{"id":"W7077890825","doi":"10.48448/gamm-6t13","title":"Zero-Shot ATC Coding with Large Language Models for Clinical Assessments","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Coding (social sciences); Bottleneck; Health care; Ontology; Process (computing); Data integration","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001686968,0.0003038976,0.0004185933,0.0002624333,0.0002912428,0.0002638718,0.002405499,0.0002516662,0.0001002483],"category_scores_gemma":[0.0002163533,0.0002415447,0.00008810924,0.0007384796,0.0003724291,0.0003045395,0.0007445483,0.0003416919,0.00001763648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005978992,"about_ca_system_score_gemma":0.001100133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004670473,"about_ca_topic_score_gemma":0.00005477421,"domain_scores_codex":[0.9971605,0.00004588179,0.0003728831,0.001163814,0.0005582891,0.0006986512],"domain_scores_gemma":[0.9980572,0.0002108975,0.0003079804,0.001026343,0.0002300854,0.0001675209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003282667,0.0006895539,0.0008659938,0.0005713349,0.0001989958,0.0001017152,0.0004002572,0.001141444,0.0003571997,0.5770993,0.3793196,0.03922177],"study_design_scores_gemma":[0.001521469,0.0002775957,0.00004048997,0.0006489466,0.0000516336,0.00001621703,0.0002057365,0.627481,0.0003708438,0.01632971,0.3521952,0.0008611662],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00000893428,0.00009402546,0.6220824,0.0004896,0.0003830938,0.000284518,0.0000329282,0.0002141264,0.3764104],"genre_scores_gemma":[0.03930632,0.00008013833,0.2683736,0.001281954,0.0003166769,0.00005849488,0.0000641219,0.00004142844,0.6904773],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6263396,"threshold_uncertainty_score":0.9849905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06960542250939906,"score_gpt":0.3862814749890439,"score_spread":0.3166760524796448,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}