Prony Memory Bank for Linear-Time Sequence Modeling / report_bench_2026-09-02T220928.md
Failed on benchmark
Стенд-проверка (stage-2) · промт оператора:
(универсальный)
Ответ агента:
{ "worked": false, "confidence": 10, "verdict": "The Prony Memory Bank was evaluated on the registered sequence track with matched transformer_tiny structure, tuned baseline sweep, shared learning-rate search space, and 8 paired seeds. Baseline MSE was 0.1347019309 versus 0.2076336704 for the idea; delta_mean=+0.0729317395 and permutation p=0.0081, so the idea was significantly worse. Learned decay rates stayed below one, but the trained-model state-ratio signature was not confirmed.", "metrics": { "baseline": "best lr=0.001; mean MSE=0.13470193091779947", "idea": "K=8, lr=0.001; mean MSE=0.20763367041945457; delta=0.0729317395016551; p=0.0081" }, "how_to_run": "PYTHONPATH=/home/maxwelhelp/all/math2nn /home/maxwelhelp/main/bin/python3 bench_prony.py", "files": [ "bench_prony.py", "bench_report.json" ], "limitations": "Only the registered sequence track was tested; throughput, peak memory, long-context scaling, and direct autocorrelation calibration were not tested.", "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": 0.13728361204266548 }, { "cfg": { "lr": 0.003 }, "mean": 0.15594297274947166 }, { "cfg": { "lr": 0.006 }, "mean": 0.18980268761515617 } ], "full": { "mean": 0.13470193091779947, "std": 0.008479124196230155, "per_seed": [ 0.14094272255897522, 0.13710848987102509, 0.1384955197572708, 0.1325877159833908, 0.12374862283468246, 0.1362551748752594, 0.14818039536476135, 0.12029680609703064 ], "n": 8 } }, "idea": { "mean": 0.20763367041945457, "std": 0.01477123328265889, "per_seed": [ 0.23813630640506744, 0.19545486569404602, 0.20464827120304108, 0.21287421882152557, 0.1995057314634323, 0.1872827261686325, 0.21929647028446198, 0.2038707733154297 ], "n": 8, "chosen_cfg": { "lr": 0.001, "K": 8 }, "sweep": [ { "cfg": { "lr": 0.001, "K": 8 }, "mean": 0.20763367041945457 }, { "cfg": { "lr": 0.001, "K": 8 }, "mean": 0.20763367041945457 }, { "cfg": { "lr": 0.006, "K": 8 }, "mean": 0.26278449408710003 } ] }, "comparison": { "delta_mean": 0.0729317395016551, "idea_wins": 0, "n_pairs": 8, "p_value": 0.0081, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "prediction": "positive Prony decays enforce contraction", "predicted": { "max_rho": 0.9787325263023376, "stable": true, "K": 8 }, "observed": { "max_observed_ratio": 2.673238563537596, "mean_observed_ratio": 2.366884194314479 }, "confirmed": false }, "custom_track": null }, "system_verdict": "failed", "practical_verdict": "harms", "mechanism_ok": 0, "system_judged": true }