Эксперимент: Conditioned PSD sensing bottleneck (#698)

{ "worked": true, "confidence": 9, "verdict": "Built a rank-one PSD sensing bottleneck toy verifier with quantile condition loss and optimized sensing vectors. All three mechanism predictions manifested: beta was invariant under common scaling while L and U scaled by 3.7^2, beta decreased from 3.281 to 1.237 as m increased from 8 to 256, and beta increased from 1.321 to 9.408 as anisotropy gamma increased from 1 to 16. At m=32, conditioning reduced test beta from 1.799 to 1.367 and increased L from 2.608 to 3.035, so the proposed effect is real in this controlled setting.", "metrics": { "baseline": "Random normalized PSD sensing, m=32: L_q05=2.6077, U_q95=4.6922, beta=1.7994", "idea": "Optimized quantile-conditioned PSD sensing, m=32: L_q05=3.0349, U_q95=4.1487, beta=1.3670; train log-condition loss 0.6917 -> 0.2812" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results_final.json", "results.json", "run_output.txt" ], "limitations": "Only synthetic rank-one PSD feature pairs were tested; no CIFAR-10 model, dense projection baseline, task accuracy, perturbation robustness, FLOPs, memory, or multi-seed evaluation was run. The width and anisotropy sweeps use empirical quantiles rather than exact global Lipschitz constants." }