{"id":"W2548734396","doi":"10.5296/jei.v2i2.10040","title":"A Model-Based Method for Content Validation of Automatically Generated Test Items","year":2016,"lang":"en","type":"article","venue":"Journal of Educational Issues","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Computer science; Content (measure theory); Item bank; Item response theory; Information retrieval; Graph; Natural language processing; Artificial intelligence; Data mining; Statistics; Mathematics; Theoretical computer science; Psychometrics","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":[0.0006671478,0.00006900712,0.0001721491,0.0001270039,0.00003123349,0.00003722453,0.0003548032,0.0000335449,0.00002546999],"category_scores_gemma":[0.001098602,0.00004492217,0.00008481684,0.00009245256,0.00001730808,0.0003171957,0.00001723075,0.00003507237,0.00000225255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005926851,"about_ca_system_score_gemma":0.000544277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006439076,"about_ca_topic_score_gemma":7.184324e-7,"domain_scores_codex":[0.9989474,0.00004874999,0.000525123,0.0001089381,0.0002736522,0.00009610408],"domain_scores_gemma":[0.9970945,0.001125624,0.0004269882,0.0001683823,0.001118219,0.00006631412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005837587,0.001262637,0.005388397,0.0001296576,0.0001435823,0.000001042469,0.001679373,0.07699293,0.6151761,0.255651,0.007675134,0.03584174],"study_design_scores_gemma":[0.0004867128,0.0001358006,0.0006685535,0.0001279664,0.00001575063,0.000009432768,0.00001455882,0.8826737,0.0844122,0.03102555,0.0003532015,0.00007651441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04623873,0.0001330415,0.9264815,0.02673742,0.0002693044,0.0000906866,0.000004645475,0.000006621184,0.00003809362],"genre_scores_gemma":[0.4000502,0.000003150529,0.5993172,0.0001020402,0.0001651557,0.000005967077,8.379855e-7,0.000003506555,0.0003520244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8056808,"threshold_uncertainty_score":0.1831873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1028713208901992,"score_gpt":0.3784143698961985,"score_spread":0.2755430490059992,"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."}}