Эксперимент: Komuro Time-Warp Expansivity Regularizer (#627)

{ "worked": true, "confidence": 8, "verdict": "Built a deterministic MVP of Komuro-style time-warp discrepancy with an affine monotone warp search and hinge expansivity statistics. All three required mechanism predictions manifested: inverse-speed warp recovery had maximum error 2.41e-4, optimized discrepancy equaled the radial-gap lower bound across the sweep, and hinge activation matched the empirical q=0.1 quantile transition. The controlled comparison reduced clock-perturbed pair discrepancy by 99.90% (0.3126 to 0.000303), but this is a mathematical toy signal rather than evidence of a trained neural ODE win.", "metrics": { "baseline": "Ordinary alpha=1 max discrepancy on clock-perturbed pairs: mean 0.312585", "idea": "Warp-optimized max discrepancy: mean 0.000303; relative reduction 0.99903. Max inverse-speed alpha error 0.0002407; radius-gap D monotone and D=|dr|; q=0.1 delta_emp=0.357631 with observed activation 0.10." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 komuro_mvp.py", "files": [ "komuro_mvp.py", "results.json", "README.txt" ], "limitations": "No learned neural ODE training, reconstruction or prediction task, irregular sampling, nonlinear warp optimization, arbitrary surjective homeomorphisms, FLOP/runtime comparison, or downstream generalization test was performed. The circular analytic flow makes the predictions unusually clean and does not establish benefit in realistic latent dynamics." }