Boundary-Radial Persistence Loss / report_bench_2026-09-01T130239.md

Mechanism confirmed, baseline not beaten

Raw ⬇ ZIP

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

(универсальный)

Ответ агента:

{ "worked": false, "confidence": 9, "verdict": "Built a structurally matched custom radial-boundary regression track with identical MLP systems for baseline MSE and the radial matching intervention. Across 8 paired seeds, the best baseline mean test MSE was 0.018877, while positive radial-loss weights worsened performance; the best idea setting was alpha=0 and therefore identical to baseline. The trained-model mechanism signature was confirmed by a positive MAE/radial-loss correlation of 0.878, but there was no significant task-metric win.", "metrics": { "baseline": "lr=0.01, alpha=0.0; mean test MSE 0.0188770521", "idea": "Best lr=0.01, alpha=0.0; mean test MSE 0.0188770521. alpha=0.05 mean 0.0210358966; alpha=0.2 mean 0.0285936717. Paired delta 0.0, permutation p=1.0." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 bench_radial.py", "files": [ "bench_radial.py", "bench_report.json" ], "limitations": "This is a compact radial-boundary regression proxy rather than full raster segmentation. Full extended persistence, relative/essential classes, H1, differentiable contour extraction, volumetric memory, and CNN segmentation were not tested. The training intervention uses a differentiable sorted-radius surrogate rather than exact discrete Hungarian matching.", "bench_report": { "bench_version": 1, "track": "radial_boundary_shapes", "model": "local_mlp_shared", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_config": { "lr": 0.01, "alpha": 0.0 }, "sweep_means": { "lr_0.001": 0.0439985367, "lr_0.003": 0.0246021044, "lr_0.01": 0.0188770521 } }, "idea": { "best_config": { "lr": 0.01, "alpha": 0.0 }, "sweep_means": { "alpha_0.0": 0.0188770521, "alpha_0.05": 0.0210358966, "alpha_0.2": 0.0285936717 } }, "comparison": { "delta_mean": 0.0, "p_value": 1.0, "verdict": "no measurable effect", "system_worked": false }, "mechanism_signature": { "observed_pearson_mae_vs_radial_loss": 0.8776371462, "confirmed": true }, "custom_track": { "name": "radial_boundary_shapes", "file": "bench_radial.py", "domain": "segmentation_geometry" } }, "system_verdict": "partial", "practical_verdict": "no_effect", "mechanism_ok": 1, "system_judged": true }