{"id":"W3115164309","doi":"10.1145/3437963.3441732","title":"Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems","year":2021,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Recommender system; Computer science; Component (thermodynamics); Fairness measure; Machine learning","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":[0.01967379,0.001093358,0.002031126,0.001190503,0.002386626,0.005064514,0.003379043,0.002708827,0.004580314],"category_scores_gemma":[0.0696457,0.0009120227,0.001279359,0.001035617,0.004523808,0.01277024,0.004871156,0.004226369,0.0007790843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002570203,"about_ca_system_score_gemma":0.002509405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004851244,"about_ca_topic_score_gemma":0.00246389,"domain_scores_codex":[0.9873356,0.006709518,0.0006720194,0.002006324,0.002493107,0.0007833857],"domain_scores_gemma":[0.9635118,0.02247085,0.002384837,0.00535937,0.004781121,0.001492092],"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":[0.0002108232,0.0001365911,0.004173918,0.0002050375,0.0001538888,0.0001639226,0.001450032,0.1086506,0.001364033,0.838374,0.002690375,0.04242672],"study_design_scores_gemma":[0.0000268833,0.00004500662,0.0005392411,0.00003735225,0.00003688766,0.00005371598,0.0001176407,0.3183983,0.0004223416,0.6776791,0.002613043,0.00003037536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02621905,0.0007545167,0.9636995,0.002746103,0.000203506,0.00009171843,0.00008038812,0.0001929117,0.006012326],"genre_scores_gemma":[0.8045483,0.0007103821,0.1885395,0.0009011357,0.0006858259,0.0002258844,0.0001253214,0.0001741578,0.004089408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01967379,"threshold_uncertainty_score":0.1040461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1990138567032828,"score_gpt":0.3518897198147765,"score_spread":0.1528758631114937,"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."}}