nx_ltr.nx

nx_ltr.nx -- R-LTR of the onsite-search S-class ladder: SOVEREIGN learning-to-rank (LIBRARY). Learn a ranking function that COMBINES features (BM25 + vector cosine + click-CTR) from labeled data, instead of trusting any single signal -- the LTR idea (cited srch_ltr.raw). This is the CLASSICAL LINEAR model trained by a pairwise perceptron (Lloyd/Rosenblatt): for each (relevant, irrelevant) pair, if the model scores them wrong, nudge the weights toward the relevant one. Integer, deterministic, no-float, no external weights. HONEST SCOPE: linear LTR; DEEP-NEURAL LTR (a trained net) is the weight-gated extension -- the same frontier as the semantic model. exports: vr_ltr_score, vr_ltr_train. license_tier: ORIGINAL