{"id":"W2172179933","doi":"10.1111/emip.12018","title":"Instructional Topics in Educational Measurement (ITEMS) Module: Using Automated Processes to Generate Test Items","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Rendering (computer graphics); Test (biology); Item bank; Process (computing); Item response theory; Task (project management); Item analysis; Artificial intelligence; Machine learning; Information retrieval; Psychometrics; Programming language; Psychology; Engineering","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":[0.005031583,0.001070521,0.0005474714,0.001856008,0.0004977059,0.001512308,0.001335552,0.001194659,0.02158501],"category_scores_gemma":[0.01919198,0.0008545227,0.0007501835,0.0009415366,0.0004731563,0.001472497,0.001878991,0.00142514,0.01750212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005648952,"about_ca_system_score_gemma":0.001544012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001091625,"about_ca_topic_score_gemma":0.001401566,"domain_scores_codex":[0.9975373,0.001198069,0.0002367024,0.0002518396,0.000657219,0.0001188043],"domain_scores_gemma":[0.9869334,0.006942446,0.0005686068,0.002180225,0.002702805,0.0006725545],"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":[0.0003817324,0.001802305,0.009491461,0.0004965241,0.0000769431,0.0001753041,0.001218377,0.002551381,0.01267287,0.007427388,0.09966303,0.8640426],"study_design_scores_gemma":[0.001561973,0.005708791,0.1183729,0.0007482915,0.0002812652,0.001883644,0.00076236,0.09066774,0.1444751,0.04467592,0.5904215,0.0004405856],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06924645,0.0002848451,0.7959716,0.002282211,0.0007628268,0.01481042,0.008618278,0.05544643,0.05257688],"genre_scores_gemma":[0.05736214,0.0001836399,0.9038378,0.0005819811,0.0001705565,0.007491949,0.00381462,0.001873661,0.02468369],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02158501,"threshold_uncertainty_score":0.07220906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09722074847346185,"score_gpt":0.3606391693617605,"score_spread":0.2634184208882987,"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."}}