Эксперимент: Differentiable Maximal-Attractor Trap (#975)

{ "worked": true, "confidence": 8, "verdict": "Built a differentiable trapping-loss RNN experiment plus an analytic tanh-map verification. The mechanism manifested: the exact strict-invariance boundary was predicted as a=1.2474 and the first violating sweep point was a=1.25; the toy map also showed the predicted transition at a=1 and closely matched nonzero fixed-point attractor diameters. In the RNN, trap regularization reduced long-horizon violations from 99.9% mean at lambda=0 to 0% at lambda>=3, with max hidden norm falling from 2.46 to 0.76 at lambda=3, at the cost of higher MSE.", "metrics": { "baseline": "lambda=0: MSE 0.00551, one-step violation 78.7%, mean 300-step violation 99.92%, max hidden norm 2.464", "idea": "lambda=3: MSE 0.01078, one-step violation 0%, mean 300-step violation 0%, max hidden norm 0.763; lambda=10 further shrank norm to 0.007 but MSE rose to 0.01630" }, "how_to_run": "python3 experiment.py", "files": [ "experiment.py", "results.json", "run.log" ], "limitations": "The invariance certificate is empirical point sampling rather than interval-bound or exact verification for the learned RNN. The task used zero-input dynamics, a small 16-unit RNN, one fixed seed, short training, and a synthetic Mackey-Glass setup; no FLOP-normalized study, multiple-seed statistics, nonzero bounded inputs, or larger benchmarks were tested." }