Эксперимент: Partial-ReNoise Neural Architecture Mutation (#1060)

{ "worked": true, "confidence": 8, "verdict": "Built a self-contained categorical partial re-noising architecture mutation MVP with validity checks, repair, an independent-prior baseline, and fixed-seed sweeps. The mechanism manifested: forward-token retention matched alpha_bar within 0.0028, edit distance increased monotonically from 0.000 at gamma=0 to 0.702 at gamma=1, and gamma=1 approached independent sampling with an edit-distance gap of 0.021. No accuracy improvement was demonstrated; post-repair validity was 100% by construction.", "metrics": { "baseline": "Independent valid-prior sampling: mean parent-child edit distance 0.7231; validity 100%; synthetic mean accuracy approximately 77.27.", "idea": "Mutation mean edit distance: gamma 0.05=0.0138, 0.15=0.0606, 0.30=0.2006, 0.60=0.4994, 1.0=0.7019. Raw validity was 98.5%, 95.5%, 85.0%, 75.5%, and 72.5% respectively; gamma=1 edit gap from independent was 0.0213; maximum retention error was 0.0028." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 partial_renoise_experiment.py", "files": [ "partial_renoise_experiment.py", "results.json" ], "limitations": "This is a toy fixed-length categorical architecture space, not NAS-Bench-201 or CIFAR-10. The reverse model is hand-designed rather than trained, latency and accuracy are synthetic proxies, only one random seed was used, and repair makes post-repair validity uninformative." }