{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T08:30:06Z","timestamp":1768033806424,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2346396"],"award-info":[{"award-number":["CNS-2346396"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Energy","award":["DE-SC0020286"],"award-info":[{"award-number":["DE-SC0020286"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767362","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:20:02Z","timestamp":1762532402000},"page":"225-234","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["LLM4FP: LLM-Based Program Generation for Triggering Floating-Point Inconsistencies Across Compilers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2346-189X","authenticated-orcid":false,"given":"Yutong","family":"Wang","sequence":"first","affiliation":[{"name":"University of California, Davis, Davis, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0861-3763","authenticated-orcid":false,"given":"Cindy","family":"Rubio-Gonz\u00e1lez","sequence":"additional","affiliation":[{"name":"University of California, Davis, Davis, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"1991. \"What Every Computer Scientist Should Know About Floating-Point Arithmetic\". ACM Comput. Surv. 23 3 (1991) 413.","DOI":"10.1145\/103162.103163"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Qurat\u00a0Ul Ain Wasi\u00a0Haider Butt Muhammad\u00a0Waseem Anwar Farooque Azam and Bilal Maqbool. 2019. A Systematic Review on Code Clone Detection. IEEE Access 7 (2019) 86121\u201386144. 10.1109\/ACCESS.2019.2918202","DOI":"10.1109\/ACCESS.2019.2918202"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Chetan Arora Ahnaf\u00a0Ibn Sayeed Sherlock\u00a0A. Licorish Fanyu Wang and Christoph Treude. 2024. Optimizing Large Language Model Hyperparameters for Code Generation. CoRR abs\/2408.10577 (2024). arXiv:https:\/\/arXiv.org\/abs\/2408.1057710.48550\/ARXIV.2408.10577","DOI":"10.48550\/ARXIV.2408.10577"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Junjie Chen Jibesh Patra Michael Pradel Yingfei Xiong Hongyu Zhang Dan Hao and Lu Zhang. 2021. A Survey of Compiler Testing. ACM Comput. Surv. 53 1 (2021) 4:1\u20134:36. 10.1145\/3363562","DOI":"10.1145\/3363562"},{"key":"e_1_3_3_1_6_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun et\u00a0al. 2021. Evaluating Large Language Models Trained on Code. CoRR abs\/2107.03374 (2021). arXiv:https:\/\/arXiv.org\/abs\/2107.03374https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555265"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2011.26"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Alastair\u00a0F. Donaldson Hugues Evrard Andrei Lascu and Paul Thomson. 2017. Automated testing of graphics shader compilers. Proc. ACM Program. Lang. 1 OOPSLA (2017) 93:1\u201393:29. 10.1145\/3133917","DOI":"10.1145\/3133917"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Joe\u00a0W. Duran and Simeon\u00a0C. Ntafos. 1984. An Evaluation of Random Testing. IEEE Trans. Software Eng. 10 4 (1984) 438\u2013444. 10.1109\/TSE.1984.5010257","DOI":"10.1109\/TSE.1984.5010257"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115662"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Maya\u00a0B. Gokhale Ganesh Gopalakrishnan Jackson Mayo Santosh Nagarakatte Cindy Rubio-Gonz\u00e1lez and Stephen\u00a0F. Siegel. 2023. Report of the DOE\/NSF Workshop on Correctness in Scientific Computing June 2023 Orlando FL. CoRR abs\/2312.15640 (2023). arXiv:https:\/\/arXiv.org\/abs\/2312.1564010.48550\/ARXIV.2312.15640","DOI":"10.48550\/ARXIV.2312.15640"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CORRECTNESS54621.2021.00007"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2007.68"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3617850"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00053"},{"key":"e_1_3_3_1_17_2","first-page":"445","volume-title":"Proceedings of the 21th USENIX Security Symposium, Bellevue, WA, USA, August 8-10, 2012","author":"Holler Christian","year":"2012","unstructured":"Christian Holler, Kim Herzig, and Andreas Zeller. 2012. Fuzzing with Code Fragments. In Proceedings of the 21th USENIX Security Symposium, Bellevue, WA, USA, August 8-10, 2012, Tadayoshi Kohno (Ed.). USENIX Association, 445\u2013458. https:\/\/www.usenix.org\/conference\/usenixsecurity12\/technical-sessions\/presentation\/holler"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Darrel\u00a0C. Ince and Sharam Hekmatpour. 1986. An Empirical Evaluation of Random Testing. Comput. J. 29 4 (1986) 380. 10.1093\/COMJNL\/29.4.380","DOI":"10.1093\/COMJNL\/29.4.380"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Juyong Jiang Fan Wang Jiasi Shen Sungju Kim and Sunghun Kim. 2024. A Survey on Large Language Models for Code Generation. CoRR abs\/2406.00515 (2024). arXiv:https:\/\/arXiv.org\/abs\/2406.0051510.48550\/ARXIV.2406.00515","DOI":"10.48550\/ARXIV.2406.00515"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00070"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594334"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2814270.2814319"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Vsevolod Livinskii Dmitry Babokin and John Regehr. 2020. Random testing for C and C++ compilers with YARPGen. Proc. ACM Program. Lang. 4 OOPSLA (2020) 196:1\u2013196:25. 10.1145\/3428264","DOI":"10.1145\/3428264"},{"key":"e_1_3_3_1_24_2","series-title":"Dagstuhl Seminar Proceedings","volume-title":"Numerical Validation in Current Hardware Architectures, 6.1. - 11.1.2008","volume":"08021","author":"Markstein Peter\u00a0W.","year":"2008","unstructured":"Peter\u00a0W. Markstein. 2008. The New IEEE-754 Standard for Floating Point Arithmetic. In Numerical Validation in Current Hardware Architectures, 6.1. - 11.1.2008(Dagstuhl Seminar Proceedings, Vol.\u00a008021), Annie A.\u00a0M. Cuyt, Walter Kr\u00e4mer, Wolfram Luther, and Peter\u00a0W. Markstein (Eds.). Internationales Begegnungs- und Forschungszentrum f\u00fcr Informatik (IBFI), Schloss Dagstuhl, Germany. http:\/\/drops.dagstuhl.de\/opus\/volltexte\/2008\/1448"},{"key":"e_1_3_3_1_25_2","unstructured":"William\u00a0M. McKeeman. 1998. Differential Testing for Software. Digit. Tech. J. 10 1 (1998) 100\u2013107. https:\/\/www.hpl.hp.com\/hpjournal\/dtj\/vol10num1\/vol10num1art9.pdf"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32041-5_20"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656618"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Christian Munley Aaron Jarmusch and Sunita Chandrasekaran. 2024. LLM4VV: Developing LLM-driven testsuite for compiler validation. Future Gener. Comput. Syst. 160 (2024) 1\u201313. 10.1016\/J.FUTURE.2024.05.034","DOI":"10.1016\/J.FUTURE.2024.05.034"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR abs\/2303.08774 (2023). arXiv:https:\/\/arXiv.org\/abs\/2303.0877410.48550\/ARXIV.2303.08774","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"e_1_3_3_1_30_2","unstructured":"OpenAI. 2025. Introducing GPT-4.1 in the API. Technical Report. https:\/\/openai.com\/research\/gpt-4-1-mini Accessed: 2025-04-14."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_3_1_32_2","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis. CoRR abs\/2009.10297 (2020). arXiv:https:\/\/arXiv.org\/abs\/2009.10297https:\/\/arxiv.org\/abs\/2009.10297"},{"key":"e_1_3_3_1_33_2","unstructured":"Chanchal\u00a0Kumar Roy and James\u00a0R Cordy. 2007. A survey on software clone detection research. Queen\u2019s School of computing TR 541 115 (2007) 64\u201368."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167780"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Max Sch\u00e4fer Sarah Nadi Aryaz Eghbali and Frank Tip. 2023. Adaptive Test Generation Using a Large Language Model. CoRR abs\/2302.06527 (2023). arXiv:https:\/\/arXiv.org\/abs\/2302.0652710.48550\/ARXIV.2302.06527","DOI":"10.48550\/ARXIV.2302.06527"},{"key":"e_1_3_3_1_36_2","first-page":"309","volume-title":"Proceedings of the 2012 USENIX Annual Technical Conference, USENIX ATC 2012, Boston, MA, USA, June 13-15, 2012","author":"Serebryany Konstantin","year":"2012","unstructured":"Konstantin Serebryany, Derek Bruening, Alexander Potapenko, and Dmitriy Vyukov. 2012. AddressSanitizer: A Fast Address Sanity Checker. In Proceedings of the 2012 USENIX Annual Technical Conference, USENIX ATC 2012, Boston, MA, USA, June 13-15, 2012, Gernot Heiser and Wilson\u00a0C. Hsieh (Eds.). USENIX Association, 309\u2013318. https:\/\/www.usenix.org\/conference\/atc12\/technical-sessions\/presentation\/serebryany"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3395363.3397380"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639121"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Chenyuan Yang Yinlin Deng Runyu Lu Jiayi Yao Jiawei Liu Reyhaneh Jabbarvand and Lingming Zhang. 2024. WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models. Proc. ACM Program. Lang. 8 OOPSLA2 (2024) 709\u2013735. 10.1145\/3689736","DOI":"10.1145\/3689736"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993532"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00030"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","unstructured":"Zhiqiang Yuan Yiling Lou Mingwei Liu Shiji Ding Kaixin Wang Yixuan Chen and Xin Peng. 2023. No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation. CoRR abs\/2305.04207 (2023). arXiv:https:\/\/arXiv.org\/abs\/2305.0420710.48550\/ARXIV.2305.04207","DOI":"10.48550\/ARXIV.2305.04207"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3062341.3062379"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3731599.3767362","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767362","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:36:40Z","timestamp":1767987400000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":42,"alternative-id":["10.1145\/3731599.3767362","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767362","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}