{"id":"W2770024286","doi":"","title":"Predict Responsibly: Increasing Fairness by Learning To Defer","year":2017,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Pipeline (software); Computer science; Decision maker; Downstream (manufacturing); Scheme (mathematics); Work (physics); Artificial intelligence; Machine learning; Risk analysis (engineering); Operations research; Economics; Business; Engineering; Operations management","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":[0.01411131,0.001347254,0.001705252,0.0006877151,0.001583386,0.002339271,0.002908224,0.002118342,0.002389889],"category_scores_gemma":[0.05323511,0.0007423189,0.0008899766,0.0004816252,0.003749504,0.005673821,0.00482897,0.004335862,0.0006342445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001871164,"about_ca_system_score_gemma":0.003326931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002596148,"about_ca_topic_score_gemma":0.002096032,"domain_scores_codex":[0.9936743,0.003242112,0.0002083274,0.001138451,0.001143452,0.0005933473],"domain_scores_gemma":[0.9574543,0.025547,0.003462738,0.009318332,0.002012157,0.002205545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001337912,0.0005167962,0.01112581,0.000142364,0.0001476125,0.0004549503,0.001403078,0.7092003,0.00776924,0.1408811,0.004669195,0.1223516],"study_design_scores_gemma":[0.00005017272,0.000145711,0.0003200618,0.0000194889,0.00002476516,0.00007199169,0.00004244562,0.9074362,0.002530917,0.08847047,0.000860602,0.00002717123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1872712,0.0004345848,0.8026208,0.002518232,0.0001230398,0.0001451894,0.00009776349,0.001159384,0.005629816],"genre_scores_gemma":[0.9620044,0.00009322331,0.03554998,0.0004440226,0.00005907262,0.00005994653,0.00004231844,0.00008822981,0.001658799],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01411131,"threshold_uncertainty_score":0.07462865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121573758043486,"score_gpt":0.280750064011967,"score_spread":0.2685926882076184,"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."}}