{"id":"W4388974973","doi":"10.1111/bju.16209","title":"Quality of erectile dysfunction information from ChatGPT and other artificial intelligence chatbots","year":2023,"lang":"en","type":"article","venue":"British Journal of Urology","topic":"Mental Health via Writing","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; York University; U.S. Department of Veterans Affairs","keywords":"Erectile dysfunction; Psychology; Quality (philosophy); Computer science; Artificial intelligence; Medicine; Psychiatry; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004361003,0.0009871338,0.0007437411,0.003769998,0.0007116049,0.002116782,0.0007850234,0.0009280192,0.1381483],"category_scores_gemma":[0.04461562,0.0004205572,0.0004838864,0.001845095,0.0002648025,0.001603735,0.001554688,0.0006624388,0.02396845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001305567,"about_ca_system_score_gemma":0.001103087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004718396,"about_ca_topic_score_gemma":0.004767123,"domain_scores_codex":[0.9960919,0.001250125,0.0005301845,0.0004354519,0.001379662,0.0003125988],"domain_scores_gemma":[0.9461004,0.04256726,0.001423886,0.0021539,0.006463566,0.001291103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.008324226,0.0016351,0.1013925,0.007759153,0.000283887,0.001191477,0.005484006,0.00645025,0.01195333,0.003299871,0.3706823,0.481544],"study_design_scores_gemma":[0.001646694,0.003215462,0.4869071,0.004192032,0.0006220681,0.001566712,0.006352615,0.08127058,0.05594455,0.009944854,0.3476276,0.0007097652],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2942351,0.001020013,0.03172516,0.001882354,0.0007353247,0.005164839,0.4677958,0.07119687,0.1262445],"genre_scores_gemma":[0.6123714,0.0005085216,0.0611961,0.0009927726,0.0001725245,0.005634546,0.2594016,0.005988364,0.05373408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1381483,"threshold_uncertainty_score":0.462152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0722376373951871,"score_gpt":0.3708669497790164,"score_spread":0.2986293123838293,"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."}}