{"id":"W4388212440","doi":"10.1109/issrew60843.2023.00052","title":"When Simulator Meets Natural Deviation: A Study on Deviations in Simulation-based ADS Testing","year":2023,"lang":"en","type":"article","venue":"","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Computer science; Flexibility (engineering); Pipeline (software); Software deployment; Simulation; Reliability engineering; Engineering; Software engineering","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":[0.0002165153,0.0001337035,0.0001440921,0.0003117526,0.00009719838,0.00001522211,0.0001209337,0.0001000158,0.00003938271],"category_scores_gemma":[0.0003770445,0.0001332141,0.00002680213,0.0008253273,0.00001401644,0.00009139188,0.00002132521,0.000228356,0.0002091813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144593,"about_ca_system_score_gemma":0.00002869993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009755897,"about_ca_topic_score_gemma":0.0001172285,"domain_scores_codex":[0.9991693,0.00002871872,0.0002705521,0.0001800175,0.0001286192,0.0002227295],"domain_scores_gemma":[0.9986681,0.00102275,0.0000250682,0.000214574,0.00004118464,0.00002827847],"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":[0.000003877256,0.00004044756,0.07206895,0.000006274179,0.00001293315,0.000007663987,0.000224214,0.9247935,0.0000569422,0.0002382712,0.00004052206,0.002506331],"study_design_scores_gemma":[0.0004271018,0.00003758273,0.2334425,0.00001118343,0.000004995316,9.129188e-8,0.000103024,0.7654017,0.00009822122,0.0002164316,0.0001409764,0.000116244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906092,0.00001803022,0.004717661,0.0003797531,0.0001345492,0.0004293217,0.000002942441,0.002741788,0.0009667532],"genre_scores_gemma":[0.9991649,2.161915e-7,0.0005456383,0.00009663003,0.00002561654,0.00004480531,0.00001334973,0.00002458153,0.00008431017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1613735,"threshold_uncertainty_score":0.5432315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03105615114185753,"score_gpt":0.273592758316889,"score_spread":0.2425366071750315,"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."}}