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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 9,
  "verdict": "Implemented and registered the planar Ising autoregressive track with a shared mlp_tiny system; only the training target changed from sampled next-spin labels to exact soft conditional probabilities. Test MSE improved from 0.117852 to 0.115734, but the paired permutation test gave p=0.23005, so this is no significant win. The NN-scale mechanism prediction was confirmed on seed 0 because conditional-probability MSE decreased from 0.0357703 to 0.0323526.",
  "metrics": {
    "baseline": "Test MSE mean 0.1178522473, std 0.0178481495; best lr=0.01, epochs=5, batch=128.",
    "idea": "Test MSE mean 0.1157343183, std 0.0174895135; best lr=0.01, epochs=5, batch=128; paired delta=-0.0021179290, p=0.23005; 5/8 wins."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 stage2_bench.py",
  "files": [
    "ising_teacher_track.py",
    "stage2_bench.py",
    "bench_report.json"
  ],
  "limitations": "The exact oracle uses cached brute-force enumeration on a fixed 4x4 ferromagnetic lattice rather than the full auxiliary-graph Kac-Ward conditional construction. Observables, long-run sample autocorrelation, larger lattices, replay-based active correction, and runtime scaling were not tested.",
  "bench_report": {
    "bench_version": 1,
    "track": "planar_ising_autoregressive",
    "model": "mlp_tiny",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.01,
        "epochs": 5,
        "batch": 128
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001,
            "epochs": 5,
            "batch": 128
          },
          "mean": 0.1614346206
        },
        {
          "cfg": {
            "lr": 0.003,
            "epochs": 5,
            "batch": 128
          },
          "mean": 0.1300708577
        },
        {
          "cfg": {
            "lr": 0.01,
            "epochs": 5,
            "batch": 128
          },
          "mean": 0.1225814894
        }
      ],
      "full": {
        "mean": 0.1178522473,
        "std": 0.0178481495,
        "per_seed": [
          0.150730595,
          0.1360894144,
          0.113548927,
          0.0899570212,
          0.1152136326,
          0.1048248708,
          0.1250655949,
          0.1073879227
        ],
        "n": 8
      }
    },
    "idea": {
      "best_cfg": {
        "lr": 0.01,
        "epochs": 5,
        "batch": 128
      },
      "mean": 0.1157343183,
      "std": 0.0174895135,
      "per_seed": [
        0.147062093,
        0.1326635182,
        0.1145763695,
        0.0900150463,
        0.1083332077,
        0.0962902904,
        0.1243165284,
        0.1126174927
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": -0.002117929,
      "idea_wins": 5,
      "n_pairs": 8,
      "per_seed_diffs": [
        -0.003668502,
        -0.0034258962,
        0.0010274425,
        5.80251e-05,
        -0.0068804249,
        -0.0085345805,
        -0.0007490665,
        0.00522957
      ],
      "p_value": 0.23005,
      "mde": 0.0037187363,
      "mde_rel_pct": 3.1554,
      "verdict": "no significant win",
      "system_worked": false
    },
    "mechanism_signature": {
      "prediction": "Exact soft conditional labels reduce trained-NN conditional probability MSE versus sampled labels.",
      "baseline_seed0": {
        "metric": 0.150730595,
        "q_mse": 0.0357702747,
        "pred_mean": 0.462284386
      },
      "idea_seed0": {
        "metric": 0.147062093,
        "q_mse": 0.0323526226,
        "pred_mean": 0.457736522
      },
      "q_mse_reduction": 0.0034176521,
      "confirmed": true
    },
    "custom_track": {
      "name": "planar_ising_autoregressive",
      "file": "ising_teacher_track.py",
      "domain": "sequence-level sampling"
    }
  },
  "system_verdict": "partial",
  "practical_verdict": "inconclusive",
  "mechanism_ok": 1,
  "system_judged": true
}