{"id":"W1986137923","doi":"10.1007/s10459-015-9593-1","title":"Constructing a validity argument for the Objective Structured Assessment of Technical Skills (OSATS): a systematic review of validity evidence","year":2015,"lang":"en","type":"review","venue":"Advances in Health Sciences Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":170,"is_retracted":false,"has_abstract":false,"ca_institutions":"The Wilson Centre; St. Paul's Hospital; University Health Network; University of British Columbia","funders":"University of Toronto","keywords":"Formative assessment; Construct validity; PsycINFO; Argument (complex analysis); Evidence-based medicine; MEDLINE; Construct (python library); Psychometrics; Psychology; Applied psychology; Computer science; Medicine; Clinical psychology; Mathematics education","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2881926,0.002664101,0.01396368,0.01436173,0.0020297,0.007482521,0.005951407,0.007661309,0.002901518],"category_scores_gemma":[0.5919432,0.002571608,0.01747613,0.007746918,0.01027282,0.00908075,0.006200534,0.005798204,0.0003918587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008142812,"about_ca_system_score_gemma":0.02231454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006824581,"about_ca_topic_score_gemma":0.01300405,"domain_scores_codex":[0.6795972,0.1875587,0.07618894,0.01351742,0.04096485,0.00217296],"domain_scores_gemma":[0.3121734,0.6300352,0.0323146,0.01173957,0.01282958,0.0009076533],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.002112143,0.0001281264,0.01301976,0.7071258,0.1242529,0.0003269013,0.001973121,0.0009867074,0.0003466559,0.01530036,0.003208704,0.1312188],"study_design_scores_gemma":[0.004262178,0.0009070383,0.01073034,0.6685458,0.2386652,0.0005829027,0.001491647,0.002528754,0.0009570066,0.04043825,0.03060394,0.000286884],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006356014,0.9641191,0.01363992,0.007595416,0.001833844,0.003646509,0.0006063794,0.00004029992,0.002162329],"genre_scores_gemma":[0.3599695,0.538139,0.06140345,0.02140798,0.002297834,0.01431658,0.001638064,0.00009827112,0.000729406],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7118074,"threshold_uncertainty_score":0.8777853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1160734690346563,"score_gpt":0.5454650536518105,"score_spread":0.4293915846171542,"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."}}