{"id":"W4283452889","doi":"10.1145/3501247.3531540","title":"On the Characteristics of Ranking-based Gender Bias Measures","year":2022,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Gender bias; Consistency (knowledge bases); Computer science; Robustness (evolution); Ranking (information retrieval); Measure (data warehouse); Data science; Machine learning; Artificial intelligence; Cognitive psychology; Data mining; Psychology; Social psychology","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":[0.05353999,0.0009632041,0.001101666,0.006699835,0.001383909,0.003964772,0.00105291,0.001575801,0.002881788],"category_scores_gemma":[0.2709543,0.000389566,0.0007743384,0.00581079,0.002515318,0.007110163,0.002693082,0.001899345,0.001074579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001930946,"about_ca_system_score_gemma":0.00135365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001723405,"about_ca_topic_score_gemma":0.001829855,"domain_scores_codex":[0.9499997,0.02659507,0.003479001,0.003531015,0.01527358,0.001121609],"domain_scores_gemma":[0.6149229,0.3110254,0.020745,0.02473148,0.02630437,0.002270753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001678598,0.0005055089,0.1702963,0.001680761,0.0008026107,0.0002326307,0.004756506,0.02225715,0.02137986,0.1348727,0.008464301,0.633073],"study_design_scores_gemma":[0.0002383294,0.004009112,0.2508205,0.001382294,0.0006885094,0.00294271,0.004537623,0.2199776,0.03676824,0.432735,0.04497849,0.0009216332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4699576,0.01467304,0.4592728,0.004919975,0.0005563435,0.000958689,0.002167892,0.001462927,0.04603073],"genre_scores_gemma":[0.8963414,0.0009235637,0.09871145,0.0005795042,0.0002381206,0.0003161063,0.0008843744,0.0003165869,0.001688935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05353999,"threshold_uncertainty_score":0.2831499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1026640627976753,"score_gpt":0.2645292449843555,"score_spread":0.1618651821866802,"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."}}