{"id":"W2137984677","doi":"10.1177/0265532207071510","title":"A confirmatory approach to differential item functioning on an ESL reading assessment","year":2006,"lang":"en","type":"article","venue":"Language Testing","topic":"EFL/ESL Teaching and Learning","field":"Arts and Humanities","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Advanced Education","funders":"","keywords":"Differential item functioning; Psychology; Reading (process); Test (biology); Language proficiency; Item response theory; Flagging; Cognitive psychology; Psychometrics; Developmental psychology; Linguistics; Mathematics education","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.09328806,0.002526378,0.001445898,0.01143738,0.00257325,0.002925877,0.001870863,0.001022589,0.002979851],"category_scores_gemma":[0.2107984,0.0006834014,0.001965057,0.004800066,0.002223623,0.002750825,0.003253985,0.002722831,0.001002356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001960218,"about_ca_system_score_gemma":0.005023564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006755117,"about_ca_topic_score_gemma":0.0094355,"domain_scores_codex":[0.9245896,0.0522566,0.005226041,0.005923046,0.01100552,0.0009991938],"domain_scores_gemma":[0.7379405,0.1397043,0.0157613,0.03585742,0.06920537,0.001531087],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009849996,0.001035889,0.3387326,0.001720917,0.0009467673,0.001017255,0.03804481,0.003044474,0.01680476,0.07664543,0.006040409,0.5149817],"study_design_scores_gemma":[0.0008131514,0.006222638,0.4699576,0.00280176,0.002017147,0.004852135,0.04737697,0.1150345,0.04214418,0.2624544,0.04547226,0.0008532064],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1889524,0.0005467553,0.7808871,0.001841866,0.0002917139,0.005390795,0.0009454471,0.0009506812,0.02019334],"genre_scores_gemma":[0.5546777,0.0002023282,0.4369658,0.0005771914,0.00009771049,0.005045694,0.0008496309,0.0001162743,0.001467605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09328806,"threshold_uncertainty_score":0.4933603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04018946173988295,"score_gpt":0.2719887309013568,"score_spread":0.2317992691614739,"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."}}