so this is not a benchmark win. The trained-model mechanism signature was confirmed: the idea had 100% nonnegative observed aggregator derivatives, while the unconstrained baseline had 0%.",
  "metrics": {
    "baseline": "dynamics/rnn_small unconstrained aggregator; best lr=0.006, epochs=10; full mean test MSE=0.005481509841047227.",
    "idea": "dynamics/rnn_small positive-weight monotone aggregator; best lr=0.003, epochs=10; full mean test MSE=0.0049165511154569685; paired delta=-0.0005649587255902588; p=0.56675; 4/8 wins."
  },
  "bench_report": {
    "bench_version": 1,
    "track": "dynamics",
    "model": "rnn_small",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.006,
        "epochs": 10
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001,
            "epochs": 10
          },
          "mean": 0.018210270907729864
        },
        {
          "cfg": {
            "lr": 0.003,
            "epochs": 10
          },
          "mean": 0.009255725424736738
        },
        {
          "cfg": {
            "lr": 0.006,
            "epochs": 10
          },
          "mean": 0.004965097992680967
        }
      ],
      "full": {
        "mean": 0.005481509841047227,
        "std": 0.0017443505414011541,
        "per_seed": [
          0.0044007012620568275,
          0.006472812034189701,
          0.004313930869102478,
          0.004672947805374861,
          0.003332370426505804,
          0.008815406821668148,
          0.007345432415604591,
          0.004498477093875408
        ],
        "n": 8
      }
    },
    "idea": {
      "mean": 0.0049165511154569685,
      "std": 0.0019956794930531424,
      "per_seed": [
        0.005324999801814556,
        0.0023787340614944696,
        0.002438431140035391,
        0.00647375825792551,
        0.0034786139149218798,
        0.0063143507577478886,
        0.0044753411784768105,
        0.008448179811239243
      ],
      "n": 8,
      "sweep": [
        {
          "cfg": {
            "lr": 0.001,
            "epochs": 10
          },
          "mean": 0.03285314375534654
        },
        {
          "cfg": {
            "lr": 0.003,
            "epochs": 10
          },
          "mean": 0.0049165511154569685
        },
        {
          "cfg": {
            "lr": 0.006,
            "epochs": 10
          },
          "mean": 0.0050386641814839095
        }
      ]
    },
    "comparison": {
      "delta_mean": -0.0005649587255902588,
      "idea_wins": 4,
      "n_pairs": 8,
      "per_seed_diffs": [
        0.0009242985397577286,
        -0.0040940779726952314,
        -0.0018754997290670872,
        0.0018008104525506496,
        0.0001462434884160757,
        -0.0025010560639202595,
        -0.002870091237127781,
        0.003949702717363834
      ],
      "p_value": 0.56675,
      "mde": 0.0022775908803314825,
      "mde_rel_pct": 41.55042946883326,
      "verdict": "no significant win",
      "system_worked": false
    },
    "mechanism_signature": {
      "prediction": "monotone aggregator has nonnegative derivatives; increasing a primitive cannot lower composite value",
      "baseline_observed": {
        "samples": 128,
        "derivative_nonnegative_fraction": 0.0,
        "mean_derivatives": [
          -0.4277612566947937,
          -0.4763301610946655
        ],
        "positive_primitive_perturbation_mean_response": -0.04277614504098892
      },
      "idea_observed": {
        "samples": 128,
        "derivative_nonnegative_fraction": 1.0,
        "mean_derivatives": [
          0.5155500173568726,
          0.5073314309120178
        ],
        "positive_primitive_perturbation_mean_response": 0.051555000245571136
      },
      "confirmed": true,
      "measurement_note": "All quantities were computed from trained benchmark models on held-out dynamics inputs."
    },
    "custom_track": null
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 bench_experiment.py",
  "files": [
    "bench_experiment.py",
    "bench_report.json"
  ],
  "limitations": "Only the built-in actuated-pendulum rollout regression track was tested; no PDE/HJ grid solver, adversarial disturbance rollout, target-set IoU, nonlinear monotone lattice, or larger-scale/high-dimensional reachability experiment was run. The benchmark used 400 training examples, 200 test examples, 10 epochs, and a small GRU.",
  "system_verdict": "partial",
  "practical_verdict": "inconclusive",
  "mechanism_ok": 1,
  "system_judged": true
}