{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001123365,0.0000549732,0.00009084748,0.0001210565,0.00004866486,0.0000937959,0.000565279,0.00001937475,0.000001522759],"category_scores_gemma":[0.000806732,0.0000386334,0.00004654743,0.0001100318,0.000009873956,0.0007630216,0.00007615348,0.0001355219,0.000002585245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008477976,"about_ca_system_score_gemma":0.00004694521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003488693,"about_ca_topic_score_gemma":0.000001858335,"domain_scores_codex":[0.9988478,0.00007309751,0.0004880591,0.00005200132,0.0004131384,0.0001258494],"domain_scores_gemma":[0.9982786,0.000619226,0.0005416789,0.00007565037,0.000453362,0.00003143993],"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":[0.000005637917,0.0001025387,0.118131,0.000009463947,0.00008560302,0.00001707304,0.004145116,0.06390452,0.03249722,0.3308772,0.00004594932,0.4501787],"study_design_scores_gemma":[0.000101048,0.00003617009,0.006687047,0.0002224879,0.000002250874,0.0001477198,0.0001720109,0.9844022,0.004600285,0.002245387,0.001328538,0.00005486505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7609475,0.001763976,0.2330461,0.0002231673,0.001914477,0.00005622113,3.418423e-7,0.00001633788,0.002031922],"genre_scores_gemma":[0.9800276,0.000006450313,0.01930923,0.00001579494,0.0005468738,0.000001011035,1.110438e-7,0.000003748071,0.00008919115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9204977,"threshold_uncertainty_score":0.1575424,"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."}}