{"id":"W2987883180","doi":"","title":"What Does It Mean for Machine Learning to Be Trustworthy","year":2020,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Trustworthiness; Artificial intelligence; Computer science; Machine learning; Data science; Computer security","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":[],"consensus_categories":[],"category_scores_codex":[0.0003081039,0.0001434797,0.00017039,0.00006090527,0.0002034318,0.0006151591,0.0008974554,0.00004109296,0.0001933156],"category_scores_gemma":[0.0002749067,0.0001079875,0.00008328113,0.0004685565,0.00001932077,0.001283215,0.000342647,0.0001292071,0.0002759063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002586796,"about_ca_system_score_gemma":0.00003259996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008491221,"about_ca_topic_score_gemma":0.001104194,"domain_scores_codex":[0.9985799,0.00004581805,0.0002432625,0.000514373,0.0002309676,0.0003856992],"domain_scores_gemma":[0.9990514,0.0002009198,0.00004766752,0.0003122055,0.000111672,0.0002761309],"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":[0.0001299107,0.0001280994,0.0006754437,0.0000964569,0.00007268417,0.00005742454,0.1466105,0.0192582,0.009748155,0.4523208,0.01849848,0.3524039],"study_design_scores_gemma":[0.00009655325,0.0003933785,0.000005946049,0.0000146963,0.000005084056,0.000002041061,0.007613631,0.4891585,0.08408045,0.003310528,0.4150237,0.0002954694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01031295,0.00006637879,0.8407401,0.1457072,0.0005519399,0.0003935783,0.000001365464,0.0003745535,0.0018519],"genre_scores_gemma":[0.8337099,0.00006551346,0.1033486,0.05527556,0.0003276255,0.00008123957,0.0000059869,0.00003184636,0.007153673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.823397,"threshold_uncertainty_score":0.5931994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05817481502801922,"score_gpt":0.2960011575743803,"score_spread":0.2378263425463611,"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."}}