{"id":"W2169966878","doi":"10.1186/1472-6920-4-23","title":"The impact of two multiple-choice question formats on the problem-solving strategies used by novices and experts","year":2004,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Foothills Medical Centre; Health Sciences Centre; University of Calgary","funders":"","keywords":"Multiple choice; Think aloud protocol; Computer science; Psychometrics; Matching (statistics); Pencil (optics); Test (biology); Educational measurement; Mathematics education; Management science; Psychology; Curriculum; Mathematics; Statistics; Human–computer interaction; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03751747,0.0009206188,0.0009358057,0.001322292,0.0003072898,0.002043231,0.00102948,0.001242431,0.005344424],"category_scores_gemma":[0.3042976,0.0004059898,0.0009446056,0.0008037335,0.001316792,0.003250011,0.002335594,0.001235224,0.000708813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006851497,"about_ca_system_score_gemma":0.0007294929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003421672,"about_ca_topic_score_gemma":0.0003969657,"domain_scores_codex":[0.9566606,0.02719367,0.00527119,0.003288964,0.006671481,0.0009140954],"domain_scores_gemma":[0.4227187,0.5452889,0.01323005,0.008044088,0.006945894,0.003772386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.04278998,0.01227377,0.3280247,0.003319893,0.001038797,0.0006529103,0.01741073,0.005714034,0.03207729,0.002644693,0.001919671,0.5521336],"study_design_scores_gemma":[0.005406275,0.07230864,0.8010788,0.002454088,0.001062641,0.002917085,0.008702671,0.02570084,0.05609494,0.01283126,0.01085836,0.0005844572],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885386,0.0003730637,0.006882142,0.0002508238,0.00009342581,0.0005285274,0.0001136642,0.00006260706,0.003157087],"genre_scores_gemma":[0.980432,0.0002034571,0.01711699,0.0002279529,0.00004112677,0.0009617633,0.000201726,0.0000285598,0.0007864719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03751747,"threshold_uncertainty_score":0.1984137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02945401467417535,"score_gpt":0.4096948106071412,"score_spread":0.3802407959329658,"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."}}