Reference
Findings
Every measured claim on this site, stated once. Each carries the caveat the measurement came with — a number without its conditions is the thing this site exists to complain about.
2 findings
- 01
Can a reranker improve recall?
No. Pass@10 was 20/42 in all four reranker configurations, identical to the decimal — a reranker reorders the candidate set it was handed and cannot add to it.
That the candidate set beyond rank ten held nothing useful is inferred from four models agreeing, not measured directly. recall@50 was never logged.
Reranking cannot find what retrieval missed → - 02
What does an English-only reranker cost on non-English queries?
4.8 points of Pass@1 on 42 Korean queries, and 5.4 on a second set of 56. The English-only default scored below running no reranker at all.
Recall did not move — the loss is entirely in ranking.
Your reranker speaks English. Your tickets do not. →