Эксперимент: Mode-Aware Mask Schedule (#619)

{ "worked": true, "confidence": 8, "verdict": "Implemented the mode-aware mask sampler and tested it on a synthetic two-mode masked-prediction task. Analytic schedule probabilities matched Monte Carlo measurements, and adding low-visibility masks plus a 0.01 fully masked anchor reduced empty-context mode error from 0.5504 to 0.0027 while conditional accuracy remained nearly unchanged. The mechanism therefore manifested in this toy experiment.", "metrics": { "baseline": "Conditional accuracy 0.9460; empty-context mode probability 0.2496; mode error 0.5504.", "idea": "Conditional accuracy 0.9440; empty-context mode probability 0.7973; mode error 0.0027; measured pi_1 0.1110 versus predicted 0.1100; measured full-mask mass 0.0101 versus predicted 0.0100." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json", "run.log" ], "limitations": "Tested only a small synthetic dataset with an MLP predictor; no Transformer, language corpus, unconditional generation, FLOP-normalized comparison, or repeated-seed study." }