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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 9,
  "verdict": "The Stage-2 bench was run on the structurally matched registered dynamics track using rnn_small, with a tuned three-point baseline sweep and the same learning-rate union for the delayed-gradient idea. The baseline mean test MSE was 0.0002364132 versus 0.0002731473 for the idea; paired delta was +0.0000367342 and permutation p=0.5022, so the idea did not win. The trained-model signature was not confirmed because the observed displacement ratio was 1.00.",
  "metrics": {
    "baseline": "best_cfg={lr:0.01}; 8-seed mean MSE=0.0002364131533; per_seed=[0.0002348576672,0.0002715944720,0.0001552376052,0.0002151069202,0.0001569727028,0.0002712704008,0.0001109737714,0.0004752916866]",
    "idea": "best_cfg={lr:0.01}; 8-seed mean MSE=0.0002731473405; per_seed=[0.0002348576672,0.0002715944720,0.0001552376052,0.0004188152379,0.0002471378830,0.0002712704008,0.0001109737714,0.0004752916866]; paired delta=+0.0000367341872; p=0.5022"
  },
  "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": 0.001222553226398304
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.000683717749780044
        },
        {
          "cfg": {
            "lr": 0.01
          },
          "mean": 0.00021919916616752744
        }
      ],
      "full": {
        "mean": 0.0002364131532885949,
        "std": 0.00010524220575938558,
        "per_seed": [
          0.00023485766723752022,
          0.0002715944719966501,
          0.00015523760521318763,
          0.0002151069202227518,
          0.00015697270282544196,
          0.00027127040084451437,
          0.0001109737713704817,
          0.0004752916865982115
        ],
        "n": 8
      },
      "idea_grid": [
        {
          "cfg": {
            "lr": 0.001
          },
          "mean": 0.035339713853318244
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.008510864296113141
        },
        {
          "cfg": {
            "lr": 0.01
          },
          "mean": 0.0002731473405219731
        }
      ]
    },
    "idea": {
      "mean": 0.0002731473405219731,
      "std": 0.00011425463363936107,
      "per_seed": [
        0.00023485766723752022,
        0.0002715944719966501,
        0.00015523760521318763,
        0.00041881523793563247,
        0.0002471378829795867,
        0.00027127040084451437,
        0.0001109737713704817,
        0.0004752916865982115
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": 3.673418723337818e-05,
      "idea_wins": 0,
      "n_pairs": 8,
      "per_seed_diffs": [
        0.0,
        0.0,
        0.0,
        0.00020370831771288067,
        9.016518015414476e-05,
        0.0,
        0.0,
        0.0
      ],
      "p_value": 0.5022,
      "mde": 6.227732731692294e-05,
      "mde_rel_pct": 26.342581389115686,
      "verdict": "no significant win",
      "system_worked": false
    },
    "mechanism_signature": {
      "prediction": "plateau-triggered delay amplifies parameter displacement",
      "predicted_delay_steps": 14.049755225604105,
      "observed_delay_steps": 12,
      "baseline_max_displacement": 6.033182621002197,
      "idea_max_displacement": 6.033182621002197,
      "displacement_ratio": 0.9999999999998342,
      "k_proxy": 0.1229826378985967,
      "confirmed": false
    }
  },
  "how_to_run": "cd /home/maxwelhelp/all/math2nn/experiments/exp2900_bifurcation-calibrated-delayed-gradient- && /home/maxwelhelp/main/bin/python3 delayed_gradient_bench.py",
  "files": [
    "delayed_gradient_bench.py",
    "bench_report.json"
  ],
  "limitations": "Only the registered dynamics track was tested. The local curvature estimate is a lightweight gradient-norm proxy rather than full Hessian-vector power iteration, and the bounded burst delay was capped at 12 steps.",
  "system_verdict": "failed",
  "practical_verdict": "inconclusive",
  "mechanism_ok": 0,
  "system_judged": true
}