Эксперимент: Safe Receding-Horizon Neural Topology Switching (#866)

{ "worked": true, "confidence": 8, "verdict": "Built a deterministic safe receding-horizon topology-switching MVP with exact calibration certification, interpolation planning, rejection tracking, and cut-reuse accounting. The quadratic residual identity matched numerically to 1.11e-16, the predicted minimum safe interpolation decreased monotonically as tolerance increased, and grid observations were within 0.009 of the analytic boundary. The filtered controller accepted zero violating steps, while one-shot switching had an unsafe intermediate and unfiltered gradual switching had 6/11 violations; cut reuse reduced repeated rejected evaluations from 30 to 6 in the toy replanning setup.", "metrics": { "baseline": "One-shot: endpoint MSE 0.03968 but 1 unsafe intermediate; unfiltered 11-point interpolation: 6/11 constraint violations.", "idea": "Filtered first accepted alpha 0.60 at epsilon=0.25 with 0 accepted-step violations; cut reuse: 6 versus 30 rejected evaluations over 5 replans. Analytic-versus-grid alpha error across feasible sweeps was <=0.00845." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 safe_switch.py", "files": [ "safe_switch.py", "results.json" ], "limitations": "This is a synthetic two-feature regression toy, not a ResNet, MoE, or hardware deployment. It tests loss feasibility and abstract cut reuse only; activation, spectral norm, latency, memory, learned planner quality, multi-step parameter training, and real topology speedups were not tested." }