{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01653028,0.0002986588,0.002653216,0.0004126211,0.000174618,0.00001508816,0.0006084256,0.0001498515,0.00001631539],"category_scores_gemma":[0.0212014,0.000182645,0.0002396522,0.002660228,0.0007857597,0.0003129111,0.00006783338,0.000508655,6.070117e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002556249,"about_ca_system_score_gemma":0.01880881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007086398,"about_ca_topic_score_gemma":0.00002632953,"domain_scores_codex":[0.993777,0.0008843038,0.003172996,0.0005667358,0.001258802,0.000340118],"domain_scores_gemma":[0.9891118,0.003672893,0.004951369,0.00079835,0.0013777,0.00008784336],"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":[0.000001846594,0.0001586997,0.0001590312,0.7770609,0.00001206661,3.839239e-8,0.00009510394,0.000001673231,8.641524e-8,0.001746348,0.000236567,0.2205276],"study_design_scores_gemma":[0.000114105,0.0004740276,0.00007596739,0.9784748,0.0007328803,0.0000775759,0.001331858,0.00007682634,0.000001953386,0.0008073128,0.01767644,0.000156261],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001585348,0.9825757,0.001716501,0.000975655,0.002106256,0.01241572,0.0000249915,0.00001445902,0.0001548856],"genre_scores_gemma":[0.0005196944,0.9555254,0.0404528,0.0004780826,0.0001686343,0.002758021,0.00006741155,0.00001449384,0.00001547857],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2203714,"threshold_uncertainty_score":0.9870434,"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."}}