{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001406269,0.0001401796,0.000290165,0.0004721651,0.0001774995,0.00001147263,0.0002670049,0.00007037001,0.000006010145],"category_scores_gemma":[0.001706327,0.0001632913,0.00004134378,0.0003549943,0.0000277757,0.0001166262,0.00003198261,0.0004302013,1.844925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009651111,"about_ca_system_score_gemma":0.00006122661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005404741,"about_ca_topic_score_gemma":0.000002862444,"domain_scores_codex":[0.9984057,0.0005674536,0.0002939707,0.0003235312,0.0001881058,0.000221215],"domain_scores_gemma":[0.9930745,0.006479281,0.00005655618,0.0002982893,0.00002948645,0.00006184172],"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":[0.00003698934,0.00002711705,0.0009248362,0.00009743887,0.00001287743,0.000007379144,0.0001964871,0.9863787,0.0001979398,0.0007109422,2.350935e-7,0.01140907],"study_design_scores_gemma":[0.0007336373,0.0001182804,0.001860919,0.00006278528,0.00001799866,0.00002107783,0.00005408326,0.9962466,0.0004437736,0.0001364999,0.0001421022,0.0001622496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04216866,0.0001999582,0.9565501,0.0001941173,0.0005777696,0.0001201642,0.000006221583,0.000182183,8.696197e-7],"genre_scores_gemma":[0.6520593,0.000002734343,0.3478548,0.00002672239,0.000008444998,0.00003200348,0.000001797532,0.00001160328,0.000002642514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6098906,"threshold_uncertainty_score":0.6658826,"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."}}