{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004197607,0.0004385255,0.0005136472,0.002126687,0.0002538435,0.0004770815,0.0003615256,0.0004088431,0.002308265],"category_scores_gemma":[0.02346321,0.0001415476,0.0002501104,0.0006435522,0.0004145152,0.0006743759,0.0008928257,0.0002927855,0.0006952288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002153018,"about_ca_system_score_gemma":0.0002345713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000825816,"about_ca_topic_score_gemma":0.001021811,"domain_scores_codex":[0.9967794,0.001140329,0.0003973177,0.0004726474,0.0009155609,0.0002947316],"domain_scores_gemma":[0.989696,0.005078263,0.002772511,0.0007020321,0.001416603,0.0003345681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003317884,0.00006697396,0.958778,0.0000435657,0.0000253142,0.0003661271,0.002225797,0.00006139737,0.006874078,0.000214825,0.0002320863,0.03077987],"study_design_scores_gemma":[0.00001548311,0.0003453875,0.9882373,0.00003199689,0.00001686906,0.001927102,0.001709778,0.0005375192,0.005742362,0.0004719582,0.0009446102,0.00001970403],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978821,0.0001008093,0.0009363948,0.00002058168,0.0000116702,0.00001714932,0.0001075148,0.000006380681,0.0009174535],"genre_scores_gemma":[0.9988509,0.00003243821,0.0006460841,0.00002700568,0.000005862157,0.00001918486,0.0001299888,0.000004875468,0.0002836185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004197607,"threshold_uncertainty_score":0.02219933,"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."}}