{"id":"W4411523015","doi":"10.1145/3728876","title":"MoDitector: Module-Directed Testing for Autonomous Driving Systems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Root cause; Computer science; Debugging; Reliability (semiconductor); Reliability engineering; Root cause analysis; Process (computing); Scenario testing; Embedded system; Engineering; Artificial intelligence","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":[0.001273779,0.001298076,0.0003340116,0.0009163119,0.000254231,0.0005513009,0.002340639,0.0009545211,0.003346474],"category_scores_gemma":[0.005496521,0.0004354911,0.0006335419,0.0002877341,0.0008383387,0.001353927,0.0009855236,0.0009440428,0.0005986017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005487496,"about_ca_system_score_gemma":0.0008548227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002484838,"about_ca_topic_score_gemma":0.003154759,"domain_scores_codex":[0.9988719,0.0002942861,0.00006594134,0.0001859362,0.000471233,0.0001106924],"domain_scores_gemma":[0.9969541,0.001777802,0.0003064942,0.0004991258,0.0003663077,0.00009614779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008613794,0.00049857,0.02393115,0.001033803,0.0002234109,0.001503538,0.0008412727,0.3320419,0.1653492,0.01371714,0.01612977,0.4438688],"study_design_scores_gemma":[0.0001239604,0.0007011437,0.003036974,0.0000635082,0.00006045945,0.0006703407,0.00007748,0.8558918,0.1193086,0.006602414,0.01339579,0.00006758596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1865883,0.0006387783,0.7360482,0.0003783498,0.0001423335,0.0006797118,0.0009830919,0.06771174,0.006829457],"genre_scores_gemma":[0.7055929,0.0001829682,0.2878298,0.0002809165,0.00002523804,0.0003492333,0.001227184,0.00191971,0.002592062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003346474,"threshold_uncertainty_score":0.01119506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694061228693788,"score_gpt":0.2359343562073011,"score_spread":0.2189937439203632,"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."}}