{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1307608,0.003086408,0.002419316,0.01272528,0.004675223,0.006173004,0.005034926,0.002691991,0.01011174],"category_scores_gemma":[0.3377042,0.001743782,0.002165699,0.00519865,0.002771081,0.004597738,0.005206759,0.004426127,0.01290997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003643584,"about_ca_system_score_gemma":0.01619731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005471262,"about_ca_topic_score_gemma":0.007669582,"domain_scores_codex":[0.8578998,0.08629026,0.01208642,0.009734916,0.03284383,0.001144757],"domain_scores_gemma":[0.536819,0.1877406,0.02154977,0.07387221,0.1765254,0.003492941],"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":[0.0004582713,0.0007804504,0.003660817,0.001394822,0.0001793804,0.0006340074,0.01486677,0.002545926,0.03171945,0.009786946,0.04917552,0.8847978],"study_design_scores_gemma":[0.0008649774,0.003304507,0.03169724,0.004539728,0.000723179,0.00466403,0.01543386,0.07513206,0.1280334,0.06104523,0.6724061,0.002155732],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01446872,0.0005935131,0.9418218,0.001675414,0.0004850369,0.02336576,0.0007035795,0.01012747,0.006758645],"genre_scores_gemma":[0.01704044,0.0002385235,0.9703625,0.0002675521,0.0001590779,0.006242898,0.0006736696,0.0009776956,0.004037637],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1307608,"threshold_uncertainty_score":0.6915373,"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."}}