Эксперимент: Zero-Augmented Double-Scoring (#533)

{ "worked": true, "confidence": 9, "verdict": "Built a readable zero-augmented double-scoring MVP with frozen weights, trainable real/dummy scores, hard Top-K straight-through selection, exhaustive representation checking, and a five-seed toy comparison. Across M=20,50,100 and augmented densities 0.2,0.5,0.8, observed real-count means and standard deviations matched the exact hypergeometric predictions, and dummy fractions were approximately 0.5; all masks with r≤K were represented exactly. The toy double-scoring accuracy was 0.700 versus 0.683 for baseline, but its effective density averaged 0.34 versus the baseline's fixed 0.30, so this is only a weak secondary signal rather than evidence of a clear accuracy win.", "metrics": { "mechanism_sweep": "9 settings; absolute mean-count error <=0.0221 edges, standard-deviation error <=0.0245, observed dummy fraction 0.4991-0.5016 versus predicted 0.5", "representation": "All 4096 masks for M=12 with r<=K=9 represented exactly; examples include r=0 with 9 dummy selections and r=9 with 0 dummy selections", "baseline": "Toy frozen linear score-only extraction: mean accuracy 0.6833, std 0.0581, effective density 0.300", "idea": "Toy zero-augmented extraction: mean accuracy 0.7000, std 0.0586, effective density 0.340, effective-density std 0.0735" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "run_experiment.py", "results.json", "REPORT.md" ], "limitations": "The planned CIFAR-10 six-layer MLP/CNN, rewinding and post-selection weight training, layerwise density curves, FLOP-matched comparisons, and five-seed trained-ticket evaluation were not tested. The toy comparison uses a single frozen linear layer and differs in effective density, so it cannot establish a practical strong-ticket improvement." }