{"id":"W2056983349","doi":"10.1007/s10459-011-9338-8","title":"Script concordance test item response process: The argument for probability versus typicality","year":2011,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Concordance; Test (biology); Argument (complex analysis); Psychology; Statistics; Computer science; Mathematics; Medicine","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":[0.3222542,0.001183958,0.003496118,0.004467578,0.003100863,0.003955287,0.00512458,0.004281907,0.007118159],"category_scores_gemma":[0.755002,0.001582835,0.003033256,0.00274049,0.008570866,0.008318952,0.004973779,0.006353945,0.001611094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002745587,"about_ca_system_score_gemma":0.004434074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002240553,"about_ca_topic_score_gemma":0.001898277,"domain_scores_codex":[0.609175,0.2829557,0.02555703,0.02222779,0.05823437,0.001850016],"domain_scores_gemma":[0.1207282,0.7978061,0.01459042,0.03762189,0.02791152,0.001341885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01755617,0.001863864,0.3340679,0.003335442,0.004416084,0.001079253,0.02018493,0.0168646,0.004363045,0.2006796,0.03835675,0.3572324],"study_design_scores_gemma":[0.002738477,0.004501339,0.270566,0.002355758,0.001199865,0.004589788,0.003572799,0.2977167,0.01378546,0.3764082,0.02170115,0.0008644895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.322871,0.001346592,0.6225308,0.01053112,0.002524529,0.006050462,0.001307758,0.002049227,0.03078843],"genre_scores_gemma":[0.8350237,0.0002282191,0.1519744,0.003435283,0.0005956452,0.005152558,0.0008625588,0.0004828873,0.002244833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3222542,"threshold_uncertainty_score":0.8357812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08500634466955383,"score_gpt":0.4551632643259196,"score_spread":0.3701569196563658,"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."}}