{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001449359,0.00006509935,0.0001181128,0.0003777612,0.00003464736,0.00002052618,0.00003643392,0.00005571949,0.00001563235],"category_scores_gemma":[0.00008462831,0.00006621752,0.00001373491,0.0002471688,0.00001996678,0.00004927502,0.00001018965,0.0001187514,6.513984e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002277367,"about_ca_system_score_gemma":0.0000674386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003038042,"about_ca_topic_score_gemma":0.00001710416,"domain_scores_codex":[0.9993669,0.00006971038,0.0002407533,0.0001695315,0.000050448,0.0001026228],"domain_scores_gemma":[0.9997579,0.00003861589,0.00006778604,0.00008257732,0.00003753707,0.000015612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004492511,0.0001564073,0.7715822,0.00005072817,0.0000236403,3.976757e-7,0.00977927,0.00001013779,0.0007507795,0.001448179,0.001539472,0.2146138],"study_design_scores_gemma":[0.0003204995,0.00001776794,0.9868646,0.0001955623,0.00001151004,0.000001266407,0.007903377,0.0006484408,0.00021636,0.0007635834,0.002989088,0.00006791008],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662358,0.0004340159,0.01404009,0.00004745866,0.009549482,0.0001318204,4.225351e-7,0.00001138839,0.009549575],"genre_scores_gemma":[0.9947732,0.00002431585,0.002807558,0.00002096732,0.00006723812,0.00005883866,0.00001410309,0.000003941623,0.002229855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2152824,"threshold_uncertainty_score":0.2700272,"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."}}