{"id":"W2166083835","doi":"10.1111/j.1745-3984.2001.tb01121.x","title":"Identifying Sources of Differential Item and Bundle Functioning on Translated Achievement Tests: A Confirmatory Analysis","year":2001,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; International Association for the Evaluation of Educational Achievement; University of Alberta","keywords":"Differential item functioning; Psychology; Categorization; Item analysis; Set (abstract data type); Achievement test; Test (biology); Item response theory; Social psychology; Standardized test; Mathematics education; Psychometrics; Developmental psychology; Computer science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007984227,0.0001530323,0.0003185724,0.0004542944,0.0001177871,0.00003856665,0.0001484054,0.00006511803,0.003709968],"category_scores_gemma":[0.00008939466,0.0001220973,0.0002025453,0.0004279836,0.00006406619,0.00009299398,0.000009012395,0.0002199711,0.00001475571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001175531,"about_ca_system_score_gemma":0.0001256486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003594412,"about_ca_topic_score_gemma":0.00001248289,"domain_scores_codex":[0.9977776,0.0002025134,0.000765374,0.0002061363,0.0008710651,0.0001773043],"domain_scores_gemma":[0.9982283,0.0002782333,0.0006548234,0.000143037,0.0005492137,0.0001464292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005123285,0.005390733,0.9758137,0.00003159089,0.00341109,0.000003238735,0.002754431,0.0001015901,0.004483393,0.004450032,0.001243605,0.001804268],"study_design_scores_gemma":[0.000835889,0.0004334509,0.9936495,0.00009764355,0.0005231142,0.00004271355,0.00116241,0.000007491401,0.0001037705,0.001342653,0.001685005,0.0001163467],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911334,0.001207251,0.0007280028,0.003457356,0.001278171,0.0001194905,0.000005399778,0.000004260842,0.002066663],"genre_scores_gemma":[0.9987305,0.00003428314,0.0001983477,0.0002078788,0.0003507569,0.000016782,0.000008495153,0.000008613352,0.0004443417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01783581,"threshold_uncertainty_score":0.9972008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1150924720928353,"score_gpt":0.3772707718796586,"score_spread":0.2621782997868233,"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."}}