Эксперимент: Adversarial Subspace Residual Localizer (#1338)

{ "worked": false, "confidence": 9, "verdict": "Built a Fourier-feature spherical MUSIC residual localizer and numerically verified the core stability claim: for all tested adversarial rotations, the score perturbation stayed below the measured projector distance. However, the toy localization comparison showed no advantage over the cosine control at epsilon=0.20, and the residual method was worse at epsilon=0.50, so the promised localization win was not observed.", "metrics": { "baseline": "Cosine-style control: mean grid localization error 0.00667 at projector distance 0.20; 0.00667 at 0.50.", "idea": "Residual objective: mean grid localization error 0.00667 at projector distance 0.20; 0.01079 at 0.50. Maximum score perturbations for distances 0.02, 0.05, 0.10, 0.20, 0.35 were 0.00426, 0.00880, 0.02071, 0.06770, 0.11789, respectively, all within the bound." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py > results.json", "files": [ "experiment.py", "results.json", "README.txt" ], "limitations": "This was a small synthetic, non-neural experiment with a simple max-single-direction cosine control, no trained encoder, no ranking-loss training, no feature corruption/noise study, and a coarse coordinate grid. The stability check used finite random steering vectors rather than a uniform exhaustive search." }