{"id":"W1976267793","doi":"10.1177/0013164403258444","title":"Gender and Language Differences on the Test of Workplace Essential Skills: Using Overall Mean Scores and Item-Level Differential Item Functioning Analyses","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Teacher Professional Development and Motivation","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Differential item functioning; Numeracy; Test (biology); Reading (process); Developmental psychology; Item response theory; Psychometrics; Literacy; Pedagogy","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":[0.0004838303,0.0001087188,0.0001157545,0.00005359647,0.0004915512,0.00006474565,0.00007202834,0.00006442246,0.000199391],"category_scores_gemma":[0.0005960549,0.00006592368,0.00002498368,0.0001030429,0.0002244185,0.00007575598,0.00002655369,0.0001165686,9.33177e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005044953,"about_ca_system_score_gemma":0.0000796008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002053362,"about_ca_topic_score_gemma":0.00008583613,"domain_scores_codex":[0.9987746,0.0001567561,0.0001764327,0.000233948,0.0005190833,0.0001391212],"domain_scores_gemma":[0.9991607,0.0005110275,0.0001014227,0.00005840084,0.00009521063,0.00007325929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001520977,0.002075541,0.8533868,0.00005001372,0.0001697359,9.665102e-7,0.04369533,0.00001408316,0.03451672,0.05780593,0.0005275454,0.007605282],"study_design_scores_gemma":[0.0002893586,0.00004812151,0.989032,0.0001048417,0.00002083677,0.000001049148,0.00265304,0.00000409293,0.000212976,0.007512802,0.00002735957,0.00009350229],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955927,0.0003615846,0.0003098104,0.002415865,0.0002930521,0.0001673631,0.000004092966,0.00001003396,0.0008454802],"genre_scores_gemma":[0.9987563,0.00007638597,0.0004936008,0.0001836733,0.0002469142,0.00001325386,0.000004431136,0.000003555793,0.0002218392],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1356453,"threshold_uncertainty_score":0.3780665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2966988669348659,"score_gpt":0.4094511445808479,"score_spread":0.112752277645982,"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."}}