# FAILURES.md — failed hypotheses, tests and attempts (never deleted)

date	what failed	evidence	resolution
2026-10-29	`test_incremental_equals_full_prefix_forced`: cached decoding ≠ full-prefix forward.	pytest, atol 1e-4	Root cause: forced-action forward let edits resume after STOP; made STOP absorbing (D4).
2026-10-29	rsync exclusion `experiments` also dropped `configs/experiments/`; baseline launch on M3U96b failed twice (`FileNotFoundError`).	`experiments/logs/pretrain_enlarged102m_seed1.log` (first attempts)	anchored pattern `/experiments`.
2026-10-29	Stage B bootstrap degeneracy (brief §13.1 confirmed): with U = 0 and lr 1e-3, 700 steps of forced mixed-budget training left val loss identical at every budget (0.4144 / 0.4143 / 0.4143 / 0.4146 / 0.4164 for budgets 0/1/2/4/8); grad-norm 0.01–0.02. Diagnosis: scale mismatch — backbone residual rms 5.64 vs readout difference rms 0.06, so U must grow by ×100 before edits can affect logits.	`experiments/runs/p4_editor_v1_seed01_*/metrics.jsonl` (stopped at step ~750)	D9: fixed non-learned `readout_scale` = measured backbone residual rms at bootstrap (keeps U = 0 init and exact identity; equivalent to a scale-aware learning rate). Variants with nonzero U init (std 0.02) and lr 3e-3 kept running on M2U64 / M4M64c as evidence.

spb/wp31_uqo