{"id":"W2160065345","doi":"10.1186/1472-6920-12-29","title":"Summative assessment of 5thyear medical students’ clinical reasoning by script concordance test: requirements and challenges","year":2012,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Summative assessment; Concordance; Multidisciplinary approach; Test (biology); Medical education; Curriculum; Educational measurement; Medicine; Academic year; Formative assessment; Mathematics education; Psychology; Internal medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03189705,0.0005711311,0.0008578786,0.002150539,0.0008044775,0.001321605,0.001447903,0.0007913796,0.00178883],"category_scores_gemma":[0.08078531,0.0002361225,0.0008720438,0.001108684,0.0006902352,0.001153878,0.002808913,0.000857589,0.0007133431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001159695,"about_ca_system_score_gemma":0.002340863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008466065,"about_ca_topic_score_gemma":0.002093987,"domain_scores_codex":[0.9779247,0.009191671,0.002742949,0.001045076,0.008394712,0.0007008424],"domain_scores_gemma":[0.9375654,0.023119,0.00680565,0.00397649,0.0241951,0.004338314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001696471,0.001791879,0.5792202,0.0005238929,0.0002813394,0.001140419,0.007894657,0.003655333,0.01335956,0.0006931891,0.004931753,0.3848112],"study_design_scores_gemma":[0.0002553636,0.01025494,0.8910393,0.0004776774,0.0001590652,0.004091904,0.004251755,0.03745663,0.04083554,0.00200903,0.008969757,0.0001990432],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9698867,0.0003243411,0.02288547,0.0004133364,0.0001303933,0.001106763,0.0002244799,0.0002485081,0.004780021],"genre_scores_gemma":[0.9539783,0.0001983748,0.04292054,0.0001097433,0.00004819546,0.001010521,0.0005903424,0.0000386848,0.001105265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03189705,"threshold_uncertainty_score":0.1686897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0947932579973595,"score_gpt":0.488989824920343,"score_spread":0.3941965669229835,"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."}}