Эксперимент: Phase-Delay Spectral Margin for Attractor RNNs (#1211)

{ "worked": true, "confidence": 8, "verdict": "Built a phase-delay RNN with trainable nonnegative edge magnitudes, bounded phase delays, differentiable composite-Laplacian spectral regularization, and Euler stability diagnostics. The toy check reproduced the predicted boundary: amplification was 0.60 at 0.8ηc, 1.00 at ηc, and 1.40 at 1.2ηc. In the matched mini-run, the idea improved the minimum real spectral margin from 0.341 to 3.295, reduced maximum Euler amplification from 0.959 to 0.606, and reduced 12-step perturbation gain from 0.334 to 0.120, but task MSE worsened from 0.000172 to 0.00561; thus the stability effect is real, but task-performance benefit was not demonstrated.", "metrics": { "baseline": "task_mse=0.000172; min_real_eigenvalue=0.341; max_euler_amplification=0.959; 12_step_perturbation_gain=0.334", "idea": "task_mse=0.00561; min_real_eigenvalue=3.295; max_euler_amplification=0.606; 12_step_perturbation_gain=0.120" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only one small synthetic sequence task and one fixed random seed were tested; no adding-machine benchmark, multi-seed statistics, FLOP/speed comparison, long-horizon generalization, or larger attractor-RNN evaluation was performed. The perturbation test uses a short 12-step zero-input rollout, and the spectral penalty uses a dense eigensolver." }