{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:19Z","timestamp":1784268379834,"version":"3.55.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/icst69053.2026.00041","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:48:20Z","timestamp":1784238500000},"page":"244-255","source":"Crossref","is-referenced-by-count":0,"title":["Improving Automated Patch Correctness Assessment by Designing LLM-Based Oracles"],"prefix":"10.1109","author":[{"given":"Inyeong","family":"Jang","sequence":"first","affiliation":[{"name":"Duksung Women’s University,Department of Computer Science, Engineering and Converged Technology,Seoul,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University,Department of Software,Suwon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3318162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2771783.2771791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786825"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3511096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180182"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534368"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICST60714.2024.00036"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3452252"},{"key":"ref9","article-title":"Repaca: Leveraging reasoning large language models for static automated patch correctness assessment","author":"Fuster-Pena","year":"2025","journal-title":"arXiv preprint arXiv:2507.22580"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.104"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-016-9470-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2560811"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2017.45"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2016.76"},{"key":"ref16","volume-title":"Gpt-4o: System card","year":"2024"},{"key":"ref17","volume-title":"gpt-4o mini: Efficient multimodal language model","year":"2024"},{"key":"ref18","volume-title":"the llama 3.2 language model","author":"AI","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2019.8667970"},{"key":"ref20","article-title":"Marscode agent: Ai-native automated bug fixing","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2409.00899"},{"key":"ref21","first-page":"2215","article-title":"Automated repair of multi-fault programs: Obstacles, approaches, and prospects","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering","author":"Al-Bataineh"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664646.3664770"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608132"},{"key":"ref24","first-page":"1706","article-title":"Enhancing automated program repair with solution design","volume-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering","author":"Zhao"},{"key":"ref25","article-title":"Semantic-guided search for efficient program repair with large language models","author":"Le-Cong","year":"2024","journal-title":"arXiv preprint arXiv:2410.16655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18535\/ijecs.v13i12.4956"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.197"},{"key":"ref28","first-page":"arXiv-2404","article-title":"Llm-powered test case generation for detecting tricky bugs","author":"Liu","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref29","article-title":"The prompt alchemist: Automated llm -tailored prompt optimization for test case generation","author":"Gao","year":"2025","journal-title":"arXiv preprint arXiv:2501.01329"},{"key":"ref30","first-page":"968","article-title":"Automated patch correctness assessment: How far are we?","volume-title":"Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00064"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3255177"},{"key":"ref33","article-title":"Patchzero: Zero-shot automatic patch correctness assessment","author":"Zhou","year":"2023","journal-title":"arXiv preprint arXiv:2303.00202"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3505247"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3617850"},{"key":"ref36","article-title":"Exploring and evaluating hallucinations in llm-powered code generation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2404.00971"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3428972"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MedAI59581.2023.00044"},{"key":"ref39","article-title":"A survey on code generation with 11 m -based agents","author":"Dong","year":"2025","journal-title":"arXiv preprint arXiv:2508.00083"},{"key":"ref40","first-page":"arXiv\u20132308","article-title":"Llm is like a box of chocolates: the non-determinism of chatgpt in code generation","author":"Ouyang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30185"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663801"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WIECON-ECE60392.2023.10456393"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3769082"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icse55347.2025.00038"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3092703.3092718"}],"event":{"name":"2026 IEEE International Conference on Software Testing, Verification and Validation (ICST)","location":"Daejeon, Korea, Republic of","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,22]]}},"container-title":["2026 IEEE International Conference on Software Testing, Verification and Validation (ICST)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11600401\/11600462\/11600469.pdf?arnumber=11600469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:27:19Z","timestamp":1784266039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11600469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icst69053.2026.00041","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}