{"id":"W6891601451","doi":"10.48448/adjb-gt22","title":"Biasly: An Expert-Annotated Dataset for Subtle Misogyny Detection and Mitigation","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Task (project management); Range (aeronautics); Binary number; Binary classification; Training set; Baseline (sea); Annotation","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000968262,0.0003806868,0.0002932305,0.001342393,0.0002357764,0.0004510199,0.0005055778,0.0002566146,0.0002796131],"category_scores_gemma":[0.0002533098,0.0003535584,0.00003621936,0.001289318,0.001173003,0.0005644719,0.0001387145,0.0002224494,0.001311814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002201288,"about_ca_system_score_gemma":0.0002979155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00103016,"about_ca_topic_score_gemma":0.005223128,"domain_scores_codex":[0.9972029,0.00005869941,0.0003146907,0.001285032,0.0006051388,0.0005335647],"domain_scores_gemma":[0.9986182,0.0000506172,0.0002331086,0.0006974613,0.0001389589,0.000261619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003372995,0.00009984677,0.000009203958,0.0001321459,0.00003882114,0.000007805095,0.0002733409,0.0000064111,0.1174274,0.0002215686,0.8638382,0.01791155],"study_design_scores_gemma":[0.0005208098,0.0002683752,0.00002850913,0.0001880014,0.00008102465,0.00003541949,0.0002408656,0.05525513,0.007444898,0.001319115,0.934015,0.0006028966],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.03774609,0.04850664,0.07637339,0.005120909,0.033009,0.03436652,0.5723531,0.0220245,0.1704999],"genre_scores_gemma":[0.1760514,0.0007612983,0.1181815,0.003120924,0.009075053,0.001734717,0.1472516,0.01233545,0.5314881],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.4251015,"threshold_uncertainty_score":0.9998916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04313064696090599,"score_gpt":0.357013826636822,"score_spread":0.3138831796759159,"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."}}