{"id":"W2804311512","doi":"10.1007/s11934-018-0799-7","title":"Surgical Education, Simulation, and Simulators—Updating the Concept of Validity","year":2018,"lang":"en","type":"review","venue":"Current Urology Reports","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Toronto General Hospital; University of Toronto","funders":"","keywords":"Summative assessment; Generalizability theory; Construct validity; External validity; Context (archaeology); Construct (python library); Formative assessment; Medicine; Mentorship; Medical education; Test (biology); Process (computing); Quality (philosophy); Psychology; Computer science; Psychometrics; Social psychology; Clinical psychology; Pedagogy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007949353,0.0003002654,0.001303452,0.0001184781,0.0001324142,0.00001480231,0.00007496861,0.0003100876,0.0003306358],"category_scores_gemma":[0.001127226,0.0001865982,0.0003339152,0.0002807529,0.000485013,0.00004048561,0.00008967938,0.0004717094,0.000008297523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002876656,"about_ca_system_score_gemma":0.0006228245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002147113,"about_ca_topic_score_gemma":2.777636e-7,"domain_scores_codex":[0.9973442,0.0003298295,0.001326088,0.0005105641,0.000266631,0.0002226843],"domain_scores_gemma":[0.9961532,0.00162512,0.001171933,0.000536722,0.0003513169,0.000161683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000158562,0.0001768238,0.003649316,0.001736145,0.0001247365,0.00005504431,0.0001302241,0.0001203698,3.862819e-9,0.0003953308,0.0003027476,0.9932934],"study_design_scores_gemma":[0.0003024106,0.00007655487,0.0001980231,0.001086789,0.001010949,0.0008086297,0.00001039752,0.0004333071,1.381247e-7,0.0001569104,0.9957669,0.0001490224],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001835602,0.994358,0.000043788,0.00004360401,0.001526354,0.0008074963,0.000005932066,0.00004882281,0.00133039],"genre_scores_gemma":[0.2980123,0.6998017,0.00002392234,0.00008447507,0.001423289,0.00004431381,0.00043869,0.00004899056,0.0001223388],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9954641,"threshold_uncertainty_score":0.7609253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1373971338598521,"score_gpt":0.4453425775551967,"score_spread":0.3079454436953446,"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."}}