Second narration episode — gritty technical observation о 4DGS-from-scratch ceiling после TASK-105 binary test. 12 spatial + 22 Wan train = test PSNR 25; добавил 121 frame Wan — упал к 13. Diversity > volume. Real 4D avatar требует CAP4D-class diffusion-trained — pending FLAME unblock. Pure 4DGS narration на v2 source, 35 sec, ~15 sec compute.
TASK-105 binary test: data enrichment retrain. Naive temporal-only expansion (10 frames + 121 Wan motion frames at fixed camera) caused REGRESSION — train PSNR 30.5 (locked в overfit), test PSNR 13.16 (vs v2 25.4). v3 rolled back, v2 restored as production. Ceiling confirmed: 4DGS-from-scratch на synthetic data cannot generalize beyond training distribution без diverse spatial+temporal sampling. CAP4D-class diffusion-trained 4DGS = real path forward (FLAME owner unblock pending).