{"id":"W2295035569","doi":"10.55612/s-5002-025-001","title":"Using Automated Processes to Generate Test Items And Their Associated Solutions and Rationales to Support Formative Feedback","year":2015,"lang":"en","type":"article","venue":"Interaction design & architecture(s)/ID&A Interaction design & architecture(s)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Computer science; Task (project management); Process (computing); Test (biology); Human–computer interaction; Mathematics education; Psychology; Programming language; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001741716,0.0009366187,0.0007826874,0.001485857,0.0009641049,0.001139619,0.0007318304,0.00024749,0.00004096893],"category_scores_gemma":[0.002663815,0.0008091072,0.0001368171,0.001399946,0.0001143353,0.001596269,0.0005015521,0.00105541,0.0001541417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007074727,"about_ca_system_score_gemma":0.0005742181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002691147,"about_ca_topic_score_gemma":0.0001362861,"domain_scores_codex":[0.9943335,0.001321286,0.001186364,0.001361543,0.0007338118,0.001063517],"domain_scores_gemma":[0.994004,0.002687404,0.0007669006,0.0005962842,0.001082708,0.0008627526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000605289,0.0003181339,0.000130505,0.00009953458,0.0003599686,0.00004120321,0.03882913,0.8267555,0.09228578,0.0005768505,0.006409057,0.03358911],"study_design_scores_gemma":[0.002647788,0.006601621,0.0009141137,0.002033141,0.0001675244,0.0046785,0.005042777,0.7462503,0.1102685,0.004336337,0.113339,0.003720296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02896291,0.0001662526,0.9645472,0.001524481,0.001509095,0.001885707,0.00005057212,0.001110681,0.0002431443],"genre_scores_gemma":[0.9000572,0.00001881175,0.09692968,0.001154749,0.0004820727,0.0003477038,0.00004846515,0.0001112549,0.0008500759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8710943,"threshold_uncertainty_score":0.9998973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1320321774201125,"score_gpt":0.3178800245209402,"score_spread":0.1858478471008276,"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."}}