{"id":"W2745464303","doi":"10.1177/0146621617726788","title":"Using Automatic Item Generation to Create Solutions and Rationales for Computerized Formative Testing","year":2017,"lang":"en","type":"article","venue":"Applied Psychological Measurement","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Computer science; Item bank; Computerized adaptive testing; Test (biology); Quality (philosophy); Item response theory; Psychometrics; Psychology; Mathematics education","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001060076,0.0001374374,0.000177122,0.00004970345,0.001306019,0.0003664051,0.0003504722,0.00004791889,0.000002145619],"category_scores_gemma":[0.0002930706,0.0001128313,0.00003472512,0.00005602745,0.00003046303,0.0001925665,0.0001421016,0.00007154422,0.00001029962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008550854,"about_ca_system_score_gemma":0.0000164059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008349119,"about_ca_topic_score_gemma":0.000002219281,"domain_scores_codex":[0.99875,0.0000487695,0.0002787464,0.0003718559,0.000292753,0.0002578465],"domain_scores_gemma":[0.9990312,0.0001018478,0.0002170621,0.0003352784,0.0002271099,0.00008742941],"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":[0.00002282412,0.0001742294,0.0003611541,0.00005576481,0.00007530279,0.000002352088,0.001489637,0.003588975,0.3189853,0.5180908,0.0004915687,0.156662],"study_design_scores_gemma":[0.001391442,0.0004830671,0.04520983,0.0002473838,0.00002681812,0.0000240407,0.00009057285,0.9371367,0.004553573,0.005508154,0.004722164,0.0006062655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07323544,0.00002677239,0.9243351,0.0003514246,0.0003149278,0.0006929854,0.000001462312,0.00009359196,0.000948355],"genre_scores_gemma":[0.7137338,6.211527e-7,0.2858119,0.0001635493,0.000145537,0.0001183405,9.078199e-7,0.000004666539,0.00002068456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9335477,"threshold_uncertainty_score":0.9999942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.534223811307965,"score_gpt":0.385328940422152,"score_spread":0.148894870885813,"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."}}