{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006842522,0.00004490072,0.00005959357,0.0000619023,0.0001998781,0.00004254574,0.0005649954,0.000008950078,0.0005621157],"category_scores_gemma":[0.00006609657,0.00002678803,0.00004487201,0.000248935,0.00002135265,0.00006636937,0.0001285396,0.0001125995,0.00002402476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002054382,"about_ca_system_score_gemma":0.0000792547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007436597,"about_ca_topic_score_gemma":2.461985e-7,"domain_scores_codex":[0.9989842,0.00009382125,0.0001489005,0.0000684572,0.0006029222,0.0001016739],"domain_scores_gemma":[0.9994065,0.0001618745,0.00006353442,0.0002673657,0.00007893646,0.00002180035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005181766,0.0001876542,0.001794213,0.00001408126,0.00001360984,0.000006419579,0.001789549,0.000814233,0.0008122107,0.9559516,0.004956438,0.0336082],"study_design_scores_gemma":[0.002271455,0.001479547,0.1690468,0.0000194192,0.00002642828,0.00002159208,0.0006881599,0.6661963,0.06722881,0.01004685,0.08211726,0.0008573721],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5077716,0.000008174377,0.474131,0.003506106,0.0004942677,0.0003761435,0.00002449355,0.0001338693,0.01355436],"genre_scores_gemma":[0.9972681,3.318787e-7,0.0004419673,0.002040269,0.000005943443,0.00001382068,0.000002411201,0.00000180238,0.0002254005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9459047,"threshold_uncertainty_score":0.6154773,"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."}}