nx_beir_arms_lib.nx

nx_beir_arms_lib.nx -- THE ONE CHOOSER of the arm the BRIGHT sweep writes into search.leaderboard (search R0f, 2026-09-16). WHY A LIB: be_bright used to choose between plain BM25 and the BM25Q RRF fusion only, so the cross-encoder arm's twelve-split average was read by nobody and could never reach the row -- a whole day of rerank compute would have left the placement at the lexical floor with nothing in the receipt saying so. The choice is a pure function of the sweep's own averages so an in-process gate can hold every branch (nx_beir_arms_gate), and the harness composes it. THE RULES, each pre-declared on search.plan before the run that could benefit from it: plain the floor; always eligible fused the BM25Q RRF arm: eligible only when its own rule held in the SAME sweep (fusion beat plain on the long subset AND every no-repeat query ranked identically), and its average is at least the plain average prf RM3-style pseudo-relevance feedback (R0g): eligible only when EVERY split measured it and it EXCEEDS plain and the best so far -- the non-reasoning expansion control the R0c rewriter must beat crossenc the sovereign BERT cross-encoder rerank over a LICENSED data asset: eligible only when EVERY split measured it (a partial average is not a placement) and it EXCEEDS plain BM25 (the R0 accept rule) and the best so far cefusion RRF over the BM25 order and the cross-encoder order: same eligibility as crossenc; it displaces the pure rerank only when STRICTLY higher, so a tie keeps the simpler arm license_tier: ORIGINAL No hw writes (Rule 26).