{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03824244,0.002680288,0.001050098,0.006609483,0.0009641433,0.003421476,0.003407287,0.001722362,0.008732769],"category_scores_gemma":[0.1745299,0.001339741,0.001476971,0.003413301,0.00147145,0.003256897,0.002550721,0.002802091,0.003484465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001415725,"about_ca_system_score_gemma":0.003650214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001046562,"about_ca_topic_score_gemma":0.001819351,"domain_scores_codex":[0.9654917,0.02233861,0.003349878,0.002096359,0.00639554,0.000327939],"domain_scores_gemma":[0.7930138,0.1456481,0.01069306,0.02288139,0.02685905,0.0009044861],"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":[0.0004369041,0.0007394668,0.003939663,0.0007960885,0.0001085711,0.0004281734,0.002001417,0.01368782,0.01278565,0.02358065,0.009504001,0.9319916],"study_design_scores_gemma":[0.001634482,0.00184272,0.005021922,0.001883539,0.0003433718,0.001926005,0.00153875,0.6633273,0.1029804,0.1355617,0.08314712,0.0007926568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005644991,0.00008036325,0.9853556,0.0002080049,0.0001048313,0.001533333,0.000271565,0.005596731,0.001204636],"genre_scores_gemma":[0.01960601,0.00006410777,0.9777033,0.00006526697,0.00003487245,0.00110317,0.0005033651,0.00040766,0.0005122962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03824244,"threshold_uncertainty_score":0.2022478,"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."}}