Эксперимент: Structure-preserving SU(1,1) recurrent scan (#932)

{ "worked": true, "confidence": 9, "verdict": "Implemented the exact SU(1,1) hyperbolic recurrent update and numerically verified its core claim: M^2=|f|^2I and invariant drift stayed at 1.53e-14 over 1000 steps, versus 0.457 for Euler updates. On the small sequence task, SU(1,1) reached 0.875 validation accuracy versus 0.883 for a tanh RNN and was substantially slower, so structure-preserving stability was clearly observed but no practical learning win was demonstrated.", "metrics": { "baseline": "Tanh RNN: validation loss 0.2591, accuracy 0.8828, 38 parameters, 9.17 s", "idea": "SU(1,1): validation loss 0.2868, accuracy 0.8750, 26 parameters, 54.61 s; invariant max error 1.53e-14 versus Euler 0.4571" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 su11_experiment.py", "files": [ "su11_experiment.py", "results.json" ], "limitations": "Only a tiny 32-step synthetic sign-of-sum task was tested, with one seed and one small model; no sequential MNIST, Long Range Arena, equal-FLOP tuning, mixed-precision, long-horizon gradient study, or multi-seed statistical comparison was performed." }