{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003283558,0.0001712687,0.0001679814,0.0001269849,0.0007569516,0.0004306865,0.0001187387,0.00003516833,0.0003042379],"category_scores_gemma":[0.0001429073,0.0001544034,0.00004287659,0.00004956797,0.00003298739,0.0001479602,0.0000345337,0.0003789527,0.00004515198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006243904,"about_ca_system_score_gemma":0.000017979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002071881,"about_ca_topic_score_gemma":0.0001009964,"domain_scores_codex":[0.9988267,0.000133504,0.0002173383,0.0002979494,0.0002178588,0.0003066141],"domain_scores_gemma":[0.9993432,0.0002398286,0.00009873646,0.0002019359,0.00004080019,0.00007556553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00006704642,0.001330337,0.03656032,0.0003391904,0.000110818,0.0001342017,0.3439125,0.0116457,0.03161876,0.4849252,0.004294096,0.0850618],"study_design_scores_gemma":[0.005339117,0.003028467,0.1635192,0.002937029,0.0004675487,0.000197098,0.3803941,0.3092317,0.001603548,0.001251674,0.1260356,0.005994899],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6617964,0.00001896131,0.001521015,0.00001865965,0.0002064411,0.00009409395,0.000003259159,0.0004304296,0.3359108],"genre_scores_gemma":[0.9885792,3.62004e-8,0.003605275,0.0002652948,0.001968866,0.0000223817,0.00005916184,0.00004007219,0.005459712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4836735,"threshold_uncertainty_score":0.6296386,"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."}}