{"id":"W4307811455","doi":"10.1145/3569935","title":"Simulator-based Explanation and Debugging of Hazard-triggering Events in DNN-based Safety-critical Systems","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg; European Commission; Université du Luxembourg","keywords":"Debugging; Computer science; Hazard; Software engineering; Programming language","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":[0.001305591,0.0008041154,0.0002863822,0.0003709508,0.0001923458,0.0004260976,0.001352104,0.0007262297,0.001358669],"category_scores_gemma":[0.007053859,0.0003983215,0.0003226364,0.0001361087,0.000678874,0.001035945,0.0008433737,0.00118637,0.00020747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001140617,"about_ca_system_score_gemma":0.001055981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004635123,"about_ca_topic_score_gemma":0.006513576,"domain_scores_codex":[0.9994828,0.0001974378,0.00003408354,0.0001203789,0.0001196989,0.00004558777],"domain_scores_gemma":[0.9971601,0.001715853,0.000322927,0.0004016604,0.0003085938,0.00009091331],"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":[0.0002051635,0.0000595412,0.002017559,0.00007460594,0.00002654703,0.0002130687,0.00015528,0.9368846,0.008124391,0.002963507,0.0008303709,0.04844537],"study_design_scores_gemma":[0.000005209825,0.00002455395,0.0001430262,0.00000552861,0.000003568987,0.00001547545,0.000007971963,0.9934219,0.004429131,0.001686473,0.0002536372,0.000003613565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2143006,0.000409033,0.7759064,0.0005996611,0.0001096037,0.00009715538,0.0002469659,0.006085415,0.002245147],"genre_scores_gemma":[0.9327576,0.0001085774,0.06599442,0.0001130351,0.000008886765,0.0000449357,0.0001948334,0.0001229188,0.0006547268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004635123,"threshold_uncertainty_score":0.009216309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04752392328673987,"score_gpt":0.3100093273240562,"score_spread":0.2624854040373163,"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."}}