justin 2e10279beb eval: new baseline on the 4-endpoint embed pool index ...

22 queries against the prod image index rebuilt today on the expanded
GPU pool with the resilient embedder (PR #8): dense MRR 0.539→0.924,
bm25+rerank 0.920→0.959, hybrid_rrf+rerank 0.875→0.960 vs the
2026-05-22 baseline. No regression from mixed-provenance embeddings.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-06-10 20:38:23 -04:00

..

baseline-20260610.md

eval: new baseline on the 4-endpoint embed pool index

2026-06-10 20:38:23 -04:00

baseline.md

search: BM25-default + cross-encoder rerank, hybrid behind env gate

2026-05-22 13:06:51 -04:00

with_reranker.md

search: BM25-default + cross-encoder rerank, hybrid behind env gate

2026-05-22 13:06:51 -04:00