{"id":"W4414450177","doi":"10.48550/arxiv.2508.20902","title":"Automated Test Validators for Flaky Cyber-Physical System Simulators: Approach and Evaluation","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Real-time simulation and control systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ranking (information retrieval); Test (biology); Genetic programming; System under test; Test suite; Test case; Filter (signal processing); Domain (mathematical analysis); Fault (geology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003419054,0.0003612703,0.0005279063,0.0002559,0.0001102237,0.0001121174,0.0002590517,0.0003435876,0.000003740915],"category_scores_gemma":[0.00005562167,0.0004123567,0.0001986076,0.0003080559,0.00003641252,0.0001559313,0.0001388146,0.0002345773,0.00001160116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004424817,"about_ca_system_score_gemma":0.00009453935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004261181,"about_ca_topic_score_gemma":0.000003671399,"domain_scores_codex":[0.9985841,0.0001159077,0.0002710499,0.0006404669,0.000123582,0.0002648869],"domain_scores_gemma":[0.9986704,0.0003237981,0.000123925,0.0005231453,0.0002294608,0.0001292962],"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":[0.00001673734,0.00003714795,0.0006334927,0.0009654387,0.0001950747,0.000002924839,0.0001122497,0.9894341,0.00004707845,0.008163756,0.0001852413,0.000206741],"study_design_scores_gemma":[0.001279863,0.00001982906,0.0004658165,0.0001747397,0.0004238783,0.000001017069,0.000207012,0.9964054,0.00004004478,0.0003889594,0.0002298795,0.0003636011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8559865,0.0001243492,0.1178417,0.000008820101,0.0008688589,0.003332761,0.0002491882,0.003337429,0.01825032],"genre_scores_gemma":[0.99911,0.000006020782,0.00009879419,0.000004180023,0.0001455201,0.00002032231,0.0001675478,0.0000360343,0.0004115878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1431235,"threshold_uncertainty_score":0.9998328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04353128723020386,"score_gpt":0.2081185026311139,"score_spread":0.16458721540091,"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."}}