{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T14:22:11Z","timestamp":1770560531940,"version":"3.49.0"},"reference-count":135,"publisher":"Association for Computing Machinery (ACM)","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"abstract":"<jats:p>Given the increasing adoption of modern AI-enabled control systems, ensuring their safety and reliability has become a critical task in software testing. One prevalent approach to testing control systems is falsification, which aims to find an input signal that causes the control system to violate a formal safety specification using optimization algorithms. However, applying falsification to AI-enabled control systems poses two significant challenges: (1)\u00a0it requires the system to execute numerous candidate test inputs, which can be time-consuming, particularly for systems with AI models that have many parameters, and (2)\u00a0multiple safety requirements are typically defined as a conjunctive specification, which is difficult for existing falsification approaches to comprehensively cover.<\/jats:p>\n          <jats:p>\n            This paper introduces\n            <jats:sc>Synthify<\/jats:sc>\n            , a falsification framework tailored for AI-enabled control systems, i.e., control systems equipped with AI controllers. Our approach performs falsification in a two-phase process. At the start,\n            <jats:sc>Synthify<\/jats:sc>\n            synthesizes a program that implements one or a few linear controllers to serve as a proxy for the AI controller. This proxy program mimics the AI controller's functionality but is computationally more efficient. Then,\n            <jats:sc>Synthify<\/jats:sc>\n            employs the\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\epsilon\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            -greedy strategy to sample a promising sub-specification from the conjunctive safety specification. It then uses a Simulated Annealing-based falsification algorithm to find violations of the sampled sub-specification for the control system. To evaluate\n            <jats:sc>Synthify<\/jats:sc>\n            , we compare it to\n            <jats:sc>PSY-TaLiRo<\/jats:sc>\n            , a state-of-the-art and industrial-strength falsification tool, on 8 publicly available control systems. On average,\n            <jats:sc>Synthify<\/jats:sc>\n            achieves a 83.5% higher success rate in falsification compared to\n            <jats:sc>PSY-TaLiRo<\/jats:sc>\n            with the same budget of falsification trials. Additionally, our method is 12.8\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            faster in finding a single safety violation than the baseline. The safety violations found by\n            <jats:sc>Synthify<\/jats:sc>\n            are also more diverse than those found by\n            <jats:sc>PSY-TaLiRo<\/jats:sc>\n            , covering 137.7% more sub-specifications.\n          <\/jats:p>","DOI":"10.1145\/3715105","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T15:53:31Z","timestamp":1737993211000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0799-5018","authenticated-orcid":false,"given":"Jieke","family":"Shi","sequence":"first","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5938-1918","authenticated-orcid":false,"given":"Zhou","family":"Yang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-8585","authenticated-orcid":false,"given":"Junda","family":"He","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1006-8493","authenticated-orcid":false,"given":"Bowen","family":"Xu","sequence":"additional","affiliation":[{"name":"North Carolina State University, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0272-6860","authenticated-orcid":false,"given":"Dongsun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8599-2197","authenticated-orcid":false,"given":"DongGyun","family":"Han","sequence":"additional","affiliation":[{"name":"Royal Holloway, University of London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4367-7201","authenticated-orcid":false,"given":"David","family":"Lo","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2025,1,27]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2012.6483411"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859453"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238192"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_24"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v33i1.27172"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19835-9_21"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985795"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME52107.2021.00079"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641513.3650141"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"e_1_2_1_11_1","unstructured":"Mariusz Bojarski Davide\u00a0Del Testa Daniel Dworakowski Bernhard Firner Beat Flepp Prasoon Goyal Lawrence\u00a0D. Jackel Mathew Monfort Urs Muller Jiakai Zhang Xin Zhang Jake Zhao and Karol Zieba. 2016. End to End Learning for Self-Driving Cars. arXiv:1604.07316\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1604.07316"},{"key":"e_1_2_1_12_1","volume-title":"EGU General Assembly Conference Abstracts (EGU General Assembly Conference Abstracts). 3574","author":"Brassington Gary","year":"2017","unstructured":"Gary Brassington. 2017. Mean absolute error and root mean square error: which is the better metric for assessing model performance?. In EGU General Assembly Conference Abstracts (EGU General Assembly Conference Abstracts). 3574. https:\/\/ui.adsabs.harvard.edu\/abs\/2017EGUGA..19.3574B"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15844-5_2"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2021.100696"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575870.3587122"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3318070"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/10722167_15"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12716"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126521"},{"key":"e_1_2_1_21_1","unstructured":"DJI. 2024. DJI Camera Drones. https:\/\/www.dji.com\/sg\/camera-drones"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14295-6_17"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15297-9_9"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10817-018-09509-5"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-25540-4_25"},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"Duan Yan","year":"2016","unstructured":"Yan Duan, Xi Chen, Rein Houthooft, John Schulman, and Pieter Abbeel. 2016. Benchmarking deep reinforcement learning for continuous control. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (New York, NY, USA) (ICML\u201916). JMLR.org, 1329\u20131338. https:\/\/proceedings.mlr.press\/v48\/duan16.pdf"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.29007\/r74f"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.29007\/xwl1"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.29007\/trr1"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.29007\/fhnk"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459605"},{"key":"e_1_2_1_32_1","unstructured":"Nathan Fulton Nathan Hunt Nghia Hoang and Subhro Das. 2020. Formal Verification of End-to-End Learning in Cyber-Physical Systems: Progress and Challenges. (2020). arXiv:2006.09181\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2006.09181"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06543-w"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00079"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583136"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510188"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00155"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09982-4"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICST46399.2020.00019"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639149"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225072"},{"key":"e_1_2_1_42_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Becker, S.\u00a0Thrun, and K.\u00a0Obermayer (Eds.), Vol.\u00a015","author":"Hinton E","year":"2002","unstructured":"Geoffrey\u00a0E Hinton and Sam Roweis. 2002. Stochastic Neighbor Embedding. In Advances in Neural Information Processing Systems, S.\u00a0Becker, S.\u00a0Thrun, and K.\u00a0Obermayer (Eds.), Vol.\u00a015. MIT Press. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2002\/file\/6150ccc6069bea6b5716254057a194ef-Paper.pdf"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(92)90053-I"},{"key":"e_1_2_1_44_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1l8oANFDH","author":"Inala Jeevana\u00a0Priya","year":"2020","unstructured":"Jeevana\u00a0Priya Inala, Osbert Bastani, Zenna Tavares, and Armando Solar-Lezama. 2020. Synthesizing Programmatic Policies that Inductively Generalize. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1l8oANFDH"},{"key":"e_1_2_1_45_1","unstructured":"Ismailbennani. [n.d.]. zlscheck: A random testing tool for z\u00e9lus. https:\/\/github.com\/ismailbennani\/zlscheck"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42064-018-0053-6"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/1-84628-148-2"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2016.7778091"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps52748.2021.9682055"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534398"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2602089"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-021-08708-5"},{"key":"e_1_2_1_55_1","unstructured":"Volodymyr Kuleshov and Doina Precup. 2014. Algorithms for multi-armed bandit problems. (2014). arXiv:1402.6028\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/1402.6028"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641399.3641401"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.536312"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596444"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501710.3519521"},{"key":"e_1_2_1_60_1","unstructured":"Timothy\u00a0P. Lillicrap Jonathan\u00a0J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2019. Continuous control with deep reinforcement learning. arXiv:1509.02971\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1509.02971"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549111"},{"key":"e_1_2_1_62_1","unstructured":"Deyun Lyu Jiayang Song Zhenya Zhang Zhijie Wang Tianyi Zhang Lei Ma and Jianjun Zhao. 2023. AutoRepair: Automated Repair for AI-Enabled Cyber-Physical Systems under Safety-Critical Conditions. (2023). arXiv:2304.05617\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2304.05617"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30206-3_12"},{"key":"e_1_2_1_64_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.), Vol.\u00a031. Curran Associates","author":"Mania Horia","year":"2018","unstructured":"Horia Mania, Aurelia Guy, and Benjamin Recht. 2018. Simple random search of static linear policies is competitive for reinforcement learning. In Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.), Vol.\u00a031. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/7634ea65a4e6d9041cfd3f7de18e334a-Paper.pdf"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","unstructured":"Logan Mathesen Giulia Pedrielli and Georgios Fainekos. 2021. Efficient Optimization-Based Falsification of Cyber-Physical Systems with Multiple Conjunctive Requirements. In 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE). 732\u2013737. https:\/\/doi.org\/10.1109\/CASE49439.2021.9551474","DOI":"10.1109\/CASE49439.2021.9551474"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510082"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380370"},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.2514\/6.2023-3596"},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59152-6_34"},{"key":"e_1_2_1_72_1","unstructured":"NVIDIA. 2024. NVIDIA DRIVE. https:\/\/developer.nvidia.com\/drive."},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3418930"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2931057"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534388"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","unstructured":"Jarkko Peltom\u00e4ki and Ivan Porres. 2022. Falsification of Multiple Requirements for Cyber-Physical Systems Using Online Generative Adversarial Networks and Multi-Armed Bandits. In 2022 IEEE International Conference on Software Testing Verification and Validation Workshops (ICSTW). 21\u201328. https:\/\/doi.org\/10.1109\/ICSTW55395.2022.00018","DOI":"10.1109\/ICSTW55395.2022.00018"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00017"},{"key":"e_1_2_1_78_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6Tk2noBdvxt","author":"Qiu Wenjie","year":"2022","unstructured":"Wenjie Qiu and He Zhu. 2022. Programmatic Reinforcement Learning without Oracles. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6Tk2noBdvxt"},{"key":"e_1_2_1_79_1","volume-title":"Advances in Neural Information Processing Systems, I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates","author":"Rajeswaran Aravind","year":"2017","unstructured":"Aravind Rajeswaran, Kendall Lowrey, Emanuel\u00a0V. Todorov, and Sham\u00a0M Kakade. 2017. Towards Generalization and Simplicity in Continuous Control. In Advances in Neural Information Processing Systems, I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/9ddb9dd5d8aee9a76bf217a2a3c54833-Paper.pdf"},{"key":"e_1_2_1_80_1","unstructured":"Zahra Ramezani Kenan \u0160ehi\u0107 Luigi Nardi and Knut \u00c5kesson. 2023. Falsification of Cyber-Physical Systems using Bayesian Optimization. (2023). arXiv:2209.06735\u00a0[eess.SY] https:\/\/arxiv.org\/abs\/2209.06735"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48869-1_2"},{"key":"e_1_2_1_82_1","unstructured":"Tim Salimans Jonathan Ho Xi Chen Szymon Sidor and Ilya Sutskever. 2017. Evolution Strategies as a Scalable Alternative to Reinforcement Learning. (2017). arXiv:1703.03864\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1703.03864"},{"key":"e_1_2_1_83_1","unstructured":"Segway. 2024. Segway transporters. https:\/\/ap-en.segway.com\/"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454051"},{"key":"e_1_2_1_85_1","unstructured":"Jieke Shi Junda He Zhou Yang \u0110or\u0111e \u017dikeli\u0107 and David Lo. 2024. Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies. (2024). arXiv:2410.05641\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2410.05641"},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00130"},{"key":"e_1_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639475.3640097"},{"key":"e_1_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3708525"},{"key":"e_1_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556964"},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3162324"},{"key":"e_1_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10672-9_3"},{"key":"e_1_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2018.2877664"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510457.3513049"},{"key":"e_1_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3282981"},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556897"},{"key":"e_1_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_2_1_97_1","unstructured":"Tesla. 2023. Autopilot. https:\/\/www.thinkautonomous.ai\/blog\/tesla-end-to-end-deep-learning\/."},{"key":"e_1_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85248-1_15"},{"key":"e_1_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358230"},{"key":"e_1_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53288-8_1"},{"key":"e_1_2_1_101_1","volume-title":"Article 1926","author":"Trivedi Dweep","year":"2024","unstructured":"Dweep Trivedi, Jesse Zhang, Shao-Hua Sun, and Joseph\u00a0J. Lim. 2024. Learning to synthesize programs as interpretable and generalizable policies., Article 1926 (2024), 18\u00a0pages. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/d37124c4c79f357cb02c655671a432fa-Paper.pdf"},{"key":"e_1_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77935-5_30"},{"key":"e_1_2_1_103_1","unstructured":"Udacity. 2024. Udacity Self-Driving Challenge #2: Predicting Steering Angles. https:\/\/github.com\/udacity\/self-driving-car\/tree\/master\/steering-models"},{"key":"e_1_2_1_104_1","first-page":"101","article-title":"A Critique and Improvement of the","volume":"25","author":"Vargha Andr\u00e1s","year":"2000","unstructured":"Andr\u00e1s Vargha and Harold\u00a0D. Delaney. 2000. A Critique and Improvement of the \u201dCL\u201d Common Language Effect Size Statistics of McGraw and Wong. Journal of Educational and Behavioral Statistics 25, 2 (2000), 101\u2013132. http:\/\/www.jstor.org\/stable\/1165329","journal-title":"Journal of Educational and Behavioral Statistics"},{"key":"e_1_2_1_105_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol.\u00a080)","author":"Verma Abhinav","year":"2018","unstructured":"Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh, Pushmeet Kohli, and Swarat Chaudhuri. 2018. Programmatically Interpretable Reinforcement Learning. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol.\u00a080), Jennifer Dy and Andreas Krause (Eds.). PMLR, 5045\u20135054. https:\/\/proceedings.mlr.press\/v80\/verma18a.html"},{"key":"e_1_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88494-9_15"},{"key":"e_1_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527448"},{"key":"e_1_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365365.3382193"},{"key":"e_1_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.18293\/SEKE2021-087"},{"key":"e_1_2_1_110_1","volume-title":"MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems.","author":"Wang Renzhi","year":"2024","unstructured":"Renzhi Wang, Zhehua Zhou, Jiayang Song, Xuan Xie, Xiaofei Xie, and Lei Ma. 2024. MORTAR: A Model-based Runtime Action Repair Framework for AI-enabled Cyber-Physical Systems. (2024). arXiv:2408.03892\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2408.03892"},{"key":"e_1_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"e_1_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00027"},{"key":"e_1_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"e_1_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-015-0894-x"},{"key":"e_1_2_1_115_1","volume-title":"Mosaic: Model-based Safety Analysis Framework for AI-enabled Cyber-Physical Systems.","author":"Xie Xuan","year":"2023","unstructured":"Xuan Xie, Jiayang Song, Zhehua Zhou, Fuyuan Zhang, and Lei Ma. 2023. Mosaic: Model-based Safety Analysis Framework for AI-enabled Cyber-Physical Systems. (2023). arXiv:2305.03882\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2305.03882"},{"key":"e_1_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963007"},{"key":"e_1_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302504.3311814"},{"key":"e_1_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2020.2969178"},{"key":"e_1_2_1_119_1","unstructured":"Chengran Yang Hong\u00a0Jin Kang Jieke Shi and David Lo. 2024. ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models. (2024). arXiv:2412.17264\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2412.17264"},{"key":"e_1_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00056"},{"key":"e_1_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678546"},{"key":"e_1_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3482719"},{"key":"e_1_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639074"},{"key":"e_1_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2016.09.026"},{"key":"e_1_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678832"},{"key":"e_1_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598108"},{"key":"e_1_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90870-6_18"},{"key":"e_1_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858463"},{"key":"e_1_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-81685-8_29"},{"key":"e_1_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-76384-8_24"},{"key":"e_1_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3194640"},{"key":"e_1_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639477.3639740"},{"key":"e_1_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3496492"},{"key":"e_1_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314638"},{"key":"e_1_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3269804"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T15:55:41Z","timestamp":1737993341000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,27]]},"references-count":135,"alternative-id":["10.1145\/3715105"],"URL":"https:\/\/doi.org\/10.1145\/3715105","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,27]]},"assertion":[{"value":"2023-10-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3715105"}}