{"id":"W3108940771","doi":"10.4018/978-1-7998-3473-1.ch019","title":"Automating the Generation of Test Items","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in logistics, operations, and management science book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Computer science; Domain (mathematical analysis); Data science; Machine learning; Artificial intelligence; Information retrieval; Mathematics","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":[0.004757171,0.001448902,0.001038391,0.002302605,0.0005847151,0.002433091,0.002321342,0.00115092,0.0242942],"category_scores_gemma":[0.02832351,0.0006850248,0.0006666502,0.002575162,0.0004995217,0.001669758,0.001627604,0.001464252,0.02236466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009156714,"about_ca_system_score_gemma":0.001698728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002444456,"about_ca_topic_score_gemma":0.003103977,"domain_scores_codex":[0.9960622,0.001796418,0.0002176832,0.0004511364,0.001368076,0.0001044089],"domain_scores_gemma":[0.9833483,0.01114072,0.0003498081,0.001622765,0.003357852,0.0001805013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006839673,0.0001702059,0.0012945,0.0003688332,0.00001198158,0.0001191648,0.000843614,0.004441942,0.007545579,0.006238141,0.03340376,0.945494],"study_design_scores_gemma":[0.0002337069,0.0008204688,0.0132628,0.001234081,0.0001029123,0.001900318,0.002253553,0.2159186,0.07860183,0.06274243,0.6226789,0.0002504201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02680753,0.0008395455,0.8716841,0.001004772,0.000668494,0.003095357,0.002216419,0.02023375,0.07345003],"genre_scores_gemma":[0.03362925,0.0006548705,0.9292161,0.0003138467,0.00008069904,0.001522199,0.003220675,0.001452536,0.02990984],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0242942,"threshold_uncertainty_score":0.08127218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04221560599566671,"score_gpt":0.3313379888908244,"score_spread":0.2891223828951577,"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."}}