{"id":"W2920890361","doi":"10.1007/978-3-030-02242-6_3","title":"Creating Content for Educational Testing Using a Workflow That Supports Automatic Item Generation","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Workflow; Computer science; Scalability; Subject-matter expert; Test (biology); Process (computing); General partnership; Quality (philosophy); Software engineering; Knowledge management; Data science; Artificial intelligence; Database; Expert system; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004102294,0.000299557,0.0003725369,0.0003146412,0.0002226923,0.0001234348,0.0001697848,0.0004033482,0.0002165569],"category_scores_gemma":[0.001829139,0.0003212603,0.0001248593,0.0001883726,0.00002732642,0.0001299733,0.00001924957,0.0004645872,0.000005762468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000903793,"about_ca_system_score_gemma":0.001374639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002780907,"about_ca_topic_score_gemma":0.0003288645,"domain_scores_codex":[0.9982936,0.00002732938,0.0003915879,0.0003868069,0.0004205018,0.0004801555],"domain_scores_gemma":[0.9955339,0.003850999,0.0002107274,0.0001340673,0.000174072,0.000096172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003314485,0.0002517891,0.02885323,0.0008763322,0.000415028,0.00001640726,0.008355021,0.3070837,0.00827663,0.3836265,0.0003740482,0.2618382],"study_design_scores_gemma":[0.0003634465,0.00009600273,0.001430406,0.0007901263,0.0001300356,0.00001408966,0.00002067487,0.9720111,0.0001636481,0.01575971,0.008209282,0.001011417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06039055,0.008964161,0.8083811,0.006801267,0.0095114,0.008756503,0.00007961601,0.0008617142,0.09625367],"genre_scores_gemma":[0.8592411,0.00005458662,0.1144751,0.0003647342,0.006788097,0.0001475352,0.0003657233,0.0001830391,0.01838009],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7988505,"threshold_uncertainty_score":0.9999239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09761637458561982,"score_gpt":0.3381565497496243,"score_spread":0.2405401751640045,"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."}}