{"id":"W4399516157","doi":"10.2196/47562","title":"Quality of Male and Female Medical Content on English-Language Wikipedia: Quantitative Content Analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"CHEO Research Institute","keywords":"Content (measure theory); Content analysis; Quality (philosophy); Computer science; Psychology; Natural language processing; Sociology","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02360466,0.00007431825,0.0003500388,0.0005682667,0.00007509766,0.0001686043,0.0005018334,0.0002141253,0.004349217],"category_scores_gemma":[0.03317526,0.00005277678,0.0001526151,0.001109835,0.0009801117,0.000186604,0.00008407178,0.001005068,0.00001559596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001840292,"about_ca_system_score_gemma":0.001524207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002968788,"about_ca_topic_score_gemma":0.003918248,"domain_scores_codex":[0.9913604,0.001886087,0.0007497135,0.000179362,0.005580653,0.0002437533],"domain_scores_gemma":[0.9941052,0.003308767,0.0001743208,0.0001161607,0.001713146,0.000582379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0007201898,0.00120277,0.02562658,0.0002475612,0.001831895,0.0005474261,0.3942823,0.000003118021,0.0003830753,0.472668,0.05035814,0.05212897],"study_design_scores_gemma":[0.001589043,0.001881918,0.02451794,0.001557079,0.0002009407,0.00002383463,0.8948004,0.002687881,0.0009652471,0.0009295066,0.07057393,0.0002722865],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9645268,0.002597465,0.0006747495,0.02434125,0.0009572803,0.0001160629,0.000006676279,0.000009172298,0.006770558],"genre_scores_gemma":[0.9932548,0.001270049,0.00008918966,0.0001754633,0.0007520163,0.000005523732,0.000002621803,0.000005231882,0.00444511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5005181,"threshold_uncertainty_score":0.9965609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2777698035438871,"score_gpt":0.5541652395147908,"score_spread":0.2763954359709037,"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."}}