{"id":"W4391998095","doi":"10.1007/s10664-023-10433-5","title":"Evaluating the impact of flaky simulators on testing autonomous driving systems","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test (biology); Replication (statistics); Key (lock); Scope (computer science); Code coverage; Simulation; Machine learning; Operating system; Statistics; Software; Mathematics; 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":[0.0008557593,0.0002761142,0.0002797238,0.0002132317,0.0001309471,0.0003451616,0.0007429481,0.00009477434,0.000002276226],"category_scores_gemma":[0.006775856,0.0001840705,0.0001895451,0.00113397,0.00002759405,0.0002182323,0.0001906811,0.0004352234,0.00001323518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002604979,"about_ca_system_score_gemma":0.000175335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001170135,"about_ca_topic_score_gemma":9.881979e-8,"domain_scores_codex":[0.9981906,0.00007063198,0.0004192274,0.0004563496,0.0004361514,0.000427007],"domain_scores_gemma":[0.9920613,0.007000624,0.00008115017,0.0006422966,0.0001029608,0.0001116411],"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":[0.000001410885,0.00002341191,0.02658658,0.0001022775,0.00005286303,0.00002832965,0.0004559703,0.9353039,0.0002532403,0.0002321888,0.001077528,0.03588227],"study_design_scores_gemma":[0.00004795748,0.0003754763,0.0238736,0.0007115357,0.000009390677,0.00004442894,0.000001192646,0.9740264,0.0001070776,0.0005256711,0.00005931027,0.0002179976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3181773,0.0006337332,0.6648792,0.00004997366,0.0005592858,0.0001912786,0.000001997941,0.01546041,0.00004678154],"genre_scores_gemma":[0.9090666,7.105418e-7,0.09065811,0.00001594235,0.0001777891,0.00002912883,7.75879e-7,0.000033444,0.00001753143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5908893,"threshold_uncertainty_score":0.8111821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08166117695653764,"score_gpt":0.382740428437695,"score_spread":0.3010792514811574,"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."}}