Test your RAG under corpus mutation, not against a static snapshot.

RAGAS-style evaluation checks correctness against a frozen snapshot, which means routine document updates and corrections can silently break production without moving a dashboard. This ASE 2026 paper defines 11 mutation operators perturbing at both the pre-chunk index level and post-chunk retrieved-context level. Across five datasets and 28,000+ mutants, metamorphic oracles detected violations at F1 0.927-1.000 versus 0.570 for the best RAGAS metric.