{"id":"W2890473533","doi":"10.1152/advan.00186.2016","title":"Item statistics derived from three-option versions of multiple-choice questions are usually as robust as four- or five-option versions: implications for exam design","year":2018,"lang":"en","type":"article","venue":"AJP Advances in Physiology Education","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Biological Infrastructure; University of California, Irvine; National Science Foundation","keywords":"Multiple choice; Point (geometry); Class (philosophy); Quarter (Canadian coin); Mathematics education; Psychology; Index (typography); Statistics; Computer science; Mathematics; Artificial intelligence; Significant difference","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"],"consensus_categories":[],"category_scores_codex":[0.0007758594,0.0001972504,0.000293648,0.0002527299,0.0009681176,0.00002369218,0.0003762382,0.0002190058,0.00009970446],"category_scores_gemma":[0.01261685,0.0002022347,0.00006268541,0.000694217,0.0007299502,0.0007639276,0.00005376095,0.0002266246,0.00002951179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004478049,"about_ca_system_score_gemma":0.001052972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003002835,"about_ca_topic_score_gemma":0.009076363,"domain_scores_codex":[0.997493,0.001012745,0.0004700721,0.0005042619,0.0001730039,0.000346867],"domain_scores_gemma":[0.9889612,0.008825212,0.0006357384,0.0003764282,0.001116983,0.00008444265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00202249,0.002851937,0.1264749,0.0001649844,0.0002462204,7.938497e-7,0.02902365,0.009002418,0.2199678,0.4556239,0.003844283,0.1507766],"study_design_scores_gemma":[0.0008542067,0.0005626815,0.6760671,0.0002251207,0.0001005717,0.00000117186,0.009569643,0.001736176,0.001044128,0.3015221,0.007926222,0.0003908861],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5300092,0.0001811537,0.4659618,0.0007703828,0.001423496,0.00110898,0.0001615783,0.00007518556,0.0003082655],"genre_scores_gemma":[0.7187914,0.0003498458,0.279192,0.0002177,0.00053521,0.0003996371,0.0002963028,0.00002120355,0.0001967174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5495921,"threshold_uncertainty_score":0.9957003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1155585495440885,"score_gpt":0.4424690047889706,"score_spread":0.326910455244882,"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."}}