{"id":"W4412591596","doi":"10.1007/978-3-031-99267-4_11","title":"An Augmented Intelligence System for Automated Quality Control and Feedback Generation of Multiple Choice Test Items","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Multiple choice; Computer science; Control (management); Quality (philosophy); Artificial intelligence; Biology; Statistics; Mathematics; Botany","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":[0.001847943,0.00021014,0.0003574895,0.0006437522,0.0004779736,0.0005025166,0.001702219,0.0001270757,4.62927e-7],"category_scores_gemma":[0.0003393903,0.0002089757,0.00004333277,0.0002949531,0.0003489662,0.003399895,0.0005348188,0.0002166421,0.000002659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000158155,"about_ca_system_score_gemma":0.0002119903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001040411,"about_ca_topic_score_gemma":0.0000260256,"domain_scores_codex":[0.9980239,0.00007737936,0.00106694,0.0003296449,0.0003112881,0.0001909093],"domain_scores_gemma":[0.9955496,0.001441633,0.0006692691,0.001323533,0.0009364958,0.00007953779],"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":[0.000004611033,0.00003149959,0.0007144258,0.0003116316,0.00001404294,7.530774e-8,0.001430939,0.003270637,0.0003269087,0.9029406,0.00005495009,0.09089967],"study_design_scores_gemma":[0.0002818728,0.00009641994,0.001812299,0.0005494971,0.000006372946,0.000003884129,0.00005913038,0.9822528,0.0001487479,0.0001209646,0.01446677,0.0002012915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002590497,0.0002455322,0.9928845,0.0001323458,0.0003965481,0.0008138237,0.00005301687,0.0001935068,0.005021693],"genre_scores_gemma":[0.89698,0.0002497045,0.1012388,0.00018352,0.00006746256,0.00007644485,0.00008484754,0.000008982226,0.001110216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9789821,"threshold_uncertainty_score":0.8521781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07028701809007214,"score_gpt":0.3364495307656157,"score_spread":0.2661625126755435,"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."}}