Эксперимент: Adaptive Ballistic-to-Diffusive Propagation Schedule (#509)

{ "worked": true, "confidence": 8, "verdict": "Built a finite-lattice dephasing simulator, feedback controller, and matched recurrent propagation mini-experiment. The core mechanism manifested: ballistic MSD exponent was 2.00 at gamma=0, while diffusive MSD slopes matched 4J^2/gamma within 2.7% at gamma=0.5 and below 0.1% for gamma>=1; correlation and high-frequency energy also decreased with dephasing. The crossover was broad rather than a sharp switch near 4J, and adaptive control did not beat fixed ballistic propagation on the small classification task, so this is mechanism confirmation rather than an observed neural-performance win.", "metrics": { "baseline": "Fixed ballistic: loss 0.09199984, accuracy 0.97265625. Fixed diffusive: loss 0.09874058, accuracy 0.96875.", "idea": "Adaptive feedback: loss 0.09449144, accuracy 0.970703125; gamma changed from 0.5 to final 1.65498. Toy MSD slopes for gamma=[0.5,1,2,4,8,16] were [7.7801,3.9960,2.0000,1.0000,0.5000,0.2500] versus predicted [8,4,2,1,0.5,0.25]." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 adaptive_diffusion.py && /home/maxwelhelp/main/bin/python3 mini_experiment.py", "files": [ "adaptive_diffusion.py", "mini_experiment.py", "results.json", "mini_results.json", "report.json" ], "limitations": "The neural experiment was a tiny synthetic pulse-position task, not Sequential MNIST or a long-horizon copy task; it used one seed, a short 16-layer stack, and did not measure Jacobian singular values or effective receptive-field width. The high-frequency observable was a population FFT proxy, and the finite-time crossover estimate was not a rigorous sharp transition measurement." }