{"id":"W4415380101","doi":"10.1186/s41077-025-00375-x","title":"Using Kane’s validity framework to examine the implications of feedback in simulation-based assessments","year":2025,"lang":"en","type":"article","venue":"Advances in Simulation","topic":"Simulation-Based Education in Healthcare","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; University of Toronto; University Health Network; St. Michael's Hospital","funders":"","keywords":"Health services research; Argument (complex analysis); External validity; Predictive validity; Program evaluation; Test validity; Validity; Internal validity","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.589623,0.002291108,0.003780316,0.0219791,0.006650626,0.0115959,0.005127036,0.004961638,0.003010731],"category_scores_gemma":[0.8110119,0.001700241,0.008496548,0.01138354,0.03871156,0.01592636,0.01417171,0.006979909,0.0004340883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02228102,"about_ca_system_score_gemma":0.02911878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00822999,"about_ca_topic_score_gemma":0.005734728,"domain_scores_codex":[0.2566327,0.5613048,0.06010277,0.01668072,0.1011476,0.004131325],"domain_scores_gemma":[0.07840788,0.8190507,0.02816536,0.02131739,0.0520853,0.0009732781],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00164194,0.0005341322,0.2101256,0.00908791,0.004883181,0.0008028443,0.0573383,0.02150293,0.00098927,0.4170532,0.004157123,0.2718836],"study_design_scores_gemma":[0.001189643,0.003650308,0.09011373,0.02502903,0.00265488,0.001241707,0.0266543,0.1044064,0.00536094,0.7036234,0.03503386,0.001041858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1190372,0.007710593,0.7762122,0.01718998,0.001400522,0.01146264,0.0006608697,0.0002574439,0.06606852],"genre_scores_gemma":[0.7830108,0.0007685102,0.2017338,0.001553117,0.0002642916,0.01186471,0.0001837151,0.00009210261,0.0005290146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.589623,"threshold_uncertainty_score":0.5060679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1389926103905232,"score_gpt":0.527348115375092,"score_spread":0.3883555049845687,"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."}}