{"id":"W4309301527","doi":"10.1016/b978-0-12-818630-5.10026-0","title":"Automatic item generation","year":2022,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Template; Knowledge base; Test (biology); Artificial intelligence; Quality (philosophy); Natural language processing; Machine learning; Programming language","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":[0.001519272,0.002059152,0.001081375,0.003142282,0.0007547914,0.002298195,0.002306822,0.001353592,0.1777726],"category_scores_gemma":[0.004596874,0.0009222575,0.001291818,0.003273808,0.0004040402,0.002153781,0.002371369,0.001189865,0.1193605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003852985,"about_ca_system_score_gemma":0.0007340977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001592208,"about_ca_topic_score_gemma":0.001837991,"domain_scores_codex":[0.998831,0.000352978,0.00009265431,0.0002887364,0.0003410804,0.00009350774],"domain_scores_gemma":[0.9977609,0.000888865,0.00005190051,0.0005507413,0.0006793669,0.00006825961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001356115,0.00006289122,0.0003375826,0.000183442,0.00002707795,0.00009267149,0.00004638975,0.0007603121,0.007427718,0.002397655,0.07217335,0.9163553],"study_design_scores_gemma":[0.0002456602,0.0004725966,0.009238418,0.000634413,0.0002744914,0.003214989,0.0006358649,0.1631789,0.09610394,0.05800011,0.6677673,0.0002332919],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009213795,0.001218358,0.8291864,0.0004335736,0.0009629407,0.0005657839,0.00735002,0.07681122,0.07425798],"genre_scores_gemma":[0.04777804,0.0006622087,0.7949534,0.0003991425,0.0002094858,0.0006788493,0.0227532,0.004102852,0.1284629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1777726,"threshold_uncertainty_score":0.5947086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02558709402987739,"score_gpt":0.2669738738631309,"score_spread":0.2413867798332535,"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."}}