{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01408432,0.0005070386,0.0005269156,0.001544476,0.000669659,0.001224308,0.0009580818,0.0005282943,0.001098979],"category_scores_gemma":[0.06694912,0.000184333,0.0008161954,0.001377239,0.001339086,0.001111742,0.001069905,0.0006815896,0.0002489616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00137022,"about_ca_system_score_gemma":0.001496205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0226352,"about_ca_topic_score_gemma":0.06294477,"domain_scores_codex":[0.9909858,0.003205487,0.001009461,0.0008656328,0.003412416,0.0005212133],"domain_scores_gemma":[0.9428045,0.03120666,0.0134485,0.00376458,0.007078586,0.00169715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009315178,0.00003770415,0.9871761,0.00001846927,0.00007747139,0.00004917333,0.0007262327,0.0000811414,0.0004823262,0.0000477848,0.00006007154,0.0111505],"study_design_scores_gemma":[0.000005276985,0.0001780044,0.9977207,0.0000185831,0.00003263343,0.0001541004,0.000754178,0.0003507922,0.0005197769,0.00007934845,0.0001762188,0.00001031547],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977977,0.0001195137,0.001108883,0.00008706714,0.00000988499,0.00002937704,0.00007265891,0.000009353273,0.0007656211],"genre_scores_gemma":[0.9987018,0.00004126863,0.0009784529,0.00004114277,0.000008308337,0.0000192154,0.0001017489,0.000006024228,0.0001020883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0226352,"threshold_uncertainty_score":0.0744859,"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."}}