Add DFA direction-quality direct test (codex round 13 option c)

Trains both vanilla DFA (lam=0) and penalized DFA (lam=1e-2) from the same
seed, then directly measures the per-layer cosine between DFA's local
credit signal e_T @ B_l^T and the BP gradient at hidden layers. Uses the
training Bs (not fresh ones, per the Bs-specificity finding from earlier).

The penalized run is the key measurement: in that condition the BP grad is
~10^-7 (well above the eps=1e-8 floor), so a near-zero cosine here would
be the direct evidence of the second failure mode (direction-quality
ceiling) that codex round 13 hypothesized.

Pre-registered prediction: penalized cos(DFA, BP) ~ 0.01-0.05 -> direction
quality is the second, separable failure mode. Saves the penalized
checkpoint so the diagnostic protocol can be re-applied to it (where (a)
and (b) should pass, (d) should still fail).

0 files changed, 0 insertions, 0 deletions