{"id":"W4387704250","doi":"10.31234/osf.io/tbuqh","title":"Extracting Intersectional Stereotypes from Static and Contextualized Embeddings","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Gender Studies in Language","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"Social Sciences and Humanities Research Council of Canada; National Institute of Standards and Technology","keywords":"Intersectionality; Trait; Race (biology); Sociology; Social psychology; Psychology; Gender studies; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009452929,0.00110288,0.0003319732,0.002402534,0.000493072,0.001442116,0.0004072692,0.0006760484,0.004485224],"category_scores_gemma":[0.005866042,0.0003219785,0.0007669273,0.001954474,0.0005149647,0.002562843,0.001798598,0.001003524,0.003706444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004620983,"about_ca_system_score_gemma":0.0006915926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001617556,"about_ca_topic_score_gemma":0.004796342,"domain_scores_codex":[0.9989403,0.0003145273,0.0001431161,0.0003342747,0.0001741858,0.00009357729],"domain_scores_gemma":[0.9976951,0.001284811,0.0001703129,0.0003336852,0.0004594115,0.00005658775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008191218,0.0003191448,0.07608506,0.003132676,0.0003491371,0.001156078,0.01432785,0.01126343,0.06495678,0.02187215,0.06607507,0.7396435],"study_design_scores_gemma":[0.0002177512,0.0006550025,0.1246791,0.001142753,0.0005028205,0.002918621,0.04586985,0.3701031,0.0526658,0.09913418,0.3017479,0.000363028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5673746,0.00164832,0.3294048,0.0007474356,0.001052653,0.00058655,0.07193658,0.008568382,0.01868073],"genre_scores_gemma":[0.7357149,0.0004437313,0.1898493,0.0001389346,0.0001258977,0.0006128802,0.0681172,0.000864269,0.004132994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004485224,"threshold_uncertainty_score":0.01500458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09895464011811923,"score_gpt":0.3954250124716029,"score_spread":0.2964703723534837,"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."}}