{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T15:57:23Z","timestamp":1792339043513,"version":"4.4.0"},"reference-count":79,"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\/icst69053.2026.00045","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:48:20Z","timestamp":1784238500000},"page":"285-296","source":"Crossref","is-referenced-by-count":2,"title":["Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models"],"prefix":"10.1109","author":[{"given":"Sabaat","family":"Haroon","sequence":"first","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad Faraz","family":"Khan","sequence":"additional","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Humayun","sequence":"additional","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Waris","family":"Gill","sequence":"additional","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul Haddi","family":"Amjad","sequence":"additional","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali R.","family":"Butt","sequence":"additional","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taha","family":"Khan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Ali","family":"Gulzar","sequence":"additional","affiliation":[{"name":"Virginia Tech,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2107.03374"},{"key":"ref2","first-page":"1234","article-title":"Can large language models reason about code?","volume":"29","author":"Li","year":"2024","journal-title":"Empirical Software Engineering"},{"key":"ref3","first-page":"89","article-title":"Large language models are humanlevel prompt engineers - but are they human-level program reasoners?","volume-title":"Proceedings of the 2025 IEEE\/ACM International Conference on Software Engineering (ICSE \u201825)","author":"Wang"},{"key":"ref4","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref5","article-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation","author":"Lu","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.482"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LLM4Code66737.2025.00005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623342"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3543187"},{"key":"ref11","article-title":"Cursor bugbot: Ai-powered code review and debugging tool","year":"2025","journal-title":"AI-driven tool that automatically reviews pull requests and detects logic bugs, edge cases, and security issues in"},{"key":"ref12","article-title":"Introducing generative AI troubleshooting for Apache Spark in AWS Glue (preview)","author":"Sekiyama","year":"2024","journal-title":"AWS Big Data Blog"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3660771"},{"key":"ref14","article-title":"Automated fault localization in 11 ms challenges and techniques","volume-title":"Proceedings of the IEEE Conference on Software Engineering","author":"Nguyen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICST62969.2025.10989036"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417943"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3526099"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2018.8330203"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSR52588.2021.00066"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.430"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106552"},{"key":"ref23","article-title":"Python code instructions 18k alpaca","author":"iamtarun","year":"2023"},{"key":"ref24","article-title":"Codesearchnet dataset","author":"Soliman","year":"2023"},{"key":"ref25","article-title":"Gpt-4 technical report","volume-title":"tech. rep., OpenAI","year":"2023"},{"key":"ref26","article-title":"Qwen","year":"2025","journal-title":"Qwen model family from Alibaba"},{"key":"ref27","article-title":"Bug in the code stack: Can 11 ms find bugs in large python code stacks","author":"Lee"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICBDSS51270.2020.00033"},{"key":"ref29","article-title":"A study of llms\u2019 p for libraries and programming languages","author":"Twist","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639219"},{"key":"ref31","article-title":"Cruxeval: a benchmark for code reasoning, understanding and execution","volume-title":"Proceedings of the 41st International Conference on Machine Learning, ICML\u201924, JMLR.org","author":"Gu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-025-10614-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628053"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MSR52588.2021.00019"},{"key":"ref35","article-title":"An empirical study of bugs in open-source federated learning framework","author":"Shao"},{"key":"ref36","article-title":"Qwen2.5-coder technical report","author":"Hui","year":"2024"},{"key":"ref37","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref38","article-title":"Phi-4 technical report","author":"Research","year":"2024"},{"key":"ref39","article-title":"Qwq-32b: Embracing the power of reinforcement learning","author":"Team","year":"2025"},{"key":"ref40","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref41","article-title":"Claude 3.7 sonnet and claude code","year":"2025"},{"key":"ref42","article-title":"Introducing gemini 2.0: Our new ai model for the agentic era","year":"2025"},{"key":"ref43","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024"},{"key":"ref44","article-title":"Gemini 2.5 flash: Model overview","year":"2024"},{"key":"ref45","article-title":"Claude 4.5 sonnet model card","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3267446"},{"key":"ref47","first-page":"150","article-title":"Understanding the impact of training data diversity on code analysis","volume-title":"Proceedings of the IEEE\/ACM International Conference on Software Engineering","volume":"1","author":"Smith"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1264"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref50","article-title":"Context rot: How increasing input tokens impacts 11 m performance","volume-title":"tech. rep.","author":"Hong","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.130"},{"key":"ref52","article-title":"Beyond surface structure: A causal assessment of LLMs\u2019 comprehension ability","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Han"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.70777\/si.v2i6.15919"},{"key":"ref54","article-title":"On the emergence of position bias in transformers","author":"Wu","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/32.988498"},{"issue":"10","key":"ref56","first-page":"1377","article-title":"Metallaxisfl: Mutation-based fault localization","volume":"39","author":"Papadakis","year":"2013","journal-title":"IEEE Transactions on Software Engineering"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2014.44"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0943"},{"key":"ref59","article-title":"Core: Benchmarking 11 ms code reasoning capabilities through static analysis tasks","author":"Xie","year":"2025"},{"key":"ref60","article-title":"Dycodeeval: Dynamic benchmarking of reasoning capabilities in code large language models under data contamination","volume-title":"Forty-second International Conference on Machine Learning","author":"Chen"},{"key":"ref61","article-title":"Livecodebench: Holistic and contamination free evaluation of large language models for code","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Jain"},{"key":"ref62","article-title":"Livebench: A challenging, contamination-limited LLM benchmark","volume-title":"The Thirteenth International Conference on Learning Representations","author":"White"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.247"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3553363"},{"key":"ref65","article-title":"Advanced debugging techniques in 11 m based code generation","volume-title":"Proceedings of the ACM International Conference on Software Engineering","author":"Smith"},{"key":"ref66","article-title":"Deep debugging enhancing l l ms for robust code analysis","volume-title":"Proceedings of the ACM Conference on Software Engineering","author":"Lee"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTW64639.2025.10962512"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1927-4_7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3696630.3728605"},{"key":"ref71","article-title":"Codemind: Evaluating large language models for code reasoning","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2402.09664"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1124"},{"key":"ref73","article-title":"Top score on the wrong exam: On benchmarking in machine learning for vulnerability detection","volume":"arXiv:2408.12986v2","author":"Risse","year":"2024","journal-title":"arXiv Preprint"},{"key":"ref74","article-title":"Ast based mutation testing for evaluating code semantics","volume-title":"Proceedings of the IEEE Software Engineering Conference","author":"Garcia"},{"key":"ref75","article-title":"Ast transformations for robust code analysis","volume-title":"Proceedings of the ACM International Conference on Software Engineering","author":"Johnson"},{"key":"ref76","article-title":"Refining semantic alterations in code via ast transformations","author":"Patel","year":"2023","journal-title":"arXiv preprint arXiv:2308.03873"},{"key":"ref77","article-title":"Evaluating semantic preserving mutations in code","author":"Wong","year":"2024","journal-title":"arXiv preprint arXiv:2402.14261"},{"key":"ref78","article-title":"A structural approach to 11 m code understanding","author":"Johnson","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref79","article-title":"Enhancing llms for code debugging via advanced mutation techniques","volume-title":"Proceedings of the ACM International Conference on Software Engineering","author":"Garcia"}],"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\/11600545.pdf?arnumber=11600545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:22:35Z","timestamp":1784265755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11600545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/icst69053.2026.00045","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}