{"id":"W4413367821","doi":"10.1002/uro2.70028","title":"Assessing the utility of a natural language processing model in answering common urological questions","year":2025,"lang":"en","type":"article","venue":"UroPrecision","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Question answering; Computer science; Natural language processing; Natural (archaeology); Information retrieval; History","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":[0.000494278,0.00006018094,0.0001407966,0.00009684116,0.00009765778,0.00002313655,0.00007732341,0.00006918042,0.000014791],"category_scores_gemma":[0.0006075913,0.00003902035,0.00003446711,0.0003361582,0.0000659232,0.000112909,0.00003642678,0.0002999624,0.000001779006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004074543,"about_ca_system_score_gemma":0.0001617293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003595114,"about_ca_topic_score_gemma":0.00008549566,"domain_scores_codex":[0.9992056,0.00007608228,0.0003240057,0.0001430164,0.0001293767,0.0001218582],"domain_scores_gemma":[0.9994038,0.0002332354,0.00005427893,0.0001911016,0.00009374782,0.00002383179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008455556,0.0001423396,0.05216239,0.00007734251,0.000002450305,0.000003615669,0.002511233,0.000503134,0.005545355,0.00009212128,0.00007856689,0.9387969],"study_design_scores_gemma":[0.00003807844,0.00002967035,0.1560478,0.0004221533,0.00001573223,0.000004782277,0.002431616,0.8328721,0.005807689,0.002236304,0.00005374709,0.00004033207],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854412,0.0016403,0.008755227,0.001779472,0.0001429185,0.0001996567,4.966938e-7,0.00002535096,0.00201536],"genre_scores_gemma":[0.9983909,0.00002076505,0.00116266,0.0003022419,0.00002899483,0.000008398348,0.000004520675,0.000003664959,0.00007788064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9387566,"threshold_uncertainty_score":0.1591204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1346930753895011,"score_gpt":0.4995114290061578,"score_spread":0.3648183536166567,"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."}}