Эксперимент: Positive-Regime Observable ReLU State Space (#1115)

{ "worked": true, "confidence": 9, "verdict": "The positive-regime ReLU mechanism was numerically confirmed. ReLU exactly matched affine dynamics with zero negative preactivations, full observability appeared at the predicted horizon T=5, and reconstruction error scaled inversely with sigma_min using an observed log-log slope of -0.993. The positive model had perturbation error 8.5e-11 versus 1.025 for signed ReLU, but no end-to-end task win was tested.", "metrics": { "baseline": "Signed ReLU: negative-preactivation fraction 0.490; linearization error 1.025; rank 8; sigma_min(Q) 0.0603.", "idea": "Positive-regime ReLU: negative-preactivation fraction 0; positivity penalty 0; linearization error 8.5e-11; rank 8; sigma_min(Q) 0.0276. Rank transition matched prediction at T=5, and inverse-singular-value scaling matched with slope -0.993." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json", "run_output.txt" ], "limitations": "No learned copy-memory or adding task, decoder training, conditioning-loss optimization, spectral normalization, or end-to-end accuracy comparison was tested; experiments used controlled toy systems." }