Audit finite-energy KL on stochastic path measures

Expand generation recurrence to parametric error families

Add universal generation recurrence certificate

Audit learned score scope for diffusion bounds

Expand influential-set path correlations

Audit influential-set bounds on non-Gaussian paths

Broaden diffusion collapse claim scope

Widen Gaussian claims to exact time-inhomogeneous paths

Claim 6: run the 10-D Gaussian-mixture self-consuming loop independently (was source-pinned only); alpha=0 degrades 9.4x vs 1.2x at alpha=1 over 80 generations