{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002093005,0.000214406,0.0002127943,0.0001760107,0.0002335,0.00006526673,0.0008504333,0.0001676298,0.0009753447],"category_scores_gemma":[0.000009158129,0.0002196729,0.0001047157,0.00001943978,0.00004725754,0.00009351575,0.0003781465,0.0004361996,0.0001873234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001660247,"about_ca_system_score_gemma":0.000287169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.188979e-7,"about_ca_topic_score_gemma":0.000002387929,"domain_scores_codex":[0.9987665,0.00002618706,0.0002826066,0.0004280107,0.0003364456,0.0001602278],"domain_scores_gemma":[0.9989043,0.00006037101,0.0001970974,0.0007441306,0.00004605763,0.00004796758],"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":[6.669325e-8,0.000004601585,9.613605e-7,0.00000768305,0.0000186228,0.00000653052,0.00004982775,5.867888e-7,0.000009335198,0.4339194,0.0005617198,0.5654207],"study_design_scores_gemma":[0.00005217589,0.00003645469,0.00001346598,0.00003126452,0.00001598285,0.00002555948,0.000002187666,0.001626958,0.0000422078,0.06444276,0.9334857,0.0002252398],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00004857478,0.0004465651,0.000468195,0.00112026,0.001082635,0.0002672406,0.000005004128,0.0003151961,0.9962463],"genre_scores_gemma":[0.0008775386,0.00002886426,0.01183077,0.0006064211,0.0002279326,0.0001253028,0.00003288845,0.00002372063,0.9862466],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.932924,"threshold_uncertainty_score":0.9999379,"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."}}