citevahti-eval

Use when measuring or publishing CiteVahti's own accuracy — running the automatic claim-lexicon evaluation, checking it against its regression baseline, reasoning about how AI second-rater models are rated, or answering "how accurate is CiteVahti?". Follows ADR-0009's three evaluation objects (automatic lexicon eval, continuous model rating, pooled Atlas). Maintainer-facing; not for checking a researcher's…