{"id":"W2148623326","doi":"10.1111/j.1365-2923.2012.04289.x","title":"Using automatic item generation to create multiple‐choice test items","year":2012,"lang":"en","type":"article","venue":"Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":142,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Multiple choice; Licensure; Item bank; Context (archaeology); Test (biology); Certification; Item response theory; Process (computing); Artificial intelligence; Machine learning; Information retrieval; Psychometrics; Psychology; Medical education; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00754963,0.0001246295,0.0002251578,0.0004737624,0.0002038713,0.0001623564,0.0004606701,0.0001244467,0.001159293],"category_scores_gemma":[0.7219349,0.00009067009,0.00005444048,0.002072776,0.00004246828,0.0003726033,0.00008944729,0.0001521877,0.0002914871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110577,"about_ca_system_score_gemma":0.0003857977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002472663,"about_ca_topic_score_gemma":0.00002085687,"domain_scores_codex":[0.9965877,0.0004326976,0.0006803739,0.0003338678,0.001597364,0.0003680128],"domain_scores_gemma":[0.9350457,0.06236453,0.0004350242,0.0008124126,0.0004866867,0.0008556939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[9.746194e-7,0.0002211427,0.5474888,0.00000503039,0.000002998182,1.962555e-7,0.0005292401,0.00002301638,0.001626257,0.00004544527,0.02773917,0.4223177],"study_design_scores_gemma":[0.000226101,0.00005248256,0.6983389,0.000073954,0.00001679217,0.00003385551,0.0006942624,0.2327972,0.0004955762,0.0003688578,0.06666813,0.0002338725],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9412984,0.0003112696,0.04952989,0.002484786,0.004477044,0.0002246369,0.000001650563,0.00007547002,0.0015969],"genre_scores_gemma":[0.9324903,0.00000447327,0.06168871,0.002929274,0.002228603,0.0000310311,0.000007089678,0.00001155873,0.0006089523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7143853,"threshold_uncertainty_score":0.9997538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6054844956655376,"score_gpt":0.5574866617688159,"score_spread":0.04799783389672174,"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."}}