{"id":"W2120424561","doi":"10.1016/j.artmed.2005.07.005","title":"Automatic identification of confusable drug names","year":2005,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Identification (biology); Artificial intelligence; Natural language processing; Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001289111,0.0001501847,0.0003061246,0.0002543034,0.0000977747,0.000006100923,0.0002644497,0.0001075915,0.00483449],"category_scores_gemma":[0.0002970095,0.0001372683,0.00005215381,0.0004982653,0.0004363171,0.0002257488,0.0000272809,0.0004693857,0.0005356764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007661732,"about_ca_system_score_gemma":0.00006084359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001210706,"about_ca_topic_score_gemma":0.0001285177,"domain_scores_codex":[0.9981152,0.0001718132,0.0009695818,0.0002403853,0.0001979988,0.0003050489],"domain_scores_gemma":[0.9988573,0.0004729662,0.0002539794,0.0001948292,0.0001073391,0.0001135746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00012336,0.0007762123,0.003775915,0.0001015175,0.00007325708,0.00001987205,0.006697915,0.01341205,0.3943341,0.0244475,0.005663689,0.5505747],"study_design_scores_gemma":[0.0002449057,0.00005154614,0.0007095005,0.00009546161,0.00009659688,0.00001140738,0.003506084,0.2383948,0.7064441,0.01023122,0.0400017,0.0002126599],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9806526,0.0006300017,0.001251269,0.009084427,0.001299577,0.0004145838,0.00001599188,0.00009324431,0.006558272],"genre_scores_gemma":[0.9971991,0.0004842794,0.0001424847,0.00111455,0.0004103354,0.00003781487,0.00001545914,0.00001168116,0.0005843665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.550362,"threshold_uncertainty_score":0.9960752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1627823311511077,"score_gpt":0.4946868934425481,"score_spread":0.3319045622914403,"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."}}