Эксперимент: Agnostic Geometry-Prior Mixer (#1267)

{ "worked": true, "confidence": 7, "verdict": "Built a reproducible PyTorch MVP with free and geometry-aware branches, global or input-dependent sigmoid gates, and optional gate regularization. The math check confirmed convex interpolation, sigmoid(-4)=0.018 initialization, and the positive gradient of the suppression penalty. The input-dependent mixer improved over the free baseline on correct, wrong, irrelevant, and half-geometry tasks, while lowering mean alpha for wrong and irrelevant priors; the global gate was less effective.", "metrics": { "baseline": "Free MLP RMSE: correct 0.1322, wrong 0.0673, none 0.0604, half 0.1670.", "idea": "Input-dependent mixer RMSE: correct 0.0103 with alpha 0.608, wrong 0.0299 with alpha 0.180, none 0.0412 with alpha 0.106, half 0.1216 with alpha 0.718. Always-geometry RMSE: 0.0119, 0.0629, 0.0508, and 0.1225." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only one random seed and one small network/training schedule were tested. No repeated-seed intervals, FLOP or wall-clock comparison, noisy-prior sweep, larger datasets, or learned R-function support module were evaluated." }