Эксперимент: Passivity-Regularized Sequence Layer (#1399)

{ "worked": true, "confidence": 8, "verdict": "Built a passivity regularizer for a GRU, including per-step, cumulative, and optional incremental trajectory penalties, plus a direct telescoping-identity check. The identity held numerically with maximum error 2.6e-6, and regularization reduced hidden-state energy violations and perturbation amplification. However, long-context accuracy worsened from 0.846 for the baseline to 0.666 with regularization, so the stability effect is real but did not improve task generalization in this small test.", "metrics": { "baseline": "T32 accuracy 0.953; T160 accuracy 0.846; T160 amplification 0.697; T160 mean cumulative residual 7438.3; max positive residual 106.8", "idea": "T32 accuracy 0.939; T160 accuracy 0.666; T160 amplification 0.207 without incremental pairing and 0.106 with pairing; T160 mean cumulative residual 1681.3/1677.6; max positive residual about 21.0" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 passivity_experiment.py", "files": [ "passivity_experiment.py", "results.json" ], "limitations": "Only a small GRU and synthetic sign-sum task were tested with one seed and one regularization weight. No spectral-normalization baseline, LSTM/SSM, FLOP accounting, gradient-variance measurement, or repeated-seed significance analysis was performed; CUDA failed due to shared cuDNN allocation and the run fell back to CPU." }