{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:03:32Z","timestamp":1781841812885,"version":"3.54.5"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T00:00:00Z","timestamp":1722038400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T00:00:00Z","timestamp":1722038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2100035"],"award-info":[{"award-number":["CCF-2100035"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2211428"],"award-info":[{"award-number":["CCF-2211428"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Softw Eng"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s10515-024-00460-x","type":"journal-article","created":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T11:02:03Z","timestamp":1722078123000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Revisiting file context for source code summarization"],"prefix":"10.1007","volume":"31","author":[{"given":"Chia-Yi","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakash","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Collin","family":"McMillan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,27]]},"reference":[{"key":"460_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, W., Chakraborty, S., Ray, B., et\u00a0al.: A transformer-based approach for source code summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4998\u20135007 (2020)","DOI":"10.18653\/v1\/2020.acl-main.449"},{"key":"460_CR2","doi-asserted-by":"crossref","unstructured":"Ahmad, W.U., Chakraborty, S., Ray, B., et\u00a0al.: Unified Pre-training for Program Understanding and Generation (2021). arXiv preprint arXiv:2103.06333","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"460_CR3","doi-asserted-by":"crossref","unstructured":"Ahmed, T., Devanbu, P.: Few-shot training LLMs for project-specific code-summarization (2022). arXiv preprint arXiv:2207.04237","DOI":"10.1145\/3551349.3559555"},{"key":"460_CR4","doi-asserted-by":"crossref","unstructured":"Allamanis, M.: The adverse effects of code duplication in machine learning models of code. In: Proceedings of the 2019 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software, pp. 143\u2013153 (2019)","DOI":"10.1145\/3359591.3359735"},{"key":"460_CR5","doi-asserted-by":"crossref","unstructured":"Alon, U., Zilberstein, M., Levy, O., et\u00a0al.: code2vec: learning distributed representations of code. In: Proceedings of the ACM on Programming Languages 3(POPL):1\u201329 (2019)","DOI":"10.1145\/3290353"},{"key":"460_CR6","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"460_CR7","doi-asserted-by":"crossref","unstructured":"Bansal, A., Haque, S., McMillan, C.: Project-level encoding for neural source code summarization of subroutines. In: 2021 IEEE\/ACM 29th International Conference on Program Comprehension (ICPC), pp. 253\u2013264. IEEE (2021)","DOI":"10.1109\/ICPC52881.2021.00032"},{"key":"460_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3279774","author":"A Bansal","year":"2023","unstructured":"Bansal, A., Eberhart, Z., Karas, Z., et al.: Function call graph context encoding for neural source code summarization. IEEE Trans. Softw. Eng. (2023a). https:\/\/doi.org\/10.1109\/TSE.2023.3279774","journal-title":"IEEE Trans. Softw. Eng."},{"key":"460_CR9","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sharif, B., McMillan, C.: Towards modeling human attention from eye movements for neutral source code summarization. iN: Proceedings of ACM Human\u2013Computer Interaction, vol. 7 (2023b)","DOI":"10.1145\/3591136"},{"key":"460_CR10","unstructured":"Chiang, D., Rush, A.M., Barak, B.: Named Tensor Notation (2021). arXiv preprint arXiv:2102.13196"},{"key":"460_CR11","doi-asserted-by":"crossref","unstructured":"Dell, N., Vaidyanathan, V., Medhi, I., et\u00a0al.: \u201cyours is Better!\u201d Participant Response Bias in HCI. In: Proceedings of the Sigchi Conference on Human Factors in Computing Systems, pp. 1321\u20131330 (2012)","DOI":"10.1145\/2207676.2208589"},{"key":"460_CR12","unstructured":"Ding, Y., Wang, Z., Ahmad, W.U., et\u00a0al.: CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context (2022). arXiv preprint arXiv:2212.10007"},{"key":"460_CR13","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, D., Tang, D., et\u00a0al.: CodeBERT: A Pre-trained Model for Programming and Natural Languages (2020). arXiv preprint arXiv:2002.08155","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"460_CR14","doi-asserted-by":"publisher","first-page":"1706","DOI":"10.1007\/s10664-013-9260-1","volume":"19","author":"L Guerrouj","year":"2014","unstructured":"Guerrouj, L., Di Penta, M., Gu\u00e9h\u00e9neuc, Y.G., et al.: An experimental investigation on the effects of context on source code identifiers splitting and expansion. Empir. Softw. Eng. 19, 1706\u20131753 (2014)","journal-title":"Empir. Softw. Eng."},{"key":"460_CR15","doi-asserted-by":"crossref","unstructured":"Haldar, R., Wu, L., Xiong, J., et\u00a0al.: A Multi-perspective Architecture for Semantic Code Search (2020). arXiv preprint arXiv:2005.06980","DOI":"10.18653\/v1\/2020.acl-main.758"},{"key":"460_CR16","doi-asserted-by":"crossref","unstructured":"Haque, S., LeClair, A., Wu, L., et\u00a0al.: Improved automatic summarization of subroutines via attention to file context. In: Proceedings of the 17th International Conference on Mining Software Repositories, pp. 300\u2013310 (2020)","DOI":"10.1145\/3379597.3387449"},{"key":"460_CR17","doi-asserted-by":"crossref","unstructured":"Haque, S., Bansal, A., Wu, L., et\u00a0al.: Action word prediction for neural source code summarization. In: 2021 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 330\u2013341. IEEE (2021)","DOI":"10.1109\/SANER50967.2021.00038"},{"key":"460_CR18","doi-asserted-by":"crossref","unstructured":"Haque, S., Eberhart, Z., Bansal, A., et\u00a0al.: Semantic similarity metrics for evaluating source code summarization. In: Proceedings of the 30th IEEE\/ACM International Conference on Program Comprehension, pp. 36\u201347 (2022)","DOI":"10.1145\/3524610.3527909"},{"key":"460_CR19","doi-asserted-by":"crossref","unstructured":"Hill, E., Pollock, L., Vijay-Shanker, K.: Automatically capturing source code context of NL-queries for software maintenance and reuse. In: 2009 IEEE 31st International Conference on Software Engineering, pp. 232\u2013242. IEEE (2009)","DOI":"10.1109\/ICSE.2009.5070524"},{"key":"460_CR20","doi-asserted-by":"crossref","unstructured":"Holmes, R., Murphy, G.C.: Using structural context to recommend source code examples. In: Proceedings of the 27th International Conference on Software Engineering, pp. 117\u2013125 (2005)","DOI":"10.1109\/ICSE.2005.1553554"},{"key":"460_CR21","unstructured":"Hu, E.J., Shen, Y., Wallis, P., et\u00a0al.: Lora: Low-Rank Adaptation of Large Language Models (2021). arXiv preprint arXiv:2106.09685"},{"key":"460_CR22","doi-asserted-by":"crossref","unstructured":"Hu, X., Li, G., Xia, X., et\u00a0al.: Deep code comment generation. In: Proceedings of the 26th Conference on Program Comprehension, pp. 200\u2013210. ACM (2018a)","DOI":"10.1145\/3196321.3196334"},{"key":"460_CR23","doi-asserted-by":"crossref","unstructured":"Hu, X., Li, G., Xia, X., et\u00a0al.: Summarizing source code with transferred API knowledge. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 2269\u20132275. AAAI Press (2018b)","DOI":"10.24963\/ijcai.2018\/314"},{"key":"460_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liang, D., Xu, P., et\u00a0al.: Improve transformer models with better relative position embeddings. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 3327\u20133335 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.298"},{"key":"460_CR25","doi-asserted-by":"publisher","first-page":"102992","DOI":"10.1016\/j.jdeveco.2022.102992","volume":"161","author":"D Jeong","year":"2023","unstructured":"Jeong, D., Aggarwal, S., Robinson, J., et al.: Exhaustive or exhausting? Evidence on respondent fatigue in long surveys. J. Dev. Econ. 161, 102992 (2023)","journal-title":"J. Dev. Econ."},{"key":"460_CR26","doi-asserted-by":"crossref","unstructured":"Kramer, D.: API documentation from source code comments: a case study of Javadoc. In: Proceedings of the 17th Annual International Conference on Computer Documentation, pp. 147\u2013153 (1999)","DOI":"10.1145\/318372.318577"},{"issue":"2","key":"460_CR27","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s10515-022-00341-1","volume":"29","author":"L Kuang","year":"2022","unstructured":"Kuang, L., Zhou, C., Yang, X.: Code comment generation based on graph neural network enhanced transformer model for code understanding in open-source software ecosystems. Autom. Softw. Eng. 29(2), 43 (2022)","journal-title":"Autom. Softw. Eng."},{"key":"460_CR28","doi-asserted-by":"crossref","unstructured":"LeClair, A., McMillan, C.: Recommendations for datasets for source code summarization. In: Proceedings of NAACL-HLT, pp. 3931\u20133937 (2019)","DOI":"10.18653\/v1\/N19-1394"},{"key":"460_CR29","doi-asserted-by":"crossref","unstructured":"LeClair, A., Jiang, S., McMillan, C.: A neural model for generating natural language summaries of program subroutines. In: 2019 IEEE\/ACM 41st International Conference on Software Engineering (ICSE), pp. 795\u2013806. IEEE (2019)","DOI":"10.1109\/ICSE.2019.00087"},{"key":"460_CR30","doi-asserted-by":"crossref","unstructured":"LeClair, A., Haque, S., Wu, L., et\u00a0al.: Improved code summarization via a graph neural network. In: Proceedings of the 28th International Conference on Program Comprehension, pp. 184\u2013195 (2020)","DOI":"10.1145\/3387904.3389268"},{"key":"460_CR31","doi-asserted-by":"publisher","unstructured":"Li, Y., Wang, S., Nguyen, T.N.: A context-based automated approach for method name consistency checking and suggestion. In: Proceedings of the 43rd International Conference on Software Engineering. IEEE Press, ICSE \u201921, pp. 574\u2013586 (2021). https:\/\/doi.org\/10.1109\/ICSE43902.2021.00060","DOI":"10.1109\/ICSE43902.2021.00060"},{"key":"460_CR32","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1109\/TR.2022.3154773","volume":"72","author":"Z Li","year":"2022","unstructured":"Li, Z., Wu, Y., Peng, B., et al.: SeTransformer: A transformer-based code semantic parser for code comment generation. IEEE Trans. Reliab. 72, 258\u2013273 (2022)","journal-title":"IEEE Trans. Reliab."},{"key":"460_CR33","doi-asserted-by":"crossref","unstructured":"Liang, Y., Zhu, K.Q.: Automatic generation of text descriptive comments for code blocks. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11963"},{"key":"460_CR34","unstructured":"Liu, S., Chen, Y., Xie, X., et\u00a0al.: Retrieval-augmented generation for code summarization via hybrid GNN. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=zv-typ1gPxA"},{"key":"460_CR35","doi-asserted-by":"crossref","unstructured":"Nie, P., Rai, R., Li, J.J., et\u00a0al.: A framework for writing trigger-action todo comments in executable format. In: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 385\u2013396. ACM (2019)","DOI":"10.1145\/3338906.3338965"},{"key":"460_CR36","doi-asserted-by":"crossref","unstructured":"Roehm, T., Tiarks, R., Koschke, R., et\u00a0al.: How do professional developers comprehend software? In: 2012 34th International Conference on Software Engineering (ICSE), pp. 255\u2013265. IEEE (2012)","DOI":"10.1109\/ICSE.2012.6227188"},{"key":"460_CR37","doi-asserted-by":"crossref","unstructured":"Roy, D., Fakhoury, S., Arnaoudova, V.: Reassessing automatic evaluation metrics for code summarization tasks. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 1105\u20131116 (2021)","DOI":"10.1145\/3468264.3468588"},{"key":"460_CR38","doi-asserted-by":"crossref","unstructured":"Shi, L., Mu, F., Chen, X., et\u00a0al.: Are we building on the rock? On the importance of data preprocessing for code summarization. In: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 107\u2013119 (2022)","DOI":"10.1145\/3540250.3549145"},{"issue":"10","key":"460_CR39","doi-asserted-by":"publisher","first-page":"2621","DOI":"10.1073\/pnas.1516947113","volume":"113","author":"HH Sievertsen","year":"2016","unstructured":"Sievertsen, H.H., Gino, F., Piovesan, M.: Cognitive fatigue influences students\u2019 performance on standardized tests. Proc. Natl. Acad. Sci. 113(10), 2621\u20132624 (2016). https:\/\/doi.org\/10.1073\/pnas.1516947113","journal-title":"Proc. Natl. Acad. Sci."},{"key":"460_CR40","doi-asserted-by":"crossref","unstructured":"Sridhara, G., Hill, E., Muppaneni, D., et\u00a0al.: Towards automatically generating summary comments for java methods. In: Proceedings of the 25th IEEE\/ACM international conference on Automated software engineering, pp. 43\u201352 (2010)","DOI":"10.1145\/1858996.1859006"},{"key":"460_CR41","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. 27, 3104\u20133112 (2014)"},{"key":"460_CR42","doi-asserted-by":"crossref","unstructured":"Tang, Z., Shen, X., Li, C., et\u00a0al.: AST-trans: Code summarization with efficient tree-structured attention. In: Proceedings of the 44th International Conference on Software Engineering, pp. 150\u2013162 (2022)","DOI":"10.1145\/3510003.3510224"},{"key":"460_CR43","unstructured":"Touvron, H., Lavril, T., Izacard, G., et\u00a0al.: LLaMA: Open and Efficient Foundation Language Models (2023). arXiv preprint arXiv:2302.13971"},{"key":"460_CR44","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 6000\u20136010 (2017)"},{"key":"460_CR45","doi-asserted-by":"crossref","unstructured":"Wan, Y., Zhao, Z., Yang, M., et\u00a0al.: Improving automatic source code summarization via deep reinforcement learning. In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering, pp. 397\u2013407. ACM (2018)","DOI":"10.1145\/3238147.3238206"},{"key":"460_CR46","doi-asserted-by":"publisher","unstructured":"Wang, S., Wen, M., Lin, B., et\u00a0al.: Lightweight global and local contexts guided method name recommendation with prior knowledge. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. Association for Computing Machinery, New York, NY, USA, ESEC\/FSE 2021, pp. 741\u2013753 (2021). https:\/\/doi.org\/10.1145\/3468264.3468567","DOI":"10.1145\/3468264.3468567"},{"key":"460_CR47","unstructured":"Wei, B., Li, G., Xia, X., et al.: Code generation as a dual task of code summarization. Adv. Neural Inf. Process. Syst. 32, 6563\u20136573 (2019)"},{"key":"460_CR48","doi-asserted-by":"crossref","unstructured":"Wei, B., Li, Y., Li, G., et\u00a0al.: Retrieve and refine: exemplar-based neural comment generation. In: Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering, pp. 349\u2013360 (2020)","DOI":"10.1145\/3324884.3416578"},{"key":"460_CR49","unstructured":"Z\u00fcgner, D., Kirschstein, T., Catasta, M., et\u00a0al.: Language-agnostic representation learning of source code from structure and context. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=Xh5eMZVONGF"}],"container-title":["Automated Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-024-00460-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10515-024-00460-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-024-00460-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T15:05:38Z","timestamp":1730127938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10515-024-00460-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,27]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["460"],"URL":"https:\/\/doi.org\/10.1007\/s10515-024-00460-x","relation":{},"ISSN":["0928-8910","1573-7535"],"issn-type":[{"value":"0928-8910","type":"print"},{"value":"1573-7535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,27]]},"assertion":[{"value":"17 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2024","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 competing interests","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"62"}}