nx_distrib_embed.nx

nx_distrib_embed.nx -- R3 rung 2 (R3b): a SOVEREIGN DISTRIBUTIONAL embedder = the Jina-Embeddings replacement, count-based (NOT a trained neural net, NO float, NO training loop): "you shall know a word by the company it keeps" (Firth 1957 / Turney-Pantel 2010). Word vector = its co-occurrence row over a corpus; doc vector = sum of its words' rows; similarity = integer cosine (isqrt). This is the SEMANTIC lever nx_vec_index needed. THE PROOF (what BM25 canNOT do): query 'cat' retrieves the DOG doc over the CAR doc even though NEITHER contains the word 'cat' -- pure semantic (shared context), zero lexical overlap. main() = KAT gate + neg-control. HONEST SCOPE: proves the METHOD on a controlled mini-corpus (docs pre-tokenized to word-IDs to isolate the embedder from string-tokenization). Scaling to the real 519-doc library (tokenizer + big matrix) = R3b-scale. license_tier: ORIGINAL expect_exit: 0