Эксперимент: Conditioned Irregular-Delay State Encoder (#798)

{ "worked": true, "confidence": 9, "verdict": "Implemented exact continuous-time delay observability and timestamp-conditioned least-squares reconstruction in run_experiment.py. The mechanism manifested: noise scaling had observed log-log slope 0.9992 versus predicted 1.0, reconstruction error correlated with the predicted inverse-Gram noise factor at Spearman rho=0.943, the pseudoinverse bound held, and optimized delay placement increased sigma_min by 43.4%. In the Poisson-irregular toy comparison, using actual timestamps reduced latent reconstruction error by 94.1–97.3% versus a fixed uniform-delay decoder, though this comparison gives the proposed method the correct timestamps and is not a learned neural-model win.", "metrics": { "baseline": "Fixed nominal uniform-delay least-squares decoder; mean latent error for mean timestamp gaps [0.08, 0.15, 0.30, 0.50] was [1.0613, 0.7987, 0.6477, 0.9155].", "idea": "Timestamp-conditioned least-squares decoder; corresponding errors were [0.0630, 0.0359, 0.0289, 0.0244], relative improvements [94.1%, 95.5%, 95.5%, 97.3%]. Core checks: noise slope 0.9992, Spearman rho 0.9429, maximum normalized bound ratio 0.9927, delay-design sigma_min improvement 1.434x." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "run_experiment.py", "results.json", "experiment_output.txt" ], "limitations": "Only a 2D linear damped oscillator was tested. No GRU, MLP, Lorenz-63, learned delays, nonlinear Jacobian regularization, prediction loss, rollout stability, runtime/FLOP, or missing-data neural training experiment was evaluated; the baseline comparison is an oracle-style linear timestamp mismatch test." }