Эксперимент: Noisy Scrambling-Front Network (#536)

{ "worked": true, "confidence": 8, "verdict": "Built a discrete Euler–Maruyama Fisher–KPP simulator and a six-layer gated residual MLP. Measured front speeds were within 5.6%, 4.9%, and 9.9% of 2√(Dr), while zero-state log-growth rates matched r within 0.027. Increasing kappa broadened the front from width 33.0 to 133.7 and 139.4; the gated MLP did not produce a meaningful task-loss improvement over baseline.", "metrics": { "baseline": "Parity toy task: final loss 0.690793, 7298 parameters.", "idea": "Parity toy task: final loss 0.690761, 7299 parameters; front-speed relative errors 5.6%-9.9%; stability slope errors <=0.027; noise width 33.0 at kappa=0, 133.7 at kappa=0.15, and 139.4 at kappa=0.5." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only a tiny synthetic parity task was tested, with one fixed seed and a deterministic input-derived gate. The stochastic PDE uses explicit Euler–Maruyama, clipping, finite reflecting boundaries, and a coarse grid; noise broadening may depend on discretization and clipping. Copy and induction tasks, equal-FLOP profiling, learned saliency initialization, and larger sequence models were not tested." }