{"ID":2921565,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T04:17:48.870468959Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00994","arxiv_id":"2606.00994","title":"A Registry-Bound LLM Pipeline for Evidence-Grounded Trait Extraction across Tropical Plants, Aquatic Species, and Exotic Pets","abstract":"We describe a registry-bound large-language-model extraction pipeline producing evidence-grounded structured trait records at scale, on cultivated tropical plant, aquatic, and pet species. Four mechanisms render LLM-derived rows auditable: a versioned 39-key closed-vocabulary trait registry constraining every admitted value to a typed schema; a per-row verbatim evidence quote tying each value to source text; a per-row confidence label (high or medium; low dropped pre-persist); and multi-version preservation. Applied to 409,880 publishable species from the Tropical Species Encyclopedia, the pipeline executed 706,220 runs and persisted 5,489,881 trait records across 409,820 species (99.985%), 81.57% at high confidence. We report three validation layers in descending evidentiary strength: at full population, 90.12% of 5,427,588 evidence-bearing rows have their quote as a verbatim source substring (93.49% excluding one compliance meta-trait); a quote-supports-value audit on n=100 stratified non-red-zone rows yielded 100/100 (lower bound 96.30%); face-validity on n=50 red-zone rows yielded 50/50 Accept (lower bound 92.86%). Per-record correctness is not claimed; 100% pending human curation. The contribution is the four-mechanism framework.","short_abstract":"We describe a registry-bound large-language-model extraction pipeline producing evidence-grounded structured trait records at scale, on cultivated tropical plant, aquatic, and pet species. Four mechanisms render LLM-derived rows auditable: a versioned 39-key closed-vocabulary trait registry constraining every admitted...","url_abs":"https://arxiv.org/abs/2606.00994","url_pdf":"https://arxiv.org/pdf/2606.00994v1","authors":"[\"Jeff Wang\"]","published":"2026-05-31T04:17:47Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}