{"id":"W3092787839","doi":"","title":"Exchanging Lessons Between Algorithmic Fairness and Domain Generalization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Generalization; Computer science; Disjoint sets; Task (project management); Machine learning; Artificial intelligence; Domain (mathematical analysis); Theoretical computer science; Mathematics","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":[0.01996479,0.001374744,0.001784552,0.0009812729,0.00164511,0.003029849,0.002686474,0.002634027,0.002240054],"category_scores_gemma":[0.08440052,0.000608804,0.0008840717,0.0009020526,0.005820972,0.007985112,0.006691714,0.005474332,0.0006927978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001816175,"about_ca_system_score_gemma":0.002807757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001551315,"about_ca_topic_score_gemma":0.001883111,"domain_scores_codex":[0.9892869,0.005811467,0.0003928244,0.002404941,0.001560794,0.0005429687],"domain_scores_gemma":[0.9462775,0.03525346,0.002053017,0.01300015,0.002145814,0.001270019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005215657,0.0002685649,0.008597118,0.000260616,0.0002204505,0.0001896095,0.000846184,0.3762112,0.003919507,0.4412452,0.005569319,0.1621506],"study_design_scores_gemma":[0.00004063946,0.00009975062,0.0006684514,0.00004377067,0.00002097205,0.00008892826,0.00008114635,0.477231,0.002320338,0.5175035,0.001872285,0.00002914206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03350903,0.00056374,0.9591329,0.002287871,0.0001371686,0.00005866685,0.00006036789,0.0003192664,0.003930968],"genre_scores_gemma":[0.7678545,0.0005604053,0.225702,0.00156401,0.0004511665,0.0002303788,0.0001989732,0.0003164844,0.003122119],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01996479,"threshold_uncertainty_score":0.1055852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0885948343235872,"score_gpt":0.2086838632726356,"score_spread":0.1200890289490484,"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."}}