{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:10:38Z","timestamp":1750824638574,"version":"3.41.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302021","62177003"],"award-info":[{"award-number":["62302021","62177003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JK2024-28"],"award-info":[{"award-number":["JK2024-28"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tse.2025.3564599","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:40:18Z","timestamp":1745602818000},"page":"1685-1701","source":"Crossref","is-referenced-by-count":0,"title":["On the Applicability of Code Language Models to Scientific Computing Programs"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2439-0684","authenticated-orcid":false,"given":"Qianhui","family":"Zhao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3905-8133","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0809-7470","authenticated-orcid":false,"given":"Xiao","family":"Long","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0195-0684","authenticated-orcid":false,"given":"Chengru","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-5893","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.449"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"article-title":"Program synthesis with large language models","year":"2021","author":"Austin","key":"ref4"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for MTevaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Meas. Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref6","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-46002-9_24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3267446"},{"article-title":"MCEVAL: Massively multilingual code evaluation","year":"2024","author":"Chai","key":"ref9"},{"article-title":"Training and evaluating a jupyter notebook data science assistant","year":"2022","author":"Chandel","key":"ref10"},{"article-title":"Evaluating large language models trained on code","year":"2021","author":"Chen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00182"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.728"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"article-title":"Incoder: A generative model for code infilling and synthesis","year":"2022","author":"Fried","key":"ref15"},{"article-title":"The pile: An 800gb dataset of diverse text for language modeling","year":"2020","author":"Gao","key":"ref16"},{"year":"2022","key":"ref17","article-title":"Codeparrot"},{"key":"ref18","article-title":"GraphcodeBERT: Pre-training code representations with data flow","volume-title":"Proc. Iclr","author":"Guo","year":"2021"},{"article-title":"Deepseek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning","year":"2025","author":"Guo","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/nnnnnnn.nnnnnnn"},{"key":"ref21","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"Proc. ICLR","author":"He","year":"2022"},{"article-title":"Measuring coding challenge competence with APPs","year":"2021","author":"Hendrycks","key":"ref22"},{"key":"ref23","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref24"},{"article-title":"The stack: 3 tb of permissively licensed source code","year":"2022","author":"Kocetkov","key":"ref25"},{"article-title":"Unsupervised translation of programming languages","year":"2020","author":"Lachaux","key":"ref26"},{"key":"ref27","first-page":"14967","article-title":"DOBF: A deobfuscation pre-training objective for programming languages","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lachaux","year":"2021"},{"key":"ref28","first-page":"18319","article-title":"DS-1000: A natural and reliable benchmark for data science code generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lai","year":"2023"},{"key":"ref29","first-page":"21314","article-title":"CodeRL: Mastering code generation through pretrained models and deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Le","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.4324\/9781003022022-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1108\/ws.2000.07949fab.004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref34","first-page":"473","article-title":"Multi-task learning based pre-trained language model for code completion","volume-title":"Proc. 35th IEEE\/ACM Int. Conf. Automated Softw. Eng.","author":"Liu","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510154"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3649594"},{"key":"ref37","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","volume-title":"Proc. NeurIPS Datasets Benchmarks","author":"Lu","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.431"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"1372","DOI":"10.1145\/3377811.3380926","article-title":"Suggesting natural method names to check name consistencies","volume-title":"Proc. ACM\/IEEE 42nd Int. Conf. Softw. Eng.","author":"Nguyen","year":"2020"},{"article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","year":"2022","author":"Nijkamp","key":"ref40"},{"year":"2022","key":"ref41","article-title":"ChatGPT: Optimizing language models for dialogue"},{"key":"ref42","first-page":"26619","article-title":"Measuring the impact of programming language distribution","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Orlanski","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"issue":"140","key":"ref44","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SCAM52516.2021.00028"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-023-01832-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468588"},{"article-title":"Code Llama: Open foundation models for code","year":"2023","author":"Roziere","key":"ref48"},{"article-title":"Programming puzzles","year":"2021","author":"Schuster","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.12"},{"article-title":"Tag-LLM: Repurposing general-purpose LLMs for specialized domains","year":"2024","author":"Shen","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549145"},{"key":"ref53","first-page":"5966","article-title":"Boosting code summarization by embedding code structures","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Son","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.231"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6430"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3715964"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"article-title":"Pretraining and updating language-and domain-specific large language model: A case study in Japanese business domain","year":"2024","author":"Takahashi","key":"ref58"},{"article-title":"Exploration and adaptation of large language models for specialized domains","year":"2023","author":"Aken","key":"ref59"},{"key":"ref60","first-page":"65030","article-title":"Grammar prompting for domain-specific language generation with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054857"},{"article-title":"SyncoBERT: Syntax-guided multi-modal contrastive pre-training for code representation","year":"2021","author":"Wang","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.301"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2022.107130"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.151"},{"article-title":"Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence","year":"2024","author":"Zhu","key":"ref68"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11048386\/10977820.pdf?arnumber=10977820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T17:34:16Z","timestamp":1750786456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10977820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":68,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tse.2025.3564599","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"type":"print","value":"0098-5589"},{"type":"electronic","value":"1939-3520"},{"type":"electronic","value":"2326-3881"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}