{"id":"W4386804672","doi":"10.1007/978-3-031-43415-0_18","title":"Fairness in Multi-Task Learning via Wasserstein Barycenters","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Machine learning; Bridge (graph theory); Multi-task learning; Binary number; Univariate; Representation (politics); Field (mathematics); Mathematics; Multivariate statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003349182,0.0003567879,0.0004858427,0.0007450994,0.0008119549,0.0005763749,0.001416228,0.0006940714,0.00003198025],"category_scores_gemma":[0.001080938,0.000368152,0.0001401858,0.0008266756,0.00176859,0.0005456926,0.0004551982,0.001982153,0.00008020656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006565289,"about_ca_system_score_gemma":0.0008979067,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003441538,"about_ca_topic_score_gemma":0.02986926,"domain_scores_codex":[0.9963234,0.0001597918,0.0004291173,0.0009180508,0.001243799,0.0009258519],"domain_scores_gemma":[0.9979793,0.0009442069,0.0002175138,0.0003357165,0.00027801,0.0002452287],"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":[0.00003885016,0.0001559611,0.00604809,0.0001725471,0.00005755207,0.0007543474,0.1720072,0.08366419,0.0003932476,0.06515792,0.0000682388,0.6714818],"study_design_scores_gemma":[0.002396857,0.0005983977,0.0054649,0.004204992,0.0000526579,0.00001042674,0.0003541071,0.1920571,0.0002664776,0.7717612,0.01832193,0.004510887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001965048,0.0002997247,0.9547601,0.009912701,0.005247344,0.0009558398,0.000008573208,0.000422011,0.02642864],"genre_scores_gemma":[0.9835294,0.0004109345,0.008822417,0.001452172,0.000691243,0.000008344744,0.000009775305,0.00007806565,0.00499758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9815644,"threshold_uncertainty_score":0.999877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05112664867657155,"score_gpt":0.335570504624754,"score_spread":0.2844438559481824,"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."}}