0 releases 185 tags

RSS feed

• archive/eval-f3-acceptance 025e042fd0

  Compare

  Order cross-database fusion by cosine similarity to the query

  Ghost released this 2026-09-01 13:09:37 +02:00 | 40 commits to main since this release

  Retrieval scores are each database's own rank arithmetic; the databases
  in a selection share an embedder, so similarity in that one space is the
  signal comparable across databases by construction. Measured product to
  product against score ordering: +8.3 to +16.6pp recall@5 across five
  cells on two corpora, flat in collection count and corpus shape where
  score ordering dips with both, closing roughly 60% of the gap to a
  reranker; order-sensitivity residual 0.00pp in every cell. Exact ties
  collapse from 51-81% of candidates to under 1%. Full-text-only searches
  keep retrieval-score order, having no query vector. The vector column
  already travels with every search result, so the similarity costs no
  additional transfer; per-chunk embeddings are materialized only for the
  federated path that reads them.

  Downloads

  • Source code (ZIP)
    0 downloads
  • Source code (TAR.GZ)
    1 download