{"id":"W2056927280","doi":"10.3399/bjgp12x649142","title":"Comparing performance among male and female candidates in sex-specific clinical knowledge in the MRCGP","year":2012,"lang":"en","type":"article","venue":"British Journal of General Practice","topic":"Sex and Gender in Healthcare","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Island Health","funders":"","keywords":"Test (biology); Medicine; Confounding; Confidence interval; Demography; Family medicine; Biology; Internal medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.004825808,0.00008849261,0.0003250519,0.00008642035,0.00008562768,0.00006064107,0.0001144395,0.00008694621,0.0000298847],"category_scores_gemma":[0.0003894962,0.00007660138,0.00004954626,0.0001786729,0.00008359064,0.0006747626,0.00003743845,0.001033282,0.000007275486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005535303,"about_ca_system_score_gemma":0.00008487741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005157877,"about_ca_topic_score_gemma":0.0004640671,"domain_scores_codex":[0.9980792,0.0005756216,0.00068506,0.0001326607,0.0002272086,0.0003002632],"domain_scores_gemma":[0.9987561,0.0005858646,0.0002400921,0.0001278334,0.0001225271,0.000167628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001826394,0.0003279442,0.9265994,0.00006106828,0.00001767233,0.000417887,0.001840198,0.000007130105,0.00001592229,0.00001132927,0.002153573,0.06836527],"study_design_scores_gemma":[0.001448755,0.000189627,0.9361064,0.0002827806,0.00002815831,0.02212934,0.004671632,0.0002736433,0.00004423453,0.000003986879,0.0347418,0.00007966767],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9602872,0.03369523,0.000005596142,0.0006230156,0.0004103861,0.0001491031,9.343954e-7,0.000003054909,0.00482548],"genre_scores_gemma":[0.9876409,0.009279147,0.0009096847,0.0005765049,0.001295994,0.000003113292,0.000002333326,0.00001118428,0.0002811754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06828561,"threshold_uncertainty_score":0.4489156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1272769807632178,"score_gpt":0.3986886550203753,"score_spread":0.2714116742571575,"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."}}