{"id":"W7132995918","doi":"","title":"Towards Trustworthy Machine Learning in High-Stakes Decision-Making Systems","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Trustworthiness; Task (project management); Heuristic; Strengths and weaknesses; Adversarial system; Focus (optics); Artificial neural network; Function (biology); Cognitive reframing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0380957,0.00178171,0.002642642,0.001660756,0.002299995,0.009122986,0.003682286,0.006304562,0.003435943],"category_scores_gemma":[0.1339533,0.001636252,0.001571518,0.001259954,0.01152441,0.01165021,0.009857598,0.01123503,0.0008661288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004522911,"about_ca_system_score_gemma":0.004542227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002441268,"about_ca_topic_score_gemma":0.001492146,"domain_scores_codex":[0.9741278,0.01705526,0.001042724,0.002827219,0.0038616,0.00108547],"domain_scores_gemma":[0.8717403,0.1034954,0.007788631,0.009648567,0.005056666,0.002270523],"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":[0.0001637507,0.00008523482,0.002098885,0.0002029582,0.0001046021,0.0002158407,0.0006977267,0.2704731,0.0007710888,0.706445,0.001245005,0.01749671],"study_design_scores_gemma":[0.00002320962,0.00003458672,0.0001473526,0.00005377744,0.00001024132,0.00003232012,0.00005115453,0.3661456,0.0004432774,0.6320514,0.0009850819,0.00002189886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01686626,0.0006937069,0.9711869,0.005962803,0.0001022829,0.00009562721,0.00006222178,0.0001717238,0.004858507],"genre_scores_gemma":[0.7649431,0.001084967,0.228669,0.001374334,0.0004973031,0.0003434624,0.0001210452,0.0001804529,0.002786333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0380957,"threshold_uncertainty_score":0.2014717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02168616051524598,"score_gpt":0.3387278517736889,"score_spread":0.3170416912584429,"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."}}