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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 10,
  "verdict": "The official registered bench run completed on token_expert_sequence, a structurally matched multi-token MoE-routing task, using 8 paired seeds and a tuned baseline sweep. The dissipative layer was significantly worse: test error increased by 0.493125 with permutation p=0.0081, so the harness verdict is idea worse (significant). The mechanism signature was not confirmed because its trained-model diagnostics returned NaN.",
  "metrics": {
    "baseline": "mlp_tiny, lr=0.01, epochs=25: mean test err=0.0015625 over 8 seeds.",
    "idea": "Dissipative reset/cycle readout, best tested r=0.5 at lr=0.01, epochs=25: mean test err=0.4946875 over 8 seeds; paired delta=+0.493125, p=0.0081."
  },
  "bench_report": {
    "bench_version": 1,
    "track": "token_expert_sequence",
    "model": "mlp_tiny",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.01,
        "epochs": 25
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001,
            "epochs": 25
          },
          "mean": 0.0012499999720603228
        },
        {
          "cfg": {
            "lr": 0.003,
            "epochs": 25
          },
          "mean": 0.0012499999720603228
        },
        {
          "cfg": {
            "lr": 0.01,
            "epochs": 25
          },
          "mean": 0.0006249999860301614
        }
      ],
      "full": {
        "mean": 0.0015624999650754035,
        "std": 0.0017399263244939971,
        "per_seed": [
          0.0,
          0.0024999999441206455,
          0.0,
          0.0,
          0.0024999999441206455,
          0.0024999999441206455,
          0.0,
          0.004999999888241291
        ],
        "n": 8
      }
    },
    "idea": {
      "mean": 0.4946874864399433,
      "std": 0.02705426452774727,
      "per_seed": [
        0.5399999618530273,
        0.5024999976158142,
        0.48499998450279236,
        0.5049999952316284,
        0.4449999928474426,
        0.5199999809265137,
        0.47999998927116394,
        0.47999998927116394
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": 0.4931249864748679,
      "idea_wins": 0,
      "n_pairs": 8,
      "per_seed_diffs": [
        0.5399999618530273,
        0.49999999767169356,
        0.48499998450279236,
        0.5049999952316284,
        0.442499992903322,
        0.517499980982393,
        0.47999998927116394,
        0.47499998938292265
      ],
      "p_value": 0.0081,
      "mde": 0.024702187634040935,
      "mde_rel_pct": 1580.9400439153835,
      "verdict": "idea worse (significant)",
      "system_worked": false
    },
    "mechanism_signature": {
      "predicted_effect": "occupation mismatch decreases as reset_rate increases",
      "mismatch_at_r": null,
      "mismatch_at_r_0.5": null,
      "observed_cycle_proxy": null,
      "confirmed": false
    },
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 25,
          "r": 0.5
        },
        "result": {
          "mean": 0.4946874864399433,
          "std": 0.02705426452774727,
          "per_seed": [
            0.5399999618530273,
            0.5024999976158142,
            0.48499998450279236,
            0.5049999952316284,
            0.4449999928474426,
            0.5199999809265137,
            0.47999998927116394,
            0.47999998927116394
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 25,
          "r": 2.0
        },
        "result": {
          "mean": 0.4946874864399433,
          "std": 0.02705426452774727,
          "per_seed": [
            0.5399999618530273,
            0.5024999976158142,
            0.48499998450279236,
            0.5049999952316284,
            0.4449999928474426,
            0.5199999809265137,
            0.47999998927116394,
            0.47999998927116394
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 25,
          "r": 8.0
        },
        "result": {
          "mean": 0.4946874864399433,
          "std": 0.02705426452774727,
          "per_seed": [
            0.5399999618530273,
            0.5024999976158142,
            0.48499998450279236,
            0.5049999952316284,
            0.4449999928474426,
            0.5199999809265137,
            0.47999998927116394,
            0.47999998927116394
          ],
          "n": 8
        }
      }
    ],
    "custom_track": {
      "name": "token_expert_sequence",
      "file": "/home/maxwelhelp/all/math2nn/bench/custom_tracks/token_expert_sequence.py",
      "domain": "moe-routing"
    }
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 official_bench.py",
  "files": [
    "official_bench.py",
    "bench_report.json",
    "token_expert_sequence_snapshot.py"
  ],
  "limitations": "The trained-model mechanism signature produced NaN diagnostics and therefore does not support the mathematical transfer claim. The official track uses classification error, which is coarse and saturated near zero for the baseline; no additional benchmark tracks were run after the structurally matched track showed a significant loss.",
  "system_verdict": "failed",
  "practical_verdict": "harms",
  "mechanism_ok": 0,
  "system_judged": true
}