0 releases 185 tags

RSS feed

• archive/eval-f2-acceptance 008a6e097f

  Compare

  Order cross-database fusion by retrieval score

  Ghost released this 2026-09-01 07:35:39 +02:00 | 41 commits to main since this release

  Rank interleaving guarantees every database slots regardless of content;
  on domain-split collections it allocates no better than chance and costs
  4.7pp recall@5 at four collections against score ordering (7.1pp at
  eight). Hybrid scores are each database's own vector/FTS rank agreement,
  which carries across databases; equal scores resolve by within-database
  rank, and only a tie on both falls to configured order, leaving
  permutation sensitivity at 0.02-0.26pp. Fused results carry the
  candidate's own retrieval score, so the context-expansion re-sort
  preserves fused order.

  Downloads

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