CHECKLIST: add pitfall #6.5 — silent self-cosine fallback when aux nets not saved

Discovered in our own cnn_baseline.py: when the random feedback Bs (for
DFA) or bridge predictor (for SB/CB) are not persisted alongside the
model checkpoint, post-hoc Gamma computation cannot reconstruct the
local credit signal. Instead of erroring, the script falls back to
cos(BP_grad, BP_grad) = 1.0 and records that as Gamma. Reader who
doesn't notice the small 'Gamma_note' field interprets 1.0 as perfect
alignment.

Recommendation: always save aux nets alongside checkpoints; if they're
missing, report Gamma as N/A, not 1.0.

0 files changed, 0 insertions, 0 deletions