{"id":"W2965434934","doi":"10.5539/ies.v12n8p59","title":"Detecting Gender Differences in PISA 2012 Mathematics Test with Differential Item Functioning","year":2019,"lang":"en","type":"article","venue":"International Education Studies","topic":"Education, Achievement, and Giftedness","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Differential item functioning; Context (archaeology); Logistic regression; Item response theory; Multilevel model; Test (biology); Sample (material); Test validity; Construct validity; Construct (python library); Social psychology; Psychometrics; Developmental psychology; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001757609,0.0001803757,0.0002141854,0.0002804119,0.000107169,0.00006310156,0.0001926706,0.00005338357,0.001734209],"category_scores_gemma":[0.0002722706,0.000147348,0.0000384829,0.0002050262,0.00006462126,0.0002368758,0.00004274934,0.0001630176,0.0002434407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001452895,"about_ca_system_score_gemma":0.00009874131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001209943,"about_ca_topic_score_gemma":0.0002578093,"domain_scores_codex":[0.9987656,0.00004792084,0.0003633215,0.0003311332,0.0002845054,0.0002074926],"domain_scores_gemma":[0.9982741,0.000655057,0.0002434125,0.0002079945,0.0005806306,0.00003875352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002074601,0.0008164913,0.9768503,0.00004181764,0.0002421077,3.499769e-7,0.01490739,0.00000333954,0.0001166295,0.003895985,0.001109685,0.001995153],"study_design_scores_gemma":[0.0004998671,0.00006475676,0.9246046,0.0001314995,0.00003106366,0.0000100125,0.07179026,0.0000352922,0.00004488358,0.001151066,0.001435953,0.0002007517],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97643,0.0005993077,0.0005989036,0.0004956067,0.009284223,0.0002398412,0.00000515402,0.00004579495,0.01230119],"genre_scores_gemma":[0.9797525,0.00004238761,0.0006148648,0.0001606244,0.0004795424,0.0002258986,0.00002406591,0.0000202087,0.01867986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05688287,"threshold_uncertainty_score":0.9991783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09779288800822464,"score_gpt":0.3959092010579396,"score_spread":0.298116313049715,"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."}}