{"id":"W4229008399","doi":"10.1007/s10459-022-10114-w","title":"Examining the validity argument for the Ottawa Surgical Competency Operating Room Evaluation (OSCORE): a systematic review and narrative synthesis","year":2022,"lang":"en","type":"review","venue":"Advances in Health Sciences Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Summative assessment; Argument (complex analysis); Competence (human resources); External validity; Internal validity; Medical education; MEDLINE; Psychology; Medicine; Formative assessment; Applied psychology; Social psychology; Pedagogy; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1109205,0.001890444,0.01009873,0.01192477,0.001363628,0.007250493,0.003984438,0.005955559,0.006606599],"category_scores_gemma":[0.3866273,0.001919722,0.01060945,0.008333174,0.003791783,0.006927591,0.004923146,0.005127741,0.0004657444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01294088,"about_ca_system_score_gemma":0.03414022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01384969,"about_ca_topic_score_gemma":0.04461563,"domain_scores_codex":[0.8890737,0.05665461,0.03167827,0.005310035,0.01563211,0.001651227],"domain_scores_gemma":[0.6723952,0.2848668,0.02861736,0.003673471,0.009409684,0.001037494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0005722135,0.00002223288,0.001466788,0.9359562,0.02750767,0.000116867,0.0007154685,0.0001583007,0.0001115826,0.00205597,0.003302488,0.02801404],"study_design_scores_gemma":[0.0008342362,0.0001185258,0.001841004,0.8773563,0.1015988,0.0001521486,0.0006224414,0.0001746725,0.0001162601,0.002128011,0.01500164,0.0000559807],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002115214,0.985054,0.001144908,0.006393487,0.001091823,0.002330331,0.0008152271,0.00001722325,0.001037857],"genre_scores_gemma":[0.1059374,0.858004,0.007625453,0.01764688,0.001066818,0.008201215,0.0008653795,0.00004144294,0.0006114997],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.1109205,"threshold_uncertainty_score":0.5866106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1421613514146165,"score_gpt":0.4924021311000273,"score_spread":0.3502407796854108,"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."}}