v0.3.2: per-category breakdown, dataset version in report

v0.3: fix all reviewed issues (bugs #1-3, issues #4-8, 125 tests pass)

v0.2.1: claim quality filter, relevance check, stricter over-abstention, grounded_accept_rate

v0.1.4: frame-based contradictions, span-match upgrade, false_contradiction_rate, concise hypothesis

v0.1.2: slot-typed contradictions, NOT_IN_EVIDENCE postprocess, partial_hypothesis, punctuation fix

v0.1 patch: strengthen verifier/gate/metrics

Add src/report.py