{"id":"W2115065139","doi":"10.3109/0142159x.2014.899687","title":"Weighting checklist items and station components on a large-scale OSCE: Is it worth the effort?","year":2014,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Innovations in Medical Education","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada; University of British Columbia","funders":"","keywords":"Weighting; Checklist; Reliability (semiconductor); Test (biology); Scale (ratio); Consistency (knowledge bases); Computer science; Licensure; Statistics; Data mining; Psychology; Artificial intelligence; Medicine; Mathematics; Medical education; Cognitive psychology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002239365,0.0001477318,0.0002260526,0.00008429284,0.0002213179,0.00002723388,0.0001354325,0.0001961539,0.002622803],"category_scores_gemma":[0.001992982,0.00009344927,0.00004322905,0.0002878804,0.0002236689,0.00004883153,0.000049189,0.0007956514,0.0001363758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007698197,"about_ca_system_score_gemma":0.00007107943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004548631,"about_ca_topic_score_gemma":0.00001242997,"domain_scores_codex":[0.9978075,0.0001046575,0.0003986459,0.0002904233,0.001098958,0.0002997895],"domain_scores_gemma":[0.9991921,0.00007678856,0.0001100915,0.0003457112,0.00009497537,0.0001802947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001448049,0.001659433,0.3477906,0.0002404006,0.0001231039,0.00001172725,0.01511532,9.245224e-7,0.0001458521,0.002958934,0.4616308,0.170178],"study_design_scores_gemma":[0.002865083,0.0002381201,0.1539464,0.0005347077,0.00009300358,0.00004101069,0.001857879,0.1205549,0.00008560655,0.0003669373,0.7191857,0.0002307211],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9236421,0.00004319522,0.002222034,0.05765574,0.0004493397,0.0002993745,0.000001441849,0.00005477367,0.01563201],"genre_scores_gemma":[0.9719968,0.00002082689,0.0005348106,0.0189091,0.001000718,0.00005047188,0.0001266253,0.00002643567,0.007334174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2575548,"threshold_uncertainty_score":0.9982889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01954355735836385,"score_gpt":0.3249957843628187,"score_spread":0.3054522270044549,"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."}}