Rank ILIKE matches by lexical coverage instead of recency and attach lexical scores to keyword rows so MemFuseBench candidate recall rises sharply while Chinese hybrid ordering stays unchanged.
Co-authored-by: Cursor <cursoragent@cursor.com>
Wire an offline benchmark over the production pgvector ranking path so Memory V2 recall can be measured with candidate/ranking loss split before lifecycle work lands.
Co-authored-by: Cursor <cursoragent@cursor.com>
john