{"id":"W4407098810","doi":"10.1080/15434303.2025.2455196","title":"Differential Item Functioning Due to Cultural Familiarity on a Large-Scale Reading Test: Does the Length of Residence Matter?","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Differential item functioning; Psychology; Reading (process); Scale (ratio); Test (biology); Residence; Item response theory; Psychometrics; Developmental psychology; Linguistics; Geography; Sociology; Demography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002635869,0.0001976091,0.0004161496,0.000381679,0.0003488715,0.0004043621,0.0008954201,0.0000760258,0.0004235713],"category_scores_gemma":[0.006917705,0.00009908403,0.0001464125,0.001785621,0.0000580519,0.0002242498,0.0001269074,0.0003146392,0.00004380498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006266213,"about_ca_system_score_gemma":0.00003928794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003421109,"about_ca_topic_score_gemma":0.0001998626,"domain_scores_codex":[0.9967728,0.0006052325,0.0007084486,0.0005900934,0.0009425812,0.000380809],"domain_scores_gemma":[0.9796287,0.01891887,0.0003037312,0.0008863478,0.0001903543,0.00007202741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009287456,0.0002988652,0.710614,0.00004427918,0.00006531377,0.00003628416,0.01502431,0.00003176865,0.02495592,0.002064525,0.01152146,0.2352504],"study_design_scores_gemma":[0.0003476424,0.0004401426,0.934936,0.0001673914,0.00002672681,0.000005533338,0.05745522,0.002297265,0.00114404,0.002765784,0.0002525607,0.0001616946],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9002083,0.0000388525,0.08772122,0.00143408,0.0008612484,0.0002754668,0.00002986952,0.00005955232,0.009371401],"genre_scores_gemma":[0.9884573,0.000001683877,0.007358666,0.0005704284,0.0001180259,0.00003359832,0.000003722086,0.000007793355,0.003448737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2350887,"threshold_uncertainty_score":0.8281639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07156230965493464,"score_gpt":0.4314743672554329,"score_spread":0.3599120576004983,"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."}}