Эксперимент: Pre-Training Depth Feasibility Certificates (#520)

{ "worked": true, "confidence": 8, "verdict": "Built a readable certificate-planning MVP with calibration, structural-floor bracketing, resource-radius computation, and feasible/impossible/unresolved decisions. Empirical sweeps confirmed the predicted depth exponent (-0.9989 vs -1), metadata halving law (maximum absolute ratio error 0.0217), and threshold boundary (predicted D=11.51, first passing grid D=16). The certificate avoided 22 of 90 evaluations and retained all successful candidates, but rejected 0/66 doomed candidates because the conservative lower bound could not exceed the target in this toy setting; therefore the mathematical mechanism manifested, but strong practical screening benefit was not demonstrated.", "metrics": { "baseline": "Exhaustive evaluation: 90/90 candidates evaluated; 24 successful and 66 doomed.", "idea": "Certificate screening: 68 unresolved candidates evaluated, 22 feasible candidates certified, 22 evaluations avoided, 100% feasible-certificate precision, 100% successful-candidate retention, 0/66 doomed candidates rejected." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 certificate_experiment.py", "files": [ "certificate_experiment.py", "results.json", "README.md" ], "limitations": "This is a synthetic scalar-error experiment, not CIFAR-10/WikiText-2 or neural-network quantization-aware training. The structural floor, constants, arithmetic penalty, and target are simulated rather than learned from real teacher/student models; no GPU-hours, wall-clock speedup, accuracy calibration, bootstrap confidence intervals, or real integer saturation tests were measured." }