{"id":"W4401990439","doi":"10.1109/dsn-s60304.2024.00018","title":"Harnessing Explainability to Improve ML Ensemble Resilience","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Resilience (materials science); Computer science; Materials science","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008844289,0.0001913571,0.0001677109,0.0001959704,0.0002415535,0.001112538,0.001217172,0.00006860777,0.00008958094],"category_scores_gemma":[0.0003556529,0.0001675407,0.00008287387,0.001337902,0.00006847866,0.001680472,0.0005596054,0.000190041,0.00181962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001913644,"about_ca_system_score_gemma":0.0002265847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003068633,"about_ca_topic_score_gemma":0.0001085838,"domain_scores_codex":[0.9975647,0.00007582941,0.0003489047,0.001016071,0.0003821575,0.0006122864],"domain_scores_gemma":[0.998206,0.0002873078,0.00002579888,0.001082466,0.0001534818,0.0002449709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007281562,0.0000559266,0.00007755119,0.00007529373,0.000007276327,0.0001321101,0.003055491,0.0007798634,0.08177869,0.5039611,0.00450209,0.4055673],"study_design_scores_gemma":[0.00003259812,0.0001903516,0.0001794321,0.00009099503,0.000004388462,0.00002324242,0.0006966371,0.2237023,0.667336,0.07261176,0.03465722,0.0004750047],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03695851,0.0001779234,0.938199,0.005176844,0.001267926,0.0003105114,8.570863e-7,0.0009183503,0.01699005],"genre_scores_gemma":[0.9234547,0.000004423103,0.06999552,0.0007879952,0.0001150781,0.00006083781,3.379491e-7,0.0000149202,0.005566164],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8864962,"threshold_uncertainty_score":0.9999244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02183897680273461,"score_gpt":0.2982170399967199,"score_spread":0.2763780631939853,"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."}}