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

(универсальный)

Ответ агента:

{
  "worked": false,
  "confidence": 9,
  "verdict": "Implemented the wide-tree invariant alignment mechanism as a tree-moment consistency regularizer in an end-to-end MLP on the structurally matched unordered point-set denoising track. The orthogonal-invariance sanity check passed with relative error 2.94e-7, but the full benchmark found the idea significantly worse: MSE rose from 0.03499 to 0.04198, paired delta +0.00699, permutation p=0.0163. The trained-model mechanism signature was not confirmed because mean tree-feature correlation decreased from 0.9267 to 0.9220.",
  "metrics": {
    "baseline": "Best baseline lr=0.006, weight_decay=0.0; full 8-seed test MSE 0.0349912 ± 0.0021176.",
    "idea": "Best idea config lr=0.003, weight_decay=0.0, tree_lambda=0.05; full 8-seed test MSE 0.0419774 ± 0.0049313; paired delta +0.0069862, 1/8 wins, permutation p=0.0163."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 stage2_bench.py",
  "files": [
    "stage2_bench.py",
    "bench_report.json"
  ],
  "limitations": "Only the unordered point-set denoising custom track and mlp_med architecture were tested. The implementation uses fixed low-order centered moments rather than randomized recursive bipartite contractions, and does not test Hungarian or Sinkhorn matching, larger tree families, alternative architectures, or larger datasets. A local training loop was necessary because the generic trainer assumes scalar regression targets while this track has six-dimensional targets.",
  "bench_report": {
    "bench_version": 1,
    "track": "unordered_pointset_denoising",
    "model": "mlp_med",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.006,
        "weight_decay": 0.0
      },
      "full": {
        "mean": 0.034991197753697634,
        "std": 0.002117625587373799,
        "per_seed": [
          0.036085259169340134,
          0.03398258239030838,
          0.03428776562213898,
          0.0314578041434288,
          0.034709829837083817,
          0.03937392309308052,
          0.035850487649440765,
          0.034181930124759674
        ],
        "n": 8
      }
    },
    "idea": {
      "best_cfg": {
        "lr": 0.003,
        "weight_decay": 0.0,
        "tree_lambda": 0.05
      },
      "mean": 0.0419774423353374,
      "std": 0.0049312628769484414,
      "per_seed": [
        0.039885085076093674,
        0.03695981204509735,
        0.038052886724472046,
        0.04973628371953964,
        0.04566482454538345,
        0.036613475531339645,
        0.04028519243001938,
        0.04862197861075401
      ],
      "n": 8
    },
    "comparison": {
      "delta_mean": 0.006986244581639767,
      "idea_wins": 1,
      "n_pairs": 8,
      "p_value": 0.0163,
      "verdict": "idea worse (significant)",
      "system_worked": false
    },
    "math_check": {
      "gram_tree_orthogonal_invariance_relative_error": 2.9398856327134126e-07
    },
    "mechanism_signature": {
      "observed_baseline_mean_tree_corr": 0.9266873237022839,
      "observed_idea_mean_tree_corr": 0.9220414828405017,
      "confirmed": false
    },
    "custom_track": {
      "name": "unordered_pointset_denoising",
      "file": "bench/custom_tracks/unordered_pointset_denoising.py",
      "domain": "point-set-diffusion"
    }
  },
  "system_verdict": "failed",
  "practical_verdict": "harms",
  "mechanism_ok": 0,
  "system_judged": true
}