Эксперимент: STL-Robust Mixture-of-Experts Gating (#368)

{ "worked": true, "confidence": 9, "verdict": "Built a NumPy MVP of STL-robust MoE gating with smooth STL robustness, robustness-adapted transitions, Bayesian posterior updates, and synthetic dynamical experts. The mechanism checks passed: observed log-odds slope 1.3000 versus predicted 1.3000, switching boundary beta=1.500 versus predicted 1.500, and beta=0 robustness sensitivity was exactly zero across the sweep. However, at beta=2.8 the STL router worsened one-step MSE (0.02525 vs 0.02513) and 50-step rollout MSE (3.531 vs 3.115), so there is no demonstrated accuracy win; worked=true reflects that the requested mechanism manifested, not that task performance improved.", "metrics": { "baseline": "One-step MSE 0.02513; 50-step rollout MSE 3.115; mode-2 selection rate 0.4313.", "idea": "At beta=2.8: one-step MSE 0.02525; 50-step rollout MSE 3.531; mode-2 selection rate 0.2063. Math: log-odds slope 1.3000/1.3000 predicted, boundary 1.500/1.500 predicted, beta=0 max transition difference 0.0." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 stl_robust_moe.py", "files": [ "stl_robust_moe.py", "results.json" ], "limitations": "This is a fixed-expert NumPy prototype rather than a trained GRU/state-space model; it uses one synthetic safety formula, one true regime, and a modest 160-episode experiment. The beta performance sweep uses independently sampled episodes rather than a shared paired dataset, and no CUDA, learning, missing-observation training, multi-formula STL, or statistical significance analysis was tested." }