{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00339711,0.001433289,0.0006135634,0.004430144,0.001902354,0.001837545,0.002456228,0.002762815,0.01314757],"category_scores_gemma":[0.01801175,0.000335329,0.0008333971,0.002877649,0.001124415,0.002127714,0.003801909,0.002164404,0.01376067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00126062,"about_ca_system_score_gemma":0.002310661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01249941,"about_ca_topic_score_gemma":0.03894098,"domain_scores_codex":[0.9964283,0.001013107,0.0003979013,0.0009967312,0.0009422227,0.0002217013],"domain_scores_gemma":[0.9864219,0.004602089,0.0009676633,0.004344279,0.003053054,0.0006109888],"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":[0.000493522,0.0003095897,0.0129038,0.00169255,0.0001173972,0.0007301946,0.001561975,0.003258184,0.01009178,0.00664007,0.8513694,0.1108314],"study_design_scores_gemma":[0.000250658,0.0001597205,0.02973728,0.0005306249,0.000080597,0.0009692956,0.001364619,0.01602401,0.01132543,0.008966515,0.9303983,0.0001928679],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.05307277,0.002352957,0.05489219,0.002289352,0.00174449,0.001099236,0.8300685,0.02215742,0.03232316],"genre_scores_gemma":[0.04188246,0.0003239726,0.05323995,0.0005812884,0.0001890684,0.00138865,0.8911054,0.001655426,0.009633777],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01314757,"threshold_uncertainty_score":0.04398298,"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."}}