{"id":"W3033267246","doi":"10.3389/fpsyg.2020.01088","title":"Using Corpus Analyses to Help Address the DIF Interpretation: Gender Differences in Standardized Writing Assessment","year":2020,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Gender Studies in Language","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Psychology; Differential item functioning; Test (biology); Interpretation (philosophy); Spelling; Boston Naming Test; Cognitive psychology; Interpretability; Linguistics; Cognition; Developmental psychology; Psychometrics; Item response theory","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":[0.04571695,0.0008668797,0.0009894393,0.00612877,0.001670736,0.002399488,0.001029657,0.0006365909,0.006056078],"category_scores_gemma":[0.1828847,0.0004477066,0.0007441881,0.00450587,0.001634751,0.00161831,0.003499549,0.0009949816,0.0008010383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009726314,"about_ca_system_score_gemma":0.0008963763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001778844,"about_ca_topic_score_gemma":0.003952198,"domain_scores_codex":[0.9637862,0.01975976,0.005959453,0.003640537,0.006294394,0.0005596498],"domain_scores_gemma":[0.7969455,0.1549593,0.0120254,0.01678593,0.01864226,0.0006415102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001981686,0.000757275,0.5179613,0.002374828,0.0008416615,0.00158152,0.05160063,0.001715095,0.02984635,0.01515345,0.01050235,0.3656839],"study_design_scores_gemma":[0.0002443751,0.001400296,0.9137993,0.0006148001,0.0003936054,0.001335107,0.01146784,0.01307523,0.0180028,0.0113011,0.02817308,0.0001924561],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8761943,0.0008937401,0.09924936,0.0004176729,0.0005420301,0.002965361,0.003021532,0.0004323706,0.01628362],"genre_scores_gemma":[0.9079565,0.0003128029,0.07945742,0.0002647907,0.0001620577,0.006317787,0.003030446,0.0002941683,0.002204094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04571695,"threshold_uncertainty_score":0.2417772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1870382146697567,"score_gpt":0.4757906005330269,"score_spread":0.2887523858632702,"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."}}