{"id":"W2418897741","doi":"10.55016/ojs/ajer.v59i4.55750","title":"Fairness in Computerized Testing: Detecting Item Bias using CATSIB with Impact Present","year":2014,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Item response theory; Item analysis; Applied psychology; Psychometrics; Statistics; Econometrics; Social psychology; Clinical psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.002043945,0.0001140641,0.0002463768,0.001010708,0.0002118349,0.0001865671,0.001281438,0.00006951373,0.00009881629],"category_scores_gemma":[0.009984024,0.00008291614,0.0000653576,0.002059103,0.000129025,0.0006674106,0.0002639651,0.0005888878,0.00001863974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002013765,"about_ca_system_score_gemma":0.001019046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002785939,"about_ca_topic_score_gemma":0.0006332041,"domain_scores_codex":[0.99786,0.0004401293,0.0004214798,0.000254474,0.0006206747,0.0004033076],"domain_scores_gemma":[0.9785753,0.01980799,0.0002724758,0.0004367036,0.0007481285,0.0001594307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001579664,0.0007645886,0.9506183,0.00004489489,0.0002092242,0.00001340992,0.001022724,0.007545436,0.004233772,0.01506105,0.0007448668,0.01958377],"study_design_scores_gemma":[0.002260994,0.001217324,0.4893355,0.0006017137,0.00004372211,0.001798316,0.0002771765,0.491522,0.002829779,0.008384161,0.001247656,0.0004817014],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975373,0.00008414044,0.01985024,0.003771992,0.000080614,0.00007761749,4.773372e-7,0.000002169696,0.0007597663],"genre_scores_gemma":[0.9735869,0.000003227725,0.02604883,0.0000253633,0.000167564,0.000003522447,0.00000146837,0.000007910648,0.0001552225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4839765,"threshold_uncertainty_score":0.9983553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1773974531280598,"score_gpt":0.4178530397295161,"score_spread":0.2404555866014563,"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."}}