{"id":"W2562551526","doi":"10.1111/emip.12129","title":"A Process for Reviewing and Evaluating Generated Test Items","year":2016,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test (biology); Process (computing); Subject-matter expert; Quality (philosophy); Domain (mathematical analysis); Computerized adaptive testing; Item bank; Item response theory; Data science; Artificial intelligence; Psychometrics; Expert system; Mathematics; Statistics; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003246549,0.00009676581,0.0001053364,0.00003632392,0.0002495731,0.0001710147,0.0001140323,0.00002275727,0.000009624368],"category_scores_gemma":[0.009328654,0.00006709971,0.00001601981,0.00008805052,0.00001386406,0.0007657589,0.00002769258,0.00004599572,0.000008729598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004630772,"about_ca_system_score_gemma":0.0001366717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002792605,"about_ca_topic_score_gemma":0.000001093036,"domain_scores_codex":[0.9988226,0.0001487449,0.0002040837,0.000292691,0.0003856871,0.0001461568],"domain_scores_gemma":[0.9972374,0.001422132,0.0001765302,0.0001206002,0.0009836692,0.00005967383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009147698,0.0005360389,0.01147234,0.001007356,0.0002389004,0.000002162071,0.01161925,0.00007867711,0.1559656,0.4058563,0.004294302,0.4088376],"study_design_scores_gemma":[0.0005587229,0.0004486511,0.00405378,0.00157576,0.00006164302,0.0000992026,0.0006378458,0.002302137,0.004046478,0.003634486,0.9821467,0.0004346101],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03711686,0.08924071,0.5798398,0.2832959,0.003176091,0.002820685,0.000009729967,0.000214437,0.004285828],"genre_scores_gemma":[0.9344079,0.0007348306,0.05617469,0.0006895736,0.001398982,0.0002653913,0.000001931473,0.00001875436,0.006307872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9778524,"threshold_uncertainty_score":0.9990162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2464384762232207,"score_gpt":0.4293302723194807,"score_spread":0.18289179609626,"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."}}