{"id":"W4327644549","doi":"10.1007/978-3-031-28238-6_24","title":"De-biasing Relevance Judgements for Fair Ranking","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Microsoft (Canada); University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Ranking (information retrieval); Judgement; Relevance (law); Computer science; Set (abstract data type); Artificial intelligence; Biasing; Gender bias; Process (computing); Machine learning; Information retrieval; Psychology; Social psychology; Voltage","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":[0.04927327,0.001844039,0.003444855,0.006000045,0.002579933,0.00554489,0.004229721,0.003493528,0.01084202],"category_scores_gemma":[0.2065042,0.001159446,0.002125985,0.005567659,0.003185406,0.007677005,0.006115421,0.006035007,0.004388251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002308491,"about_ca_system_score_gemma":0.003143532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001707577,"about_ca_topic_score_gemma":0.003594841,"domain_scores_codex":[0.934287,0.04035386,0.003818741,0.005249663,0.0145638,0.001726918],"domain_scores_gemma":[0.8448822,0.1072401,0.003791162,0.02568808,0.01699183,0.001406669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001156835,0.000210368,0.00170432,0.001243063,0.0005366118,0.0001153514,0.0006979773,0.02766167,0.007885227,0.1366988,0.03550839,0.7865813],"study_design_scores_gemma":[0.0002035019,0.0002163294,0.001109743,0.0003378542,0.0002324422,0.0002635547,0.0001491037,0.3225437,0.00812242,0.6475799,0.01912905,0.0001124429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00598011,0.001800346,0.9843551,0.0009182935,0.000722539,0.000219729,0.0002660528,0.001023158,0.004714704],"genre_scores_gemma":[0.2921647,0.001095287,0.6894625,0.001040405,0.002119235,0.0007563476,0.001445006,0.001001983,0.01091462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04927327,"threshold_uncertainty_score":0.2605851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03901985798360569,"score_gpt":0.2754367443815013,"score_spread":0.2364168863978956,"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."}}