{"id":"W2142413505","doi":"10.1080/15305058.2011.635830","title":"The Role of Item Models in Automatic Item Generation","year":2012,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Item bank; Item response theory; Field (mathematics); Process (computing); Task (project management); Item analysis; Artificial intelligence; Machine learning; Psychometrics; Psychology","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":[0.1279199,0.002776089,0.00282673,0.008547199,0.001303519,0.008516186,0.005290098,0.002853358,0.004128389],"category_scores_gemma":[0.418778,0.002515118,0.002862836,0.008665964,0.004301609,0.01465584,0.00476228,0.007323967,0.002568312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003782161,"about_ca_system_score_gemma":0.003877409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0025931,"about_ca_topic_score_gemma":0.002607672,"domain_scores_codex":[0.8342605,0.1430801,0.004869926,0.004279421,0.01280252,0.0007074144],"domain_scores_gemma":[0.5033818,0.4442065,0.006742728,0.02469528,0.02012955,0.0008440106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000395873,0.0005847348,0.0231175,0.00175484,0.001287175,0.000244258,0.005975557,0.06319576,0.001612983,0.2520176,0.0108443,0.6389694],"study_design_scores_gemma":[0.0002815787,0.0004358502,0.007168454,0.001271338,0.0003344533,0.0004171213,0.001044127,0.5068424,0.003528201,0.4621869,0.01610634,0.000383202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006905769,0.000599454,0.9866475,0.0008926291,0.00009327484,0.0008523762,0.0002101879,0.001167729,0.002631098],"genre_scores_gemma":[0.09355135,0.0006672812,0.9005472,0.0004997245,0.0001000172,0.002896419,0.000587077,0.000459108,0.0006918836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1279199,"threshold_uncertainty_score":0.676513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05584327543240598,"score_gpt":0.2802359057096199,"score_spread":0.224392630277214,"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."}}