{"id":"W4392902227","doi":"10.32920/25418206.v1","title":"Exploration and Mitigation of Stereotypical Gender Biases in Information Retrieval Systems","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Relevance (law); Judgement; Ranking (information retrieval); Debiasing; Computer science; Information retrieval; Set (abstract data type); Artificial intelligence; Machine learning; 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":[0.01128296,0.000724746,0.000901545,0.001348142,0.00067676,0.001751108,0.001389866,0.001034843,0.001134681],"category_scores_gemma":[0.04399433,0.0003713093,0.0006915639,0.001045839,0.001021997,0.003238745,0.00207617,0.0009050494,0.0006859368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001148927,"about_ca_system_score_gemma":0.001559259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001879064,"about_ca_topic_score_gemma":0.002536997,"domain_scores_codex":[0.9887412,0.006411538,0.0007932057,0.001074076,0.002499679,0.0004802153],"domain_scores_gemma":[0.9813957,0.009570766,0.002035773,0.004073734,0.002630182,0.0002938432],"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":[0.001302244,0.0005255134,0.03070964,0.0008394676,0.0003330756,0.000239882,0.002246108,0.06548654,0.09519634,0.01217273,0.003016206,0.7879323],"study_design_scores_gemma":[0.0002160384,0.001953571,0.03078171,0.000185299,0.0002755084,0.0007089654,0.001446502,0.7458978,0.1491418,0.05654333,0.01264265,0.0002068935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5863096,0.002511183,0.4019083,0.001503582,0.0001085282,0.0003407606,0.0003296742,0.001833782,0.005154659],"genre_scores_gemma":[0.9101809,0.0003715484,0.08725049,0.0002934453,0.00007380385,0.0001453594,0.0003017065,0.00008911541,0.001293582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01128296,"threshold_uncertainty_score":0.05967075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08431150949639821,"score_gpt":0.2853085942659542,"score_spread":0.200997084769556,"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."}}