{"id":"W4416723220","doi":"10.5489/cuaj.9302","title":"Comparative assessment of AI models in addressing questions on priapism","year":2025,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Priapism; MEDLINE; Continuing medical education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03772401,0.0008171779,0.001017647,0.002814368,0.0005617975,0.003107743,0.001185659,0.0009464014,0.001261156],"category_scores_gemma":[0.139685,0.0002773672,0.001337433,0.001404271,0.001043285,0.001908513,0.002713952,0.0009608906,0.0004223397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00229799,"about_ca_system_score_gemma":0.002277335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002155025,"about_ca_topic_score_gemma":0.002765632,"domain_scores_codex":[0.9737606,0.01789349,0.001829731,0.001321102,0.004660888,0.0005342108],"domain_scores_gemma":[0.7832646,0.1825876,0.01022659,0.006821286,0.01468421,0.002415754],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005933367,0.002890853,0.4016331,0.003978512,0.00101525,0.0003020796,0.04393991,0.01036982,0.004541914,0.00233563,0.004393806,0.5186658],"study_design_scores_gemma":[0.001343926,0.0151666,0.6627765,0.003672892,0.003154556,0.001519357,0.03629572,0.2192849,0.01914625,0.008781265,0.02809929,0.0007587533],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737509,0.0007007713,0.01553164,0.0006435869,0.0000713591,0.001599675,0.0003078299,0.0004712468,0.006922911],"genre_scores_gemma":[0.9638586,0.0004709931,0.03268202,0.0002316743,0.00003671557,0.001630983,0.0004753577,0.00003865361,0.0005748009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.962276,"threshold_uncertainty_score":0.199506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2077476182995771,"score_gpt":0.4709061944454124,"score_spread":0.2631585761458354,"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."}}