{"id":"W4413985408","doi":"10.3389/feduc.2025.1595658","title":"Detection of cultural and linguistic differential item functioning in reading assessment","year":2025,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Reading and Literacy Development","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reading (process); Linguistics; Differential item functioning; Computer science; Natural language processing; Differential (mechanical device); Psychology; Artificial intelligence; Engineering; Developmental psychology; Psychometrics; Item response theory; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03490157,0.0005954499,0.0006767126,0.004060132,0.0008635037,0.001705331,0.0007470787,0.0004692249,0.001050381],"category_scores_gemma":[0.08971119,0.000321515,0.001000525,0.003846417,0.001628519,0.001302089,0.002682903,0.0009747977,0.0003845402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128276,"about_ca_system_score_gemma":0.0009804968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003155204,"about_ca_topic_score_gemma":0.005963242,"domain_scores_codex":[0.9662838,0.02144226,0.003301703,0.002118632,0.005948184,0.0009054642],"domain_scores_gemma":[0.9486542,0.02919162,0.007879149,0.00598771,0.007573236,0.0007141084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002233474,0.00007415226,0.9302109,0.0001305362,0.0002194176,0.0001473299,0.00539274,0.0004216054,0.001080982,0.001002888,0.0003284141,0.06076759],"study_design_scores_gemma":[0.00001734707,0.0003010264,0.9870451,0.0001461548,0.00008169307,0.0004852325,0.004738758,0.002277861,0.001807093,0.001527597,0.001537358,0.00003476044],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9839336,0.0003579704,0.009674272,0.0001672862,0.00004474496,0.0001463329,0.0002017103,0.00004497126,0.005429086],"genre_scores_gemma":[0.9954097,0.00007179593,0.003908587,0.00005018497,0.000007280248,0.0001351189,0.0002227396,0.00001492309,0.0001797256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03490157,"threshold_uncertainty_score":0.1845794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01071442182995253,"score_gpt":0.3310993309938428,"score_spread":0.3203849091638903,"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."}}