{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004427779,0.002906287,0.001414557,0.00476334,0.001114404,0.003293508,0.002702979,0.001554474,0.0227703],"category_scores_gemma":[0.01935514,0.001445008,0.001845775,0.002198736,0.0006362324,0.002343685,0.002935116,0.001659952,0.01239387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103349,"about_ca_system_score_gemma":0.00257905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003914359,"about_ca_topic_score_gemma":0.003801212,"domain_scores_codex":[0.9974032,0.0006367149,0.0003666031,0.0005123042,0.0009236667,0.0001575631],"domain_scores_gemma":[0.9838135,0.00868952,0.0005090768,0.002820724,0.003505738,0.0006613996],"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":[0.0008026866,0.00086565,0.00656352,0.000567941,0.0001069092,0.000907327,0.001020732,0.005889337,0.04306024,0.005078746,0.05291577,0.8822211],"study_design_scores_gemma":[0.0006815836,0.000737498,0.01260677,0.0007607637,0.0003743135,0.001931905,0.0009888406,0.4193433,0.3173515,0.05459692,0.1901242,0.0005024479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01015309,0.00008274438,0.867407,0.0001845947,0.000121528,0.001265717,0.002478574,0.1132681,0.00503868],"genre_scores_gemma":[0.04909147,0.00009741404,0.9246016,0.0001832454,0.00004685706,0.001221399,0.006750351,0.01008743,0.007920125],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0227703,"threshold_uncertainty_score":0.0761742,"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."}}