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

(универсальный)

Ответ агента:

{
  "worked": true,
  "confidence": 8,
  "verdict": "Built a structurally matched custom rooted-tree classification track and paired MLP systems using the canonical benchmark training loop. The M=8 branch-length polynomial fingerprint achieved mean test error 0.0000 versus 0.47625 for the tuned baseline; all 8 paired differences favored the idea and the permutation p-value was 0.0081. The trained-model signature confirmed the predicted mechanism, with output-distance ratio 4.9185.",
  "metrics": {
    "baseline": "Best lr=0.003; 8-seed mean test error 0.47625, std 0.04292.",
    "idea": "Best lr=0.010; 8-seed mean test error 0.00000, std 0.00000; paired delta=-0.47625, p=0.0081, 8/8 wins."
  },
  "bench_report": {
    "bench_version": 1,
    "track": "rooted_tree_branch_classification",
    "model": "mlp_tiny",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.003
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001
          },
          "mean": 0.5112499818205833
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.4912499859929085
        },
        {
          "cfg": {
            "lr": 0.01
          },
          "mean": 0.4912499859929085
        }
      ],
      "full": {
        "mean": 0.47624998912215233,
        "std": 0.04292071696077957,
        "per_seed": [
          0.4599999785423279,
          0.5450000166893005,
          0.5299999713897705,
          0.429999977350235,
          0.429999977350235,
          0.4399999976158142,
          0.4650000035762787,
          0.5099999904632568
        ],
        "n": 8
      }
    },
    "idea": {
      "mean": 0.0,
      "std": 0.0,
      "per_seed": [
        0.0,
        0.0,
        0.0,
        0.0,
        0.0,
        0.0,
        0.0,
        0.0
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": -0.47624998912215233,
      "idea_wins": 8,
      "n_pairs": 8,
      "per_seed_diffs": [
        -0.4599999785423279,
        -0.5450000166893005,
        -0.5299999713897705,
        -0.429999977350235,
        -0.429999977350235,
        -0.4399999976158142,
        -0.4650000035762787,
        -0.5099999904632568
      ],
      "p_value": 0.0081,
      "mde": 0.038366227085568125,
      "mde_rel_pct": 8.05590088438357,
      "verdict": "idea better (significant)",
      "system_worked": true
    },
    "custom_track": {
      "name": "rooted_tree_branch_classification",
      "file": "tree_polynomial_track.py",
      "domain": "graph-nn"
    },
    "idea_config": {
      "lr": 0.01
    },
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "result": {
          "mean": 0.026249999413266778,
          "std": 0.022185299058062068,
          "per_seed": [
            0.004999999888241291,
            0.044999998062849045,
            0.02499999850988388,
            0.07000000029802322,
            0.014999999664723873,
            0.004999999888241291,
            0.004999999888241291,
            0.03999999910593033
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "result": {
          "mean": 0.006874999846331775,
          "std": 0.006584783448351579,
          "per_seed": [
            0.0,
            0.004999999888241291,
            0.014999999664723873,
            0.014999999664723873,
            0.0,
            0.004999999888241291,
            0.0,
            0.014999999664723873
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "result": {
          "mean": 0.0,
          "std": 0.0,
          "per_seed": [
            0.0,
            0.0,
            0.0,
            0.0,
            0.0,
            0.0,
            0.0,
            0.0
          ],
          "n": 8
        }
      }
    ],
    "mechanism_signature": {
      "prediction": "trained fingerprint outputs separate topology pair more than sum baseline",
      "observed_baseline_output_distance": 0.0020921695977449417,
      "observed_idea_output_distance": 0.010290324687957764,
      "predicted_ratio_lower_bound": 1.0,
      "observed_ratio": 4.918494513565848,
      "confirmed": true
    }
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 stage2_bench.py",
  "files": [
    "tree_polynomial_track.py",
    "stage2_bench.py",
    "bench_report.json"
  ],
  "limitations": "The custom fixed-size six-node synthetic track is not a real phylogenetic dataset; no variable-size trees, TreeLSTM/GNN architecture, complex evaluations, calibration under edge noise, or larger-scale overflow study was tested.",
  "system_verdict": "worked",
  "practical_verdict": "helps",
  "mechanism_ok": 1,
  "system_judged": true
}