{"id":"W2619928717","doi":"10.2147/amep.s128321","title":"Investigating a self-scoring interview simulation for learning and assessment in the medical consultation","year":2017,"lang":"en","type":"article","venue":"Advances in Medical Education and Practice","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Reliability (semiconductor); Medical education; Computer science; Variance (accounting); Objective structured clinical examination; Psychology; Applied psychology; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01619076,0.0005411467,0.0003586867,0.001094617,0.0007716766,0.001196951,0.000846773,0.0006707918,0.003015046],"category_scores_gemma":[0.08854983,0.0002732565,0.0006891191,0.0005421922,0.001066924,0.0007282037,0.001653382,0.001032653,0.001199843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001295002,"about_ca_system_score_gemma":0.001789638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008192257,"about_ca_topic_score_gemma":0.001820414,"domain_scores_codex":[0.9830993,0.01323105,0.001113897,0.000741663,0.001349961,0.0004641876],"domain_scores_gemma":[0.9026725,0.07191166,0.005436913,0.006282851,0.0110045,0.002691472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001937871,0.005937387,0.5304801,0.0006221563,0.0001580832,0.001230896,0.08718549,0.008279617,0.03282654,0.002642174,0.006490917,0.3222087],"study_design_scores_gemma":[0.001222878,0.02741211,0.5989463,0.0006434698,0.0003067355,0.004050408,0.124711,0.1073486,0.07733713,0.007599972,0.04962192,0.0007995055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9621432,0.00003395496,0.03008758,0.0003544583,0.00005500423,0.002072222,0.000208785,0.0003103352,0.004734398],"genre_scores_gemma":[0.9500614,0.00005664997,0.04614006,0.0001297849,0.00002293824,0.001540998,0.0002494232,0.00003015385,0.001768484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01619076,"threshold_uncertainty_score":0.08562589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06238171820043661,"score_gpt":0.5473635698218368,"score_spread":0.4849818516214002,"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."}}