{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02899567,0.002473033,0.001019283,0.004975563,0.001033255,0.004171585,0.002769847,0.001581398,0.005788904],"category_scores_gemma":[0.1651608,0.001044617,0.0009285649,0.002707643,0.001354247,0.004203952,0.003026868,0.002228276,0.003685252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080827,"about_ca_system_score_gemma":0.00295908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001344288,"about_ca_topic_score_gemma":0.001924509,"domain_scores_codex":[0.9678488,0.02067426,0.001785656,0.003081091,0.006276916,0.0003332076],"domain_scores_gemma":[0.747499,0.1856539,0.01107761,0.0334541,0.02108538,0.00123005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005267281,0.001601385,0.005800945,0.0004968083,0.0001480165,0.0002448357,0.004270862,0.00977934,0.02540005,0.009023967,0.00669478,0.9360123],"study_design_scores_gemma":[0.002428434,0.004993468,0.0252788,0.001071327,0.0004291051,0.001861789,0.003426374,0.5613951,0.193977,0.1226409,0.0815265,0.0009712074],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02646299,0.00007882938,0.9610217,0.0002217108,0.00005749926,0.002091913,0.0003275693,0.006577578,0.003160336],"genre_scores_gemma":[0.07666408,0.00006610037,0.9181778,0.00009926533,0.0000407718,0.00242778,0.000613771,0.000428653,0.001481666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02899567,"threshold_uncertainty_score":0.1533456,"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."}}