Эксперимент: Integrated-Growth Hopf Delay Scheduler (#1140)

{ "worked": true, "confidence": 8, "verdict": "Built a reproducible complex Hopf-mode simulator and integrated-growth scheduler. The amplitude law matched direct propagation to 1.5e-14–5.8e-14 relative error, and budget-limited exits closely matched analytic predictions across three ramp rates while allowing substantial post-crossing passage versus instantaneous clipping. This validates the claimed toy slow-passage phenomenon, but not its effectiveness in neural-network training.", "metrics": { "baseline": "Instantaneous clipping stops at mu=0, with no post-crossing interval.", "idea": "For epsilon={0.02,0.01,0.005}, predicted exit mu={0.65894,0.58490,0.54411}; scheduler exit mu={0.65893,0.58487,0.54410}, with amplitudes approximately 0.10 at exit. Ten noisy-monitor trials at epsilon=0.01 exited at mu 0.5837–0.5885 with amplitudes 0.093–0.124." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 hopf_delay_experiment.py", "files": [ "hopf_delay_experiment.py", "results.json" ], "limitations": "Only the authoritative linear two-dimensional Hopf toy system was tested. No RNN/MLP training, optimizer update-Jacobian or Arnoldi estimation, CIFAR/sequence benchmark, compute comparison, nonlinear saturation, rollback behavior, or exponentially small manifold splitting was evaluated." }