{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004636242,0.0002633602,0.0003221756,0.0002867322,0.0001704137,0.0001908744,0.003315284,0.0001165137,2.104182e-7],"category_scores_gemma":[0.03071458,0.0002167859,0.0001263467,0.001030539,0.00002952619,0.0002110647,0.001027429,0.0002324453,0.000001079991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381674,"about_ca_system_score_gemma":0.00006917946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002567314,"about_ca_topic_score_gemma":1.302651e-7,"domain_scores_codex":[0.9985223,0.000004930591,0.0003701276,0.0004607684,0.0002632618,0.0003785629],"domain_scores_gemma":[0.9968408,0.001453773,0.0002249032,0.0008919362,0.0005292993,0.00005931651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008711891,0.0007168301,0.3279377,0.007613173,0.0006751289,0.000005445713,0.001384235,0.07471208,0.02810377,0.1411619,0.3258212,0.09178142],"study_design_scores_gemma":[0.000463924,0.0002371258,0.01768414,0.002675305,0.0000434567,0.00002356578,0.000004524562,0.9423926,0.01812052,0.01567956,0.002084384,0.0005909101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1327577,0.0004229309,0.8084993,0.0006602372,0.002442535,0.001538644,0.00001439627,0.05332772,0.000336457],"genre_scores_gemma":[0.4541093,6.388225e-7,0.5454134,0.00005654002,0.00006418373,0.0001725528,4.276997e-7,0.00002725267,0.0001557943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8676805,"threshold_uncertainty_score":0.9774501,"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."}}