Retrieval-augmented generation (RAG) pipelines may overlook the material relationship between a source and the query. We investigate a pre‑generation triage layer that treats this relationship as query‑dependent. The approach routes canonical query families to enhanced review and tags retrieved pages as pass, contextualize, exclude, or review. Key techniques include a four‑dimensional page score, rank‑discounted family aggregation, intent‑preserving query mutations, and a family‑held‑out router. A single‑coded pilot of 200 real URLs supplies provisional calibration anchors, and a 20,000‑row scenario with synthetic domain identifiers enables controlled workload analysis. An oracle page gate defines a risk‑coverage target for a future learned classifier. Evaluation shows that page‑level frequency cannot replace family‑level exposure and quantifies how calibration alters scenario activation. Annotation reliability remains unmeasured, and synthetic rankings omit real retrieval dynamics. The result is an auditable triage method and validation plan, not an estimate of deployed review workload, live‑Web prevalence, or downstream answer‑quality gains.
Review