{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:23:41Z","timestamp":1778779421615,"version":"3.51.4"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0711404"],"award-info":[{"award-number":["2022YFF0711404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018592","name":"\u201c333 Project\u201d of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018592","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Nanjing University - China Mobile Communications Group Co., Ltd. Joint Institute"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Softw Eng"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10515-025-00502-y","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T07:40:23Z","timestamp":1743752423000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An empirical study on the code naturalness modeling capability for LLMs in automated patch correctness assessment"],"prefix":"10.1007","volume":"32","author":[{"given":"Yuning","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenkang","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongwen","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jidong","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,2]]},"reference":[{"key":"502_CR1","doi-asserted-by":"crossref","unstructured":"Allamanis, M., Sutton, C.: Mining source code repositories at massive scale using language modeling. In: 2013 10th Working Conference on Mining Software Repositories (MSR), pp. 207\u2013216. IEEE (2013)","DOI":"10.1109\/MSR.2013.6624029"},{"key":"502_CR2","doi-asserted-by":"crossref","unstructured":"Barr, E.T., Brun, Y., Devanbu, P., Harman, M., Sarro, F.: The plastic surgery hypothesis. In: Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering, pp. 306\u2013317 (2014)","DOI":"10.1145\/2635868.2635898"},{"key":"502_CR3","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6\u201312 Dec 2020, Virtual (2020)"},{"key":"502_CR4","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.D.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"issue":"9","key":"502_CR5","first-page":"1943","volume":"47","author":"Z Chen","year":"2019","unstructured":"Chen, Z., Kommrusch, S., Tufano, M., Pouchet, L.-N., Poshyvanyk, D., Monperrus, M.: Sequencer: sequence-to-sequence learning for end-to-end program repair. IEEE Trans. Softw. Eng. 47(9), 1943\u20131959 (2019)","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"8","key":"502_CR6","first-page":"3015","volume":"33","author":"Z Chen","year":"2021","unstructured":"Chen, Z., Yan, M., Xia, X., Liu, Z., Xu, Z., Lei, Y.: Research progress of code naturalness and its application. J. Softw. 33(8), 3015\u20133034 (2021)","journal-title":"J. Softw."},{"key":"502_CR7","volume-title":"Statistical Power Analysis for the Behavioral Sciences","author":"J Cohen","year":"1977","unstructured":"Cohen, J.: Statistical Power Analysis for the Behavioral Sciences. Academic Press, New York (1977)"},{"key":"502_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 Jun 2019, vol. 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"key":"502_CR9","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al.: Codebert: a pre-trained model for programming and natural languages. In: Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16\u201320 Nov 2020, pp. 1536\u20131547 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"502_CR10","unstructured":"Fried, D., Aghajanyan, A., Lin, J., Wang, S., Wallace, E., Shi, F., Zhong, R., Yih, W.-t., Zettlemoyer, L., Lewis, M.: Incoder: A generative model for code infilling and synthesis (2022). arXiv preprint arXiv:2204.05999"},{"key":"502_CR11","doi-asserted-by":"crossref","unstructured":"Gabel, M., Su, Z.: A study of the uniqueness of source code. In: Proceedings of the Eighteenth ACM SIGSOFT International Symposium on Foundations of Software Engineering, pp. 147\u2013156 (2010)","DOI":"10.1145\/1882291.1882315"},{"key":"502_CR12","doi-asserted-by":"crossref","unstructured":"Ghanbari, A., Benton, S., Zhang, L.: Practical program repair via bytecode mutation. In: Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 19\u201330 (2019)","DOI":"10.1145\/3293882.3330559"},{"key":"502_CR13","doi-asserted-by":"crossref","unstructured":"Guerrouj, L., Bourque, D., Rigby, P.C.: Leveraging informal documentation to summarize classes and methods in context. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering, vol. 2, pp. 639\u2013 642. IEEE (2015)","DOI":"10.1109\/ICSE.2015.212"},{"key":"502_CR14","doi-asserted-by":"crossref","unstructured":"Guo, D., Lu, S., Duan, N., Wang, Y., Zhou, M., Yin, J.: Unixcoder: Unified cross-modal pre-training for code representation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 7212\u20137225 (2022)","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"502_CR15","doi-asserted-by":"crossref","unstructured":"Hindle, A., Barr, E.T., Su, Z., Gabel, M., Devanbu, P.: On the naturalness of software. In: 2012 34th International Conference on Software Engineering (ICSE), pp. 837\u2013847 (2012)","DOI":"10.1109\/ICSE.2012.6227135"},{"key":"502_CR16","unstructured":"Husain, H., Wu, H.-H., Gazit, T., Allamanis, M., Brockschmidt, M.: Codesearchnet challenge: evaluating the state of semantic code search (2019). arXiv preprint arXiv:1909.09436"},{"issue":"9","key":"502_CR17","first-page":"2665","volume":"32","author":"J Jiang","year":"2021","unstructured":"Jiang, J., Chen, J., Xiong, Y.: Survey of automatic program repair techniques. J. Softw. 32(9), 2665\u20132690 (2021)","journal-title":"J. Softw."},{"key":"502_CR18","doi-asserted-by":"crossref","unstructured":"Just, R., Jalali, D., Ernst, M.D.: 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 (2014)","DOI":"10.1145\/2610384.2628055"},{"key":"502_CR19","doi-asserted-by":"crossref","unstructured":"Kang, S., Yoo, S.: Language models can prioritize patches for practical program patching. In: Proceedings of the 3rd International Workshop on Automated Program Repair, pp. 8\u201315 (2022)","DOI":"10.1145\/3524459.3527343"},{"key":"502_CR20","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., Amodei, D.: Scaling laws for neural language models (2020). arXiv preprint arXiv:2001.08361"},{"key":"502_CR21","unstructured":"Kolak, S.D., Martins, R., Le\u00a0Goues, C., Hellendoorn, V.J.: Patch generation with language models: feasibility and scaling behavior. In: Deep Learning for Code Workshop (2022)"},{"key":"502_CR22","doi-asserted-by":"crossref","unstructured":"Le, X.-B.D., Chu, D.-H., Lo, D., Le\u00a0Goues, C., Visser, W.: S3: syntax-and semantic-guided repair synthesis via programming by examples. In: Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering, pp. 593\u2013604 (2017)","DOI":"10.1145\/3106237.3106309"},{"key":"502_CR23","unstructured":"Li, R., Allal, L.B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J., et al.: Starcoder: may the source be with you! (2023) arXiv preprint arXiv:2305.06161"},{"key":"502_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, Y., Lyu, M.R., King, I.: Code completion with neural attention and pointer networks. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 4159\u20134165. International Joint Conferences on Artificial Intelligence Organization (2018)","DOI":"10.24963\/ijcai.2018\/578"},{"key":"502_CR25","doi-asserted-by":"crossref","unstructured":"Lin, D., Koppel, J., Chen, A., Solar-Lezama, A.: 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 (2017)","DOI":"10.1145\/3135932.3135941"},{"key":"502_CR26","doi-asserted-by":"crossref","unstructured":"Liu, K., Koyuncu, A., Kim, D., Bissyand\u00e9, T.F.: Tbar: Revisiting template-based automated program repair. In: Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 31\u201342 (2019)","DOI":"10.1145\/3293882.3330577"},{"key":"502_CR27","doi-asserted-by":"crossref","unstructured":"Liu, K., Wang, S., Koyuncu, A., Kim, K., Bissyand\u00e9, T.F., Kim, D., Wu, P., Klein, J., Mao, X., Traon, Y.L.: On the efficiency of test suite based program repair: a systematic assessment of 16 automated repair systems for java programs. In: Proceedings of the ACM\/IEEE 42nd International Conference on Software Engineering, pp. 615\u2013627 (2020)","DOI":"10.1145\/3377811.3380338"},{"key":"502_CR28","doi-asserted-by":"crossref","unstructured":"Lutellier, T., Pham, H.V., Pang, L., Li, Y., Wei, M., Tan, L.: Coconut: combining context-aware neural translation models using ensemble for program repair. In: Proceedings of the 29th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 101\u2013114 (2020)","DOI":"10.1145\/3395363.3397369"},{"key":"502_CR29","doi-asserted-by":"crossref","unstructured":"Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 50\u201360 (1947)","DOI":"10.1214\/aoms\/1177730491"},{"key":"502_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen, A.T., Nguyen, T.N.: Graph-based statistical language model for code. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering, vol. 1, pp. 858\u2013868. IEEE (2015)","DOI":"10.1109\/ICSE.2015.336"},{"key":"502_CR31","doi-asserted-by":"crossref","unstructured":"Qi, Z., Long, F., Achour, S., Rinard, M.: An analysis of patch plausibility and correctness for generate-and-validate patch generation systems. In: Proceedings of the 2015 International Symposium on Software Testing and Analysis, pp. 24\u201336 (2015)","DOI":"10.1145\/2771783.2771791"},{"key":"502_CR32","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning. Technical report, OpenAI (2018)"},{"issue":"140","key":"502_CR33","first-page":"1","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, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"502_CR34","doi-asserted-by":"crossref","unstructured":"Ray, B., Hellendoorn, V., Godhane, S., Tu, Z., Bacchelli, A., Devanbu, P.: On the naturalness of buggy code. In: Proceedings of the 38th International Conference on Software Engineering, pp. 428\u2013439 (2016)","DOI":"10.1145\/2884781.2884848"},{"key":"502_CR35","doi-asserted-by":"crossref","unstructured":"Raychev, V., Vechev, M., Yahav, E.: Code completion with statistical language models. In: Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 419\u2013428 (2014)","DOI":"10.1145\/2594291.2594321"},{"key":"502_CR36","unstructured":"Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X.E., Adi, Y., Liu, J., Remez, T., Rapin, J., et al.: Code llama: open foundation models for code (2023). arXiv preprint arXiv:2308.12950"},{"key":"502_CR37","doi-asserted-by":"crossref","unstructured":"Santos, E.A., Campbell, J.C., Patel, D., Hindle, A., Amaral, J.N.: Syntax and sensibility: using language models to detect and correct syntax errors. In: 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 311\u2013322. IEEE (2018)","DOI":"10.1109\/SANER.2018.8330219"},{"key":"502_CR38","doi-asserted-by":"crossref","unstructured":"Shi, E., Wang, Y., Gu, W., Du, L., Zhang, H., Han, S., Zhang, D., Sun, H.: Cocosoda: effective contrastive learning for code search. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp. 2198\u20132210. IEEE (2023)","DOI":"10.1109\/ICSE48619.2023.00185"},{"key":"502_CR39","doi-asserted-by":"crossref","unstructured":"Smith, E.K., Barr, E.T., Le\u00a0Goues, C., Brun, Y.: Is the cure worse than the disease? Overfitting in automated program repair. In: Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering, pp. 532\u2013543 (2015)","DOI":"10.1145\/2786805.2786825"},{"key":"502_CR40","doi-asserted-by":"crossref","unstructured":"Tian, H., Liu, K., Kabor\u00e9, A.K., Koyuncu, A., Li, L., Klein, J., Bissyand\u00e9, T.F.: Evaluating representation learning of code changes for predicting patch correctness in program repair. In: Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering, pp. 981\u2013992 (2020)","DOI":"10.1145\/3324884.3416532"},{"issue":"4","key":"502_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3576039","volume":"32","author":"H Tian","year":"2023","unstructured":"Tian, H., Liu, K., Li, Y., Kabor\u00e9, A.K., Koyuncu, A., Habib, A., Li, L., Wen, J., Klein, J., Bissyand\u00e9, T.F.: The best of both worlds: combining learned embeddings with engineered features for accurate prediction of correct patches. ACM Trans. Softw. Eng. Methodol. 32(4), 1\u201334 (2023)","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"502_CR42","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al.: Llama 2: open foundation and fine-tuned chat models (2023). arXiv preprint arXiv:2307.09288"},{"key":"502_CR43","doi-asserted-by":"crossref","unstructured":"Tu, Z., Su, Z., Devanbu, P.: On the localness of software. In: Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering, pp. 269\u2013280 (2014)","DOI":"10.1145\/2635868.2635875"},{"key":"502_CR44","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"502_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, W., Joty, S., Hoi, S.C.: Codet5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation (2021). arXiv preprint arXiv:2109.00859","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"502_CR46","doi-asserted-by":"crossref","unstructured":"Wang, S., Wen, M., Lin, B., Wu, H., Qin, Y., Zou, D., Mao, X., Jin, H.: Automated patch correctness assessment: how far are we? In: Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering, pp. 968\u2013980 ( 2020)","DOI":"10.1145\/3324884.3416590"},{"key":"502_CR47","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et al.: Emergent abilities of large language models (2022). arXiv preprint arXiv:2206.07682"},{"key":"502_CR48","doi-asserted-by":"crossref","unstructured":"Wen, M., Chen, J., Wu, R., Hao, D., Cheung, S.-C.: Context-aware patch generation for better automated program repair. In: Proceedings of the 40th International Conference on Software Engineering, pp. 1\u201311 (2018)","DOI":"10.1145\/3180155.3180233"},{"issue":"6","key":"502_CR49","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. Biom. Bull. 1(6), 80\u201383 (1945)","journal-title":"Biom. Bull."},{"key":"502_CR50","doi-asserted-by":"crossref","unstructured":"Xia, C.S., Wei, Y., Zhang, L.: Automated program repair in the era of large pre-trained language models. In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE), pp. 1482\u20131494. IEEE (2023)","DOI":"10.1109\/ICSE48619.2023.00129"},{"key":"502_CR51","doi-asserted-by":"crossref","unstructured":"Xia, C.S., Zhang, L.: Less training, more repairing please: revisiting automated program repair via zero-shot learning. In: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 959\u2013971 (2022)","DOI":"10.1145\/3540250.3549101"},{"key":"502_CR52","doi-asserted-by":"crossref","unstructured":"Xin, Q., Reiss, S.P.: Identifying test-suite-overfitted patches through test case generation. In: Proceedings of the 26th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 226\u2013236 (2017)","DOI":"10.1145\/3092703.3092718"},{"key":"502_CR53","doi-asserted-by":"crossref","unstructured":"Xin, Q., Reiss, S.P.: Leveraging syntax-related code for automated program repair. In: 2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 660\u2013670. IEEE (2017)","DOI":"10.1109\/ASE.2017.8115676"},{"key":"502_CR54","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Liu, X., Zeng, M., Zhang, L., Huang, G.: Identifying patch correctness in test-based program repair. In: Proceedings of the 40th International Conference on Software Engineering, pp. 789\u2013799 (2018)","DOI":"10.1145\/3180155.3180182"},{"key":"502_CR55","doi-asserted-by":"crossref","unstructured":"Xu, F.F., Alon, U., Neubig, G., Hellendoorn, V.J.: A systematic evaluation of large language models of code. In: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming, pp. 1\u201310 (2022)","DOI":"10.1145\/3520312.3534862"},{"key":"502_CR56","unstructured":"Xu, H., Sharaf, A., Chen, Y., Tan, W., Shen, L., Van\u00a0Durme, B., Murray, K., Kim, Y.J.: Contrastive preference optimization: pushing the boundaries of LLM performance in machine translation. In: 41st International Conference on Machine Learning (2024)"},{"key":"502_CR57","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jiang, Y., Gu, M., Sun, J., Gao, J., Liu, H.: A language model for statements of software code. In: 2017 32nd IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 682\u2013687. IEEE (2017)","DOI":"10.1109\/ASE.2017.8115678"},{"key":"502_CR58","doi-asserted-by":"crossref","unstructured":"Yang, A.Z., Kolak, S., Hellendoorn, V.J., Martins, R., Goues, C.L.: Revisiting unnaturalness for automated program repair in the era of large language models (2024). arXiv preprint arXiv:2404.15236","DOI":"10.1109\/ICSE55347.2025.00089"},{"key":"502_CR59","doi-asserted-by":"crossref","unstructured":"Yang, J., Wang, Y., Lou, Y., Wen, M., Zhang, L.: A large-scale empirical review of patch correctness checking approaches. In: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 1203\u20131215 (2023)","DOI":"10.1145\/3611643.3616331"},{"key":"502_CR60","doi-asserted-by":"crossref","unstructured":"Ye, H., Martinez, M., Monperrus, M.: Neural program repair with execution-based backpropagation. In: Proceedings of the 44th International Conference on Software Engineering, pp. 1506\u20131518 (2022)","DOI":"10.1145\/3510003.3510222"},{"key":"502_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-020-09920-w","volume":"26","author":"H Ye","year":"2021","unstructured":"Ye, H., Martinez, M., Monperrus, M.: Automated patch assessment for program repair at scale. Empir. Softw. Eng. 26, 1\u201338 (2021)","journal-title":"Empir. Softw. Eng."},{"key":"502_CR62","unstructured":"Yu, Z., Martinez, M., Danglot, B., Durieux, T., Monperrus, M.: Test case generation for program repair: a study of feasibility and effectiveness. arXiv preprint arXiv:1703.00198 (2017)"},{"key":"502_CR63","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10664-018-9619-4","volume":"24","author":"Z Yu","year":"2019","unstructured":"Yu, Z., Martinez, M., Danglot, B., Durieux, T., Monperrus, M.: Alleviating patch overfitting with automatic test generation: a study of feasibility and effectiveness for the nopol repair system. Empir. Softw. Eng. 24, 33\u201367 (2019)","journal-title":"Empir. Softw. Eng."},{"key":"502_CR64","unstructured":"Zhang, Z., Chen, C., Liu, B., Liao, C., Gong, Z., Yu, H., Li, J., Wang, R.: A survey on language models for code (2023). arXiv preprint arXiv:2311.07989"},{"key":"502_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Fang, C., Sun, W., Liu, Y., He, T., Hao, X., Chen, Z.: Appt: boosting automated patch correctness prediction via fine-tuning pre-trained models. IEEE Trans. Softw. Eng. 474\u2013494 (2024)","DOI":"10.1109\/TSE.2024.3354969"}],"container-title":["Automated Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-025-00502-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10515-025-00502-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-025-00502-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T13:57:24Z","timestamp":1757512644000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10515-025-00502-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,2]]},"references-count":65,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["502"],"URL":"https:\/\/doi.org\/10.1007\/s10515-025-00502-y","relation":{},"ISSN":["0928-8910","1573-7535"],"issn-type":[{"value":"0928-8910","type":"print"},{"value":"1573-7535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,2]]},"assertion":[{"value":"10 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 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":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The experimental code of this paper can be found at","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"35"}}