{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004773056,0.001325611,0.000713199,0.001790366,0.0003359693,0.0009237125,0.002021558,0.001116356,0.001358664],"category_scores_gemma":[0.02832098,0.0003355937,0.0006423707,0.0008468912,0.0008277549,0.001188194,0.0008616808,0.001031415,0.0002792285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002177919,"about_ca_system_score_gemma":0.002329045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006670119,"about_ca_topic_score_gemma":0.005751563,"domain_scores_codex":[0.9950628,0.002427642,0.0002579502,0.0004584452,0.001539548,0.0002535685],"domain_scores_gemma":[0.9638786,0.02660844,0.002389313,0.002709953,0.003945132,0.0004686551],"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":[0.0004288316,0.0007037178,0.01039559,0.0003899614,0.0001186567,0.0001841735,0.0001844519,0.7504653,0.009424494,0.00420171,0.001851628,0.2216515],"study_design_scores_gemma":[0.0000450999,0.0001822449,0.0008519797,0.00001740928,0.00001385775,0.00004157354,0.00002705082,0.9930459,0.004711504,0.0006325114,0.000422729,0.000008109305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.510078,0.0009910479,0.4736495,0.0005073947,0.0000987099,0.0009009956,0.0005251658,0.009064667,0.004184559],"genre_scores_gemma":[0.7638254,0.000220477,0.2340207,0.00009757815,0.00001583856,0.0002367352,0.0007046237,0.0002355756,0.0006432311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006670119,"threshold_uncertainty_score":0.02524263,"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."}}