docs(05): scale-normalize the ACNet generator plot

Archimedean generators are identified only up to a scaling of their argument
(phi(t) and phi(ct) give the same copula), so the raw overlay looked far off
even though the fitted copula matched (LL near the Clayton ceiling). Normalize
both generators to phi'(0) = -1 before plotting; the learned ACNet now visibly
tracks the true Clayton, with a small residual = genuine approximation error.
Added a markdown note explaining the identifiability.

Author: thisiscam