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

(универсальный)

Ответ агента:

{
  "worked": true,
  "confidence": 8,
  "verdict": "The sequence track is structurally matched to the attention intervention. The gated local-global transformer achieved lower test MSE than the tuned dense transformer (0.372641 vs 0.403156), with 7/8 paired wins and permutation p=0.01475, satisfying the harness criterion for a significant win. The trained-model gate signature confirmed use of both local and global paths.",
  "metrics": {
    "baseline": "Dense transformer_tiny, tuned lr=0.001, 8-seed mean MSE 0.403156, std 0.052733",
    "idea": "Gated local-global transformer, lr=0.001, 8-seed mean MSE 0.372641, std 0.068380",
    "delta_mean": -0.030515525490045547,
    "p_value": 0.01475
  },
  "bench_report": {
    "bench_version": 1,
    "track": "sequence",
    "model": "transformer_tiny",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.001
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001
          },
          "mean": 0.37249068170785904
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.4498218819499016
        },
        {
          "cfg": {
            "lr": 0.01
          },
          "mean": 1.0784044712781906
        }
      ],
      "full": {
        "mean": 0.4031560346484184,
        "std": 0.052733373521801685,
        "per_seed": [
          0.3982558250427246,
          0.32343214750289917,
          0.3480452001094818,
          0.42022955417633057,
          0.4928964078426361,
          0.4031330645084381,
          0.4640232026576996,
          0.37523287534713745
        ],
        "n": 8
      }
    },
    "idea": {
      "cfg": {
        "lr": 0.001
      },
      "mean": 0.3726405091583729,
      "std": 0.06837978903352387,
      "per_seed": [
        0.3478388786315918,
        0.28696209192276,
        0.32253625988960266,
        0.41124576330184937,
        0.4993930757045746,
        0.3521648645401001,
        0.44697806239128113,
        0.3140050768852234
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": -0.030515525490045547,
      "idea_wins": 7,
      "n_pairs": 8,
      "per_seed_diffs": [
        -0.05041694641113281,
        -0.03647005558013916,
        -0.02550894021987915,
        -0.008983790874481201,
        0.0064966678619384766,
        -0.05096819996833801,
        -0.017045140266418457,
        -0.06122779846191406
      ],
      "p_value": 0.01475,
      "mde": 0.019566492866314403,
      "mde_rel_pct": 4.853330022302114,
      "verdict": "idea better (significant)",
      "system_worked": true
    },
    "mechanism_signature": {
      "prediction": "gated local-global graph attention uses bounded temporal neighbors plus all-token linear statistics",
      "observed_mean_gate": 0.5655390620231628,
      "observed_local_fraction": 0.4309374988079071,
      "predicted_local_edge_degree": 3,
      "predicted_global_path": true,
      "confirmed": true
    },
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.3726405091583729,
        "std": 0.06837978903352387
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.4466487616300583,
        "std": 0.09400408679279276
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 1.0904799774289131,
        "std": 0.2792352404713769
      }
    ],
    "track_justification": "Sequence forecasting is structurally matched because the intervention replaces multi-token self-attention."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 stage2_bench.py",
  "files": [
    "stage2_bench.py",
    "bench_report.json"
  ],
  "limitations": "Only the registered built-in sequence forecasting track was tested. Wall-clock latency, peak memory, general graph topologies, and larger datasets were not evaluated; the local branch used a fixed three-neighbor temporal pattern.",
  "system_verdict": "worked",
  "practical_verdict": "helps",
  "mechanism_ok": 1,
  "system_judged": true
}