{"id":"W3185323353","doi":"10.1109/deeptest52559.2021.00010","title":"TF-DM: Tool for Studying ML Model Resilience to Data Faults","year":2021,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dependability; Computer science; Reliability (semiconductor); Resilience (materials science); Reliability engineering; Data modeling; Focus (optics); Fault (geology); Quality (philosophy); Data mining; Software engineering; Engineering","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":[0.002581583,0.001951448,0.0006764586,0.002869622,0.0006180294,0.001256982,0.00222416,0.001685292,0.006565344],"category_scores_gemma":[0.0203073,0.00057652,0.001374346,0.001420344,0.0009672858,0.002078571,0.001891812,0.002173449,0.00169615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000980528,"about_ca_system_score_gemma":0.001476138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005790721,"about_ca_topic_score_gemma":0.006070748,"domain_scores_codex":[0.9983601,0.0003878611,0.0001656486,0.0003586537,0.0005951166,0.000132589],"domain_scores_gemma":[0.9900573,0.006804342,0.0007059096,0.001592112,0.0006463838,0.0001938944],"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":[0.0009324351,0.0006210442,0.0312666,0.002068583,0.0005988713,0.0006737945,0.0004551602,0.655697,0.01439287,0.01817514,0.1301651,0.1449533],"study_design_scores_gemma":[0.00007908721,0.0001414318,0.00272173,0.00005668016,0.0000348411,0.0002637143,0.000062712,0.962036,0.01181317,0.01158723,0.01116251,0.00004101551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1873504,0.001545844,0.5273985,0.001094646,0.0004842512,0.0006404357,0.05375224,0.2202774,0.007456238],"genre_scores_gemma":[0.6044383,0.0006184564,0.3261589,0.0006723096,0.00009969417,0.001254457,0.05689422,0.007012529,0.002851137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006565344,"threshold_uncertainty_score":0.02196324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07931967226435244,"score_gpt":0.3500755904431777,"score_spread":0.2707559181788252,"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."}}