{"id":"W2943762082","doi":"10.3390/languages4020027","title":"Detection of Gender-Biased Items in the Peabody Picture Vocabulary Test","year":2019,"lang":"en","type":"article","venue":"Languages","topic":"Reading and Literacy Development","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université TÉLUQ","funders":"","keywords":"Peabody Picture Vocabulary Test; Psychology; Vocabulary; Differential item functioning; Test (biology); Gender bias; Developmental psychology; Competence (human resources); Item response theory; Item analysis; Social psychology; Psychometrics; Linguistics","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":[0.0002248594,0.00007194227,0.0001000333,0.00006933883,0.00001564569,0.00001163844,0.0001297057,0.00006373001,0.0003645909],"category_scores_gemma":[0.00003523236,0.00004696147,0.00003011982,0.0001399098,0.00001271276,0.00002567955,0.000009924363,0.0001311466,0.0001545177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001135355,"about_ca_system_score_gemma":0.000007138695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001849332,"about_ca_topic_score_gemma":0.00002569999,"domain_scores_codex":[0.9994035,0.00008649584,0.0001403816,0.0001362047,0.0001046925,0.00012866],"domain_scores_gemma":[0.9994487,0.0002098256,0.0000518281,0.0002635342,0.00001311298,0.00001302522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000786552,0.0004089644,0.6026474,0.0001181485,0.00007855799,0.0001401928,0.218851,0.00001776699,0.1393976,0.0006182696,0.002535158,0.03510822],"study_design_scores_gemma":[0.0005074807,0.00008885298,0.9694594,0.00002833036,0.000008045679,0.00003690798,0.01477744,0.00002881361,0.004157656,0.00005221762,0.01074607,0.0001088451],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730133,0.000681869,0.00004128141,0.00007519587,0.0002685752,0.000161274,0.000005136224,0.00002293046,0.02573044],"genre_scores_gemma":[0.9962118,0.000003317129,0.0000545544,0.0003054973,0.00007467761,0.0000159552,0.00001331598,0.000008341341,0.003312499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3668119,"threshold_uncertainty_score":0.3992014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01306313937856591,"score_gpt":0.2926822473427926,"score_spread":0.2796191079642267,"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."}}