{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003221722,0.0002568934,0.000303024,0.0003006118,0.0002753218,0.0003763184,0.0007371578,0.0002332509,0.00002246768],"category_scores_gemma":[0.00002262899,0.000328141,0.0001095542,0.0006292957,0.0000727716,0.0004648404,0.001563684,0.0004081857,0.00001319904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001300171,"about_ca_system_score_gemma":0.000142963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008233428,"about_ca_topic_score_gemma":0.00002250582,"domain_scores_codex":[0.9981455,0.0002577344,0.0001784967,0.0009919206,0.000111501,0.0003148334],"domain_scores_gemma":[0.9987882,0.00008209373,0.0002076751,0.0006212594,0.0001318218,0.0001689255],"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":[0.000009957523,0.00008183227,0.01281615,0.000269375,0.0002798623,0.0008816721,0.007265138,0.2954464,0.0003110742,0.6541581,0.000183786,0.02829664],"study_design_scores_gemma":[0.0007972322,0.00002595609,0.01087134,0.0002003385,0.00007824508,0.00001287321,0.001227795,0.9523074,0.0001272215,0.03139755,0.002103927,0.0008501012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1944925,0.00009569321,0.8037754,0.0002483873,0.0002825349,0.0001354938,0.000005087366,0.0001818164,0.0007831085],"genre_scores_gemma":[0.9809474,0.0001915275,0.01755889,0.00009383194,0.0001184061,0.000001103052,0.0000669517,0.00001963149,0.001002218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.786455,"threshold_uncertainty_score":0.9999171,"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."}}