{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T06:45:02Z","timestamp":1769755502452,"version":"3.49.0"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302021"],"award-info":[{"award-number":["62302021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62177003"],"award-info":[{"award-number":["62177003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s10664-025-10716-z","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T07:20:07Z","timestamp":1764919207000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Peer-aided repairer: empowering large language models to repair advanced student assignments"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2439-0684","authenticated-orcid":false,"given":"Qianhui","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-5893","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3905-8133","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8649-7147","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenghao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"10716_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3510418","volume":"31","author":"UZ Ahmed","year":"2021","unstructured":"Ahmed UZ, Fan Z, Yi J, Al-Bataineh OI, Roychoudhury A (2021) Verifix: Verified repair of programming assignments. ACM Trans Softw Eng Methodol (TOSEM) 31:1\u201331. https:\/\/doi.org\/10.1145\/3510418","journal-title":"ACM Trans Softw Eng Methodol (TOSEM)"},{"key":"10716_CR2","doi-asserted-by":"publisher","unstructured":"Alshahwan N, Chheda J, Finogenova A, Gokkaya B, Harman M, Harper I, Marginean A, Sengupta S, Wang E (2024) Automated unit test improvement using large language models at meta. In: Companion Proceedings of the 32nd ACM international conference on the foundations of software engineering, pp 185\u2013196. https:\/\/doi.org\/10.1145\/3663529.3663839","DOI":"10.1145\/3663529.3663839"},{"issue":"OOPSLA2","key":"10716_CR3","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1145\/3563327","volume":"6","author":"R Bavishi","year":"2022","unstructured":"Bavishi R, Joshi H, Cambronero J, Fariha A, Gulwani S, Le V, Radi\u010dek I, Tiwari A (2022) Neurosymbolic repair for low-code formula languages. Proc ACM Program Lang 6(OOPSLA2):1093\u20131122","journal-title":"Proc ACM Program Lang"},{"key":"10716_CR4","unstructured":"Ben-Nun T, Jakobovits AS, Hoefler T (2018) Neural code comprehension: a learnable representation of code semantics. Adv Neural Inf Process Syst 31"},{"key":"10716_CR5","doi-asserted-by":"publisher","unstructured":"Black S, Biderman S, Hallahan E, Anthony Q, Gao L, Golding L, He H, Leahy C, McDonell K, Phang J et al (2022) Gpt-neox-20b: an open-source autoregressive language model. arXiv:2204.06745https:\/\/doi.org\/10.48550\/ARXIV.2204.06745","DOI":"10.48550\/ARXIV.2204.06745"},{"key":"10716_CR6","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H (eds) Advances in neural information processing systems 33: annual conference on neural information processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"10716_CR7","doi-asserted-by":"publisher","unstructured":"Cao J, Li M, Wen M, Cheung S-c (2023) A study on prompt design, advantages and limitations of chatgpt for deep learning program repair. arXiv:2304.08191https:\/\/doi.org\/10.48550\/ARXIV.2304.08191","DOI":"10.48550\/ARXIV.2304.08191"},{"key":"10716_CR8","unstructured":"Chen M, Tworek J, Jun H, Yuan Q, Pinto HPdO, Kaplan J, Edwards H, Burda Y, Joseph N, Brockman G et al (2021) Evaluating large language models trained on code. arXiv:2107.03374"},{"key":"10716_CR9","doi-asserted-by":"publisher","unstructured":"Chhatbar D, Ahmed UZ, Kar P (2020) Macer: a modular framework for accelerated compilation error repair. In: International conference on artificial intelligence in education. Springer, pp 106\u2013117. https:\/\/doi.org\/10.1007\/978-3-030-52237-7_9","DOI":"10.1007\/978-3-030-52237-7_9"},{"key":"10716_CR10","doi-asserted-by":"publisher","unstructured":"De\u00a0Moura L, Bj\u00f8rner N (2008) Z3: an efficient smt solver. In: International conference on tools and algorithms for the construction and analysis of systems. Springer, pp 337\u2013340. https:\/\/doi.org\/10.1007\/978-3-540-78800-3_24","DOI":"10.1007\/978-3-540-78800-3_24"},{"key":"10716_CR11","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805https:\/\/doi.org\/10.18653\/V1\/N19-1423","DOI":"10.18653\/V1\/N19-1423"},{"key":"10716_CR12","doi-asserted-by":"publisher","unstructured":"Dong Y, Jiang X, Jin Z, Li G (2023) Self-collaboration code generation via chatgpt. arXiv:2304.07590https:\/\/doi.org\/10.48550\/ARXIV.2304.07590","DOI":"10.48550\/ARXIV.2304.07590"},{"key":"10716_CR13","doi-asserted-by":"publisher","unstructured":"Fan Z, Gao X, Mirchev M, Roychoudhury A, Tan SH (2023) Automated repair of programs from large language models. In: 2023 IEEE\/ACM 45th international conference on software engineering (ICSE). IEEE, pp 1469\u20131481. https:\/\/doi.org\/10.1109\/ICSE48619.2023.00128","DOI":"10.1109\/ICSE48619.2023.00128"},{"key":"10716_CR14","unstructured":"Fried D, Aghajanyan A, Lin J, Wang S, Wallace E, Shi F, Zhong R, Yih W-t, Zettlemoyer L, Lewis M (2022) Incoder: a generative model for code infilling and synthesis. arXiv:2204.05999"},{"key":"10716_CR15","doi-asserted-by":"publisher","unstructured":"Gazzola L, Micucci D, Mariani L (2018) Automatic software repair: a survey. In: 2018 IEEE\/ACM 40th international conference on software engineering (ICSE), pp 1219\u20131219. https:\/\/doi.org\/10.1145\/3180155.3182526","DOI":"10.1145\/3180155.3182526"},{"key":"10716_CR16","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/3318162","volume":"62","author":"CL Goues","year":"2019","unstructured":"Goues CL, Pradel M, Roychoudhury A (2019) Automated program repair. Commun ACM 62:56\u201365","journal-title":"Commun ACM"},{"key":"10716_CR17","unstructured":"Gu S, Fang C, Zhang Q, Tian F, Chen Z (2024) Testart: improving llm-based unit test via co-evolution of automated generation and repair iteration 2408"},{"issue":"4","key":"10716_CR18","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1145\/3192366.3192387","volume":"53","author":"S Gulwani","year":"2018","unstructured":"Gulwani S, Radi\u010dek I, Zuleger F (2018) Automated clustering and program repair for introductory programming assignments. ACM SIGPLAN Notices 53(4):465\u2013480. https:\/\/doi.org\/10.1145\/3192366.3192387","journal-title":"ACM SIGPLAN Notices"},{"key":"10716_CR19","doi-asserted-by":"publisher","unstructured":"Guo D, Lu S, Duan N, Wang Y, Zhou M, Yin J (2022) Unixcoder: unified cross-modal pre-training for code representation. In: Proceedings of the 60th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp 7212\u20137225. https:\/\/doi.org\/10.18653\/V1\/2022.ACL-LONG.499","DOI":"10.18653\/V1\/2022.ACL-LONG.499"},{"key":"10716_CR20","doi-asserted-by":"publisher","unstructured":"Gupta R, Pal S, Kanade A, Shevade S (2017) Deepfix: fixing common c language errors by deep learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 31. https:\/\/doi.org\/10.1609\/AAAI.V31I1.10742","DOI":"10.1609\/AAAI.V31I1.10742"},{"key":"10716_CR21","doi-asserted-by":"publisher","unstructured":"He Y, Chen Z, Le\u00a0Goues C (2023) Precisebugcollector: extensible, executable and precise bug-fix collection: solution for challenge 8: automating precise data collection for code snippets with bugs, fixes, locations, and types. In: 2023 38th IEEE\/ACM international conference on automated software engineering (ASE). IEEE, pp 1899\u20131910. https:\/\/doi.org\/10.1109\/ASE56229.2023.00163","DOI":"10.1109\/ASE56229.2023.00163"},{"key":"10716_CR22","doi-asserted-by":"publisher","unstructured":"Hu Y, Ahmed UZ, Mechtaev S, Leong B, Roychoudhury A (2019) Re-factoring based program repair applied to programming assignments. In: 2019 34th IEEE\/ACM international conference on automated software engineering (ASE). IEEE\/ACM, pp 388\u2013398. https:\/\/doi.org\/10.1109\/ASE.2019.00044","DOI":"10.1109\/ASE.2019.00044"},{"key":"10716_CR23","doi-asserted-by":"publisher","unstructured":"Jiang N, Liu K, Lutellier T, Tan L (2023) Impact of code language models on automated program repair. arXiv:2302.05020https:\/\/doi.org\/10.1109\/ICSE48619.2023.00125","DOI":"10.1109\/ICSE48619.2023.00125"},{"key":"10716_CR24","doi-asserted-by":"publisher","unstructured":"Jiang N, Lutellier T, Tan L (2021) Cure: code-aware neural machine translation for automatic program repair. In: 2021 IEEE\/ACM 43rd international conference on software engineering (ICSE). IEEE, pp 1161\u20131173. https:\/\/doi.org\/10.1109\/ICSE43902.2021.00107","DOI":"10.1109\/ICSE43902.2021.00107"},{"key":"10716_CR25","doi-asserted-by":"publisher","unstructured":"Joshi H, Sanchez JC, Gulwani S, Le V, Verbruggen G, Radi\u010dek I (2023) Repair is nearly generation: Multilingual program repair with llms. In: Proceedings of the AAAI conference on artificial intelligence, vol 37, pp 5131\u20135140. https:\/\/doi.org\/10.1609\/AAAI.V37I4.25642","DOI":"10.1609\/AAAI.V37I4.25642"},{"key":"10716_CR26","doi-asserted-by":"publisher","unstructured":"Just R, Jalali D, Ernst MD (2014) Defects4j: a database of existing faults to enable controlled testing studies for java programs. In: Proceedings of the 2014 international symposium on software testing and analysis, pp 437\u2013440. https:\/\/doi.org\/10.1145\/2610384.2628055","DOI":"10.1145\/2610384.2628055"},{"issue":"1","key":"10716_CR27","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/TSE.2011.104","volume":"38","author":"C Le Goues","year":"2011","unstructured":"Le Goues C, Nguyen T, Forrest S, Weimer W (2011) Genprog: A generic method for automatic software repair. IEEE Trans Softw Eng 38(1):54\u201372. https:\/\/doi.org\/10.1109\/TSE.2011.104","journal-title":"IEEE Trans Softw Eng"},{"issue":"12","key":"10716_CR28","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TSE.2015.2454513","volume":"41","author":"C Le Goues","year":"2015","unstructured":"Le Goues C, Holtschulte N, Smith EK, Brun Y, Devanbu P, Forrest S, Weimer W (2015) The manybugs and introclass benchmarks for automated repair of c programs. IEEE Trans Softw Eng 41(12):1236\u20131256. https:\/\/doi.org\/10.1109\/TSE.2015.2454513","journal-title":"IEEE Trans Softw Eng"},{"key":"10716_CR29","doi-asserted-by":"publisher","unstructured":"Le X-BD, Chu D-H, Lo D, Le\u00a0Goues C, Visser W (2017) Jfix: semantics-based repair of java programs via symbolic pathfinder. In: Proceedings of the 26th ACM SIGSOFT international symposium on software testing and analysis, pp 376\u2013379. https:\/\/doi.org\/10.1145\/3092703.3098225","DOI":"10.1145\/3092703.3098225"},{"key":"10716_CR30","unstructured":"Li R, Allal LB, Zi Y, Muennighoff N, Kocetkov D, Mou C, Marone M, Akiki C, Li J, Chim J et al (2023) Starcoder: may the source be with you! arXiv:2305.06161"},{"key":"10716_CR31","doi-asserted-by":"publisher","unstructured":"Lin D, Koppel J, Chen A, Solar-Lezama A (2017) Quixbugs: a multi-lingual program repair benchmark set based on the quixey challenge. In: Proceedings Companion of the 2017 ACM SIGPLAN international conference on systems, programming, languages, and applications: software for humanity, pp 55\u201356. https:\/\/doi.org\/10.1145\/3135932.3135941","DOI":"10.1145\/3135932.3135941"},{"issue":"9","key":"10716_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2023) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput Surv 55(9):1\u201335. https:\/\/doi.org\/10.1145\/3560815","journal-title":"ACM Comput Surv"},{"key":"10716_CR33","doi-asserted-by":"publisher","unstructured":"Liu K, Koyuncu A, Kim D, Bissyand\u00e9 TF (2019) Tbar: revisiting template-based automated program repair. In: Proceedings of the 28th ACM SIGSOFT international symposium on software testing and analysis, pp 31\u201342. https:\/\/doi.org\/10.1145\/3293882.3330577","DOI":"10.1145\/3293882.3330577"},{"key":"10716_CR34","unstructured":"Masters K (2011) A brief guide to understanding moocs"},{"key":"10716_CR35","doi-asserted-by":"publisher","unstructured":"Mechtaev S, Yi J, Roychoudhury A (2016) Angelix: scalable multiline program patch synthesis via symbolic analysis. In: Proceedings of the 38th international conference on software engineering, pp 691\u2013701. https:\/\/doi.org\/10.1145\/2884781.2884807","DOI":"10.1145\/2884781.2884807"},{"key":"10716_CR36","doi-asserted-by":"publisher","unstructured":"Nguyen HDT, Qi D, Roychoudhury A, Chandra S (2013) Semfix: program repair via semantic analysis. In: 2013 35th International conference on software engineering (ICSE). IEEE, pp 772\u2013781. https:\/\/doi.org\/10.1109\/ICSE.2013.6606623","DOI":"10.1109\/ICSE.2013.6606623"},{"key":"10716_CR37","unstructured":"Nijkamp E, Pang B, Hayashi H, Tu L, Wang H, Zhou Y, Savarese S, Xiong C (2022) Codegen: an open large language model for code with multi-turn program synthesis. arXiv:2203.13474"},{"key":"10716_CR38","unstructured":"OpenAI (2022) ChatGPT: optimizing language models for dialogue. https:\/\/openai.com\/blog\/chatgpt"},{"key":"10716_CR39","doi-asserted-by":"crossref","unstructured":"Pu Y, Narasimhan K, Solar-Lezama A, Barzilay R (2016) sk_p: a neural program corrector for moocs. In: Companion Proceedings of the 2016 ACM SIGPLAN international conference on systems, programming, languages and applications: software for humanity, pp 39\u201340","DOI":"10.1145\/2984043.2989222"},{"key":"10716_CR40","doi-asserted-by":"publisher","unstructured":"Qi Y, Mao X, Lei Y (2013) Efficient automated program repair through fault-recorded testing prioritization. In: 2013 IEEE international conference on software maintenance. IEEE, pp 180\u2013189. https:\/\/doi.org\/10.1109\/ICSM.2013.29","DOI":"10.1109\/ICSM.2013.29"},{"key":"10716_CR41","first-page":"140","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:140\u2013114067","journal-title":"J Mach Learn Res"},{"key":"10716_CR42","doi-asserted-by":"publisher","unstructured":"Ren S, Guo D, Lu S, Zhou L, Liu S, Tang D, Sundaresan N, Zhou M, Blanco A, Ma S (2020) Codebleu: a method for automatic evaluation of code synthesis. arXiv:2009.10297https:\/\/doi.org\/10.48550\/ARXIV.2206.08474","DOI":"10.48550\/ARXIV.2206.08474"},{"key":"10716_CR43","doi-asserted-by":"publisher","unstructured":"Rolim R, Soares G, D\u2019Antoni L, Polozov O, Gulwani S, Gheyi R, Suzuki R, Hartmann B (2017) Learning syntactic program transformations from examples. In: 2017 IEEE\/ACM 39th international conference on software engineering (ICSE). IEEE, pp 404\u2013415. https:\/\/doi.org\/10.1109\/ICSE.2017.44","DOI":"10.1109\/ICSE.2017.44"},{"key":"10716_CR44","doi-asserted-by":"publisher","unstructured":"Roziere B, Gehring J, Gloeckle F, Sootla S, Gat I, Tan XE, Adi Y, Liu J, Remez T, Rapin J et al (2023) Code llama: open foundation models for code. arXiv:2308.12950https:\/\/doi.org\/10.48550\/ARXIV.2308.12950","DOI":"10.48550\/ARXIV.2308.12950"},{"key":"10716_CR45","doi-asserted-by":"publisher","unstructured":"Silva A, Fang S, Monperrus M (2023) Repairllama: efficient representations and fine-tuned adapters for program repair. arXiv:2312.15698https:\/\/doi.org\/10.48550\/ARXIV.2312.15698","DOI":"10.48550\/ARXIV.2312.15698"},{"key":"10716_CR46","doi-asserted-by":"publisher","unstructured":"Singh R, Gulwani S, Solar-Lezama A (2013) Automated feedback generation for introductory programming assignments. In: Proceedings of the 34th ACM SIGPLAN conference on programming language design and implementation, pp 15\u201326. https:\/\/doi.org\/10.1145\/2491956.2462195","DOI":"10.1145\/2491956.2462195"},{"key":"10716_CR47","doi-asserted-by":"publisher","unstructured":"Sobreira V, Durieux T, Madeiral F, Monperrus M, Almeida\u00a0Maia M (2018) Dissection of a bug dataset: anatomy of 395 patches from defects4j. In: 2018 IEEE 25th international conference on software analysis, evolution and reengineering (SANER). IEEE, pp 130\u2013140. https:\/\/doi.org\/10.1109\/SANER.2018.8330203","DOI":"10.1109\/SANER.2018.8330203"},{"key":"10716_CR48","doi-asserted-by":"publisher","unstructured":"Tan SH, Yi J, Mechtaev S, Roychoudhury A et al (2017) Codeflaws: a programming competition benchmark for evaluating automated program repair tools. In: 2017 IEEE\/ACM 39th international conference on software engineering companion (ICSE-C). IEEE, pp 180\u2013182. https:\/\/doi.org\/10.1109\/ICSE-C.2017.76","DOI":"10.1109\/ICSE-C.2017.76"},{"key":"10716_CR49","doi-asserted-by":"publisher","unstructured":"Touvron H, Lavril T, Izacard G, Martinet X, Lachaux M-A, Lacroix T, Rozi\u00e8re B, Goyal N, Hambro E, Azhar F et al (2023) Llama: open and efficient foundation language models. arXiv:2302.13971https:\/\/doi.org\/10.48550\/ARXIV.2302.13971","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"10716_CR50","doi-asserted-by":"publisher","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S et al (2023) Llama 2: open foundation and fine-tuned chat models. arXiv:2307.09288https:\/\/doi.org\/10.48550\/ARXIV.2307.09288","DOI":"10.48550\/ARXIV.2307.09288"},{"key":"10716_CR51","doi-asserted-by":"publisher","unstructured":"Trotman A, Puurula A, Burgess B (2014) Improvements to bm25 and language models examined. In: Proceedings of the 19th australasian document computing symposium, pp 58\u201365. https:\/\/doi.org\/10.1145\/2682862.2682863","DOI":"10.1145\/2682862.2682863"},{"key":"10716_CR52","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"10716_CR53","unstructured":"Wang B, Komatsuzaki A (2021) GPT-J-6B: A 6 billion parameter autoregressive language model"},{"key":"10716_CR54","doi-asserted-by":"publisher","unstructured":"Wang K, Singh R, Su Z (2018) Search, align, and repair: data-driven feedback generation for introductory programming exercises. In: Proceedings of the 39th ACM SIGPLAN conference on programming language design and implementation, pp 481\u2013495. https:\/\/doi.org\/10.1145\/3192366.3192384","DOI":"10.1145\/3192366.3192384"},{"key":"10716_CR55","doi-asserted-by":"publisher","unstructured":"Weimer W, Fry ZP, Forrest S (2013) Leveraging program equivalence for adaptive program repair: models and first results. In: 2013 28th IEEE\/ACM international conference on automated software engineering (ASE). IEEE, pp 356\u2013366. https:\/\/doi.org\/10.1109\/ASE.2013.6693094","DOI":"10.1109\/ASE.2013.6693094"},{"key":"10716_CR56","doi-asserted-by":"publisher","unstructured":"Xia CS, Wei Y, Zhang L (2022) Practical program repair in the era of large pre-trained language models. arXiv:2210.14179https:\/\/doi.org\/10.48550\/ARXIV.2210.14179","DOI":"10.48550\/ARXIV.2210.14179"},{"key":"10716_CR57","doi-asserted-by":"publisher","unstructured":"Xia CS, Zhang L (2023) Keep the conversation going: fixing 162 out of 337 bugs for \\$0.42 each using chatgpt. arXiv:2304.00385https:\/\/doi.org\/10.48550\/ARXIV.2304.00385","DOI":"10.48550\/ARXIV.2304.00385"},{"key":"10716_CR58","unstructured":"Yasunaga M, Liang P (2021) Break-it-fix-it: unsupervised learning for program repair. In: International conference on machine learning. PMLR, pp 11941\u201311952"},{"key":"10716_CR59","doi-asserted-by":"publisher","unstructured":"Ye H, Martinez M, Luo X, Zhang T, Monperrus M (2022) Selfapr: self-supervised program repair with test execution diagnostics. In: 2022 37th IEEE. In: ACM international conference on automated software engineering (ASE\u201922), IEEE. https:\/\/doi.org\/10.1145\/3551349.3556926","DOI":"10.1145\/3551349.3556926"},{"key":"10716_CR60","doi-asserted-by":"publisher","unstructured":"Ye H, Martinez M, Monperrus M (2022) Neural program repair with execution-based backpropagation. In: Proceedings of the 44th international conference on software engineering, pp 1506\u20131518. https:\/\/doi.org\/10.1145\/3510003.3510222","DOI":"10.1145\/3510003.3510222"},{"key":"10716_CR61","doi-asserted-by":"publisher","unstructured":"Yi J, Ahmed UZ, Karkare A, Tan SH, Roychoudhury A (2017) A feasibility study of using automated program repair for introductory programming assignments. In: Proceedings of the 2017 11th joint meeting on foundations of software engineering, pp 740\u2013751. https:\/\/doi.org\/10.1145\/3106237.3106262","DOI":"10.1145\/3106237.3106262"},{"key":"10716_CR62","doi-asserted-by":"publisher","unstructured":"Yuan Z, Lou Y, Liu M, Ding S, Wang K, Chen Y, Peng X (2023) No more manual tests? evaluating and improving chatgpt for unit test generation. arXiv:2305.04207https:\/\/doi.org\/10.48550\/ARXIV.2305.04207","DOI":"10.48550\/ARXIV.2305.04207"},{"issue":"6","key":"10716_CR63","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1137\/0218082","volume":"18","author":"K Zhang","year":"1989","unstructured":"Zhang K, Shasha D (1989) Simple fast algorithms for the editing distance between trees and related problems. SIAM J Comput 18(6):1245\u20131262. https:\/\/doi.org\/10.1137\/0218082","journal-title":"SIAM J Comput"},{"key":"10716_CR64","doi-asserted-by":"publisher","unstructured":"Zhang J, Cambronero J, Gulwani S, Le V, Piskac R, Soares G, Verbruggen G (2022) Repairing bugs in python assignments using large language models. arXiv:2209.14876https:\/\/doi.org\/10.48550\/ARXIV.2209.14876","DOI":"10.48550\/ARXIV.2209.14876"},{"key":"10716_CR65","doi-asserted-by":"crossref","unstructured":"Zhang J, Li D, Kolesar JC, Shi H, Piskac R (2022) Automated feedback generation for competition-level code. In: Proceedings of the 37th IEEE\/ACM international conference on automated software engineering, pp 1\u201313","DOI":"10.1145\/3551349.3560425"},{"key":"10716_CR66","unstructured":"Zhu M, Jain A, Suresh K, Ravindran R, Tipirneni S, Reddy CK (2022) Xlcost: a benchmark dataset for cross-lingual code intelligence. arXiv:2206.08474"},{"key":"10716_CR67","doi-asserted-by":"publisher","unstructured":"Zhu Q, Sun Z, Xiao Y-a, Zhang W, Yuan K, Xiong Y, Zhang L (2021) A syntax-guided edit decoder for neural program repair. In: Proceedings of the 29th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering, pp 341\u2013353. https:\/\/doi.org\/10.1145\/3468264.3468544","DOI":"10.1145\/3468264.3468544"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10716-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10716-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10716-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T04:33:29Z","timestamp":1768365209000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10716-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,5]]},"references-count":67,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10716"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10716-z","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,5]]},"assertion":[{"value":"28 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable to this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this paper.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not applicable to this study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"Not applicable to this study.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical Trial Number"}}],"article-number":"33"}}