{"id":"W2096673765","doi":"10.1186/1472-6920-13-166","title":"Construction and utilization of a script concordance test as an assessment tool for dcem3 (5th year) medical students in rheumatology","year":2013,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Concordance; Cronbach's alpha; Test (biology); Medicine; Rheumatology; Internal medicine; Context (archaeology); Medical education; Family medicine; Consistency (knowledge bases); Clinical psychology; Artificial intelligence; Computer science; Psychometrics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000951308,0.00009507821,0.0003252119,0.00008506022,0.00002688694,0.00001805908,0.0001109524,0.0002326112,0.0009659536],"category_scores_gemma":[0.1450324,0.00008087914,0.00003205052,0.0001339653,0.0002532979,0.00008238082,0.00003408797,0.0001688808,0.00001237463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005717175,"about_ca_system_score_gemma":0.003502572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005770653,"about_ca_topic_score_gemma":0.0001174698,"domain_scores_codex":[0.9981411,0.0001008268,0.0005663706,0.0002655929,0.0007675105,0.0001586056],"domain_scores_gemma":[0.992738,0.006144489,0.000177975,0.0002037476,0.0002678567,0.0004679149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004690759,0.001346223,0.9237244,0.000160554,0.000008093276,7.287794e-7,0.0001241762,1.204335e-7,0.00001503162,0.003661257,0.00171933,0.06919317],"study_design_scores_gemma":[0.003668134,0.0006598209,0.98509,0.002751547,0.00003945351,0.0001179665,0.0009432726,0.00358514,0.00004470263,0.002790951,0.0002119641,0.00009709661],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918815,0.0001053582,0.004346279,0.002117087,0.0006087043,0.0007346158,0.000002391622,0.00002068917,0.000183376],"genre_scores_gemma":[0.9883322,0.0003111635,0.009855191,0.0009487272,0.00009145062,0.0002419225,0.0001208495,0.00001102047,0.00008755026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1440811,"threshold_uncertainty_score":0.9999473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048638230242253,"score_gpt":0.4513157390124501,"score_spread":0.4208293567100276,"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."}}