{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T05:03:33Z","timestamp":1773032613932,"version":"3.50.1"},"reference-count":42,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"vor","delay-in-days":115,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20242084"],"award-info":[{"award-number":["BK20242084"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402496"],"award-info":[{"award-number":["62402496"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Software"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Commit classification is an important task in software maintenance, since it helps software developers classify code changes into different types according to their nature and purpose. This allows them to better understand how their development efforts are progressing, identify areas where they need improvement, and make informed decisions about when and how to release new versions of their software. However, existing methods are all discriminative models, usually with complex architectures that require additional output layers to produce class label probabilities, making them task\u2010specific and unable to learn features across different tasks. Moreover, they require a large amount of labeled data for fine tuning, and it is difficult to learn effective classification boundaries in the case of limited labeled data. To solve the above problems, we propose a generative framework that incorporates prompt tuning for commit classification with external knowledge (IPCK), which simplifies the model structure and learns features across different tasks, only based on the commit message information as the input. First, we proposed a generative framework based on T5 (text\u2010to\u2010text transfer transformer). This encoder\u2013decoder construction method unifies different commit classification tasks into a text\u2010to\u2010text problem, simplifying the model\u2019s structure by not requiring an extra output layer. Second, instead of fine tuning, we design a prompt tuning solution that can be adopted in few\u2010shot scenarios with only limited samples. Furthermore, we incorporate external knowledge via an external knowledge graph to map the probabilities of words into the final labels in the speech machine step to improve performance in few\u2010shot scenarios. Extensive experiments on two open available datasets demonstrate that our framework can solve the commit classification problem simply but effectively for both single\u2010label binary classification and single\u2010label multiclass classification purposes with 90% and 83% accuracy. Further, in the few\u2010shot scenarios, our method improves the adaptability of the model without requiring a large number of training samples for fine tuning.<\/jats:p>","DOI":"10.1049\/sfw2\/5566134","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T05:03:54Z","timestamp":1745643834000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Commit Classification Framework Incorporated With Prompt Tuning and External Knowledge"],"prefix":"10.1049","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1401-7885","authenticated-orcid":false,"given":"Jiajun","family":"Tong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0951-1512","authenticated-orcid":false,"given":"Xiaobin","family":"Rui","sequence":"additional","affiliation":[]}],"member":"265","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"e_1_2_14_1_2","doi-asserted-by":"crossref","unstructured":"Heri\u010dkoT.and\u0160umakB. Commit Classification Into Software Maintenance Activities: A Systematic Literature Review 2023 IEEE 47th Annual Computers Software and Applications Conference (COMPSAC) 2023 Torino Italy IEEE 1646\u20131651.","DOI":"10.1109\/COMPSAC57700.2023.00254"},{"key":"e_1_2_14_2_2","doi-asserted-by":"crossref","unstructured":"SabettaA.andBezziM. A Practical Approach to the Automatic Classification of Security-Relevant Commits 2018 IEEE International Conference on Software Maintenance and Evolution (ICSME) 2018 IEEE 579\u2013582.","DOI":"10.1109\/ICSME.2018.00058"},{"key":"e_1_2_14_3_2","doi-asserted-by":"crossref","unstructured":"ZhouY.andSharmaA. Automated Identification of Security Issues From Commit Messages and Bug Reports Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering 2017 Association for Computing Machinery 914\u2013919.","DOI":"10.1145\/3106237.3117771"},{"key":"e_1_2_14_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/math12071012"},{"key":"e_1_2_14_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3661484"},{"key":"e_1_2_14_6_2","doi-asserted-by":"crossref","unstructured":"MockusA.andVottaL. G. Identifying Reasons for Software Changes Using Historic Databases Proceedings 2000 International Conference on Software Maintenance 2000 San Jose CA USA IEEE 120\u2013130 https:\/\/doi.org\/10.1109\/ICSM.2000.883028.","DOI":"10.1109\/ICSM.2000.883028"},{"key":"e_1_2_14_7_2","doi-asserted-by":"crossref","unstructured":"LevinS.andYehudaiA. Boosting Automatic Commit Classification Into Maintenance Activities by Utilizing Source Code Changes Proceedings of the 13th International Conference on Predictive Models and Data Analytics in Software Engineering 2017 Association for Computing Machinery 97\u2013106.","DOI":"10.1145\/3127005.3127016"},{"key":"e_1_2_14_8_2","doi-asserted-by":"crossref","unstructured":"MarianoR. V. dos SantosG. E. andBrand\u00e3oW. C. Improve Classification of Commits Maintenance Activities With Quantitative Changes in Source Code 2 Proceedings of the 23rd International Conference on Enterprise Information Systems (ICEIS 2021) 2021 SciTePress 19\u201329.","DOI":"10.5220\/0010401700190029"},{"key":"e_1_2_14_9_2","doi-asserted-by":"crossref","unstructured":"GharbiS. MkaouerM. W. JenhaniI. andMessaoudM. B. On the Classification of Software Change Messages Using Multi-Label Active Learning Proceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing 2019 Association for Computing Machinery 1760\u20131767.","DOI":"10.1145\/3297280.3297452"},{"key":"e_1_2_14_10_2","doi-asserted-by":"crossref","unstructured":"HindleA. GermanD. M. GodfreyM. W. andHoltR. C. Automatic Classication of Large Changes Into Maintenance Categories 2009 IEEE 17th International Conference on Program Comprehension 2009 Vancouver BC Canada IEEE 30\u201339.","DOI":"10.1109\/ICPC.2009.5090025"},{"key":"e_1_2_14_11_2","doi-asserted-by":"crossref","unstructured":"MarianoR. V. dos SantosG. E. de AlmeidaM. V. andBrand\u00e3oW. C. Feature Changes in Source Code for Commit Classification Into Maintenance Activities 2019 18th IEEE International Conference on Machine Learning And Applications (ICMLA) 2019 Boca Raton FL USA IEEE 515\u2013518.","DOI":"10.1109\/ICMLA.2019.00096"},{"key":"e_1_2_14_12_2","doi-asserted-by":"crossref","unstructured":"H\u00f6nelS. EricssonM. L\u00f6weW. andWingkvistA. Importance and Aptitude of Source Code Density for Commit Classification Into Maintenance Activities 2019 IEEE 19th International Conference on Software Quality Reliability and Security (QRS) 2019 Sofia Bulgaria IEEE 109\u2013120.","DOI":"10.1109\/QRS.2019.00027"},{"key":"e_1_2_14_13_2","unstructured":"Heri\u010dkoT.and\u0160umakB. Using Domain-Specific Word Embeddings to Boost Keyword-Based Commit Classification Proceedings of the 13th Conference Data Analysis Methods for Software Systems 2022."},{"key":"e_1_2_14_14_2","first-page":"1","article-title":"Enhancing Security Patch Identification by Capturing Structures in Commits","author":"Wu B.","year":"2022","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"e_1_2_14_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106566"},{"key":"e_1_2_14_16_2","doi-asserted-by":"crossref","unstructured":"LeeJ. Y. D.andChieuH. L. Co-Training for Commit Classification Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021) 2021 Association for Computational Linguistics 389\u2013395.","DOI":"10.18653\/v1\/2021.wnut-1.43"},{"key":"e_1_2_14_17_2","doi-asserted-by":"crossref","unstructured":"SarwarM. U. ZafarS. MkaouerM. W. WaliaG. S. andMalikM. Z. Multi-Label Classification of Commit Messages Using Transfer Learning 2020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW) 2020 Coimbra Portugal IEEE 37\u201342.","DOI":"10.1109\/ISSREW51248.2020.00034"},{"key":"e_1_2_14_18_2","doi-asserted-by":"crossref","unstructured":"ZhouJ. PachecoM. andWanZ. et al.Finding A Needle in a Haystack: Automated Mining of Silent Vulnerability Fixes 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE) 2021 Melbourne Australia IEEE 705\u2013716.","DOI":"10.1109\/ASE51524.2021.9678720"},{"key":"e_1_2_14_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.04.024"},{"key":"e_1_2_14_20_2","unstructured":"YinD. DongL. andChengH. et al.A Survey of Knowledge-Intensive NLP With Pre-Trained Language Models 2022 arXiv preprint arXiv: 220208772."},{"key":"e_1_2_14_21_2","unstructured":"ZhaoW. X. ZhouK. andLiJ. et al.A Survey of Large Language Models 2023 arXiv preprint arXiv: 230318223."},{"key":"e_1_2_14_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"e_1_2_14_23_2","doi-asserted-by":"crossref","first-page":"31668","DOI":"10.52202\/068431-2296","article-title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","volume":"35","author":"Bevilacqua M.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_14_24_2","unstructured":"SalazarJ. LiangD. NguyenT. Q. andKirchhoffK. Masked Language Model Scoring 2019 arXiv preprint arXiv: 191014659."},{"key":"e_1_2_14_25_2","unstructured":"SongK. TanX. QinT. LuJ. andLiuT. Y. Mass: Masked Sequence to Sequence Pre-Training for Language Generation 2019 arXiv preprint arXiv: 190502450."},{"key":"e_1_2_14_26_2","unstructured":"SanhV. WebsonA. andRaffelC. et al.Multitask Prompted Training Enables Zero-Shot Task Generalization 2021 arXiv preprint arXiv: 211008207."},{"key":"e_1_2_14_27_2","first-page":"5485","article-title":"Exploring the Limits of Transfer Learning With a Unified Text-to-Text Transformer","volume":"21","author":"Raffel C.","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_2_14_28_2","doi-asserted-by":"crossref","unstructured":"LesterB. Al.RfouR. andConstantN. The Power of Scale for Parameter-Efficient Prompt Tuning 2021 arXiv preprint arXiv: 210408691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_2_14_29_2","doi-asserted-by":"crossref","unstructured":"LiuX. JiK. andFuY. et al.P-tuning: Prompt Tuning can be Comparable to Fine-Tuning Across Scales and Tasks Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) 2022 Dublin Ireland Association for Computational Linguistics 61\u201368.","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_2_14_30_2","unstructured":"GuY. HanX. LiuZ. andHuangM. Ppt: Pre-Trained Prompt Tuning for Few-Shot Learning 2021 arXiv preprint arXiv: 210904332."},{"key":"e_1_2_14_31_2","doi-asserted-by":"crossref","unstructured":"ChenX. ZhangN. andXieX. et al.KnowPrompt: Knowledge-Aware Prompt-Tuning With Synergistic Optimization for Relation Extraction Proceedings of the ACM Web Conference 2022 2022 Association for Computing Machinery 2778\u20132788.","DOI":"10.1145\/3485447.3511998"},{"key":"e_1_2_14_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.11.003"},{"key":"e_1_2_14_33_2","doi-asserted-by":"publisher","DOI":"10.3390\/ani14050755"},{"key":"e_1_2_14_34_2","doi-asserted-by":"crossref","unstructured":"YeH. J. HuH. ZhanD. C. andShaF. Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions Proceedings of the IEEE\/CVF Conference on computer Vision and Pattern Recognition 2020 Seattle WA USA IEEE 8808\u20138817.","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"e_1_2_14_35_2","first-page":"11054","article-title":"True Few-Shot Learning With Language Models","volume":"34","author":"Perez E.","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_14_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-00129-1_15"},{"key":"e_1_2_14_37_2","unstructured":"ReisS.andAbreuR. A Ground-Truth Dataset of Real Security Patches 2021 arXiv preprint arXiv: 211009635."},{"key":"e_1_2_14_38_2","doi-asserted-by":"crossref","unstructured":"MauczkaA. BroschF. SchanesC. andGrechenigT. Dataset of Developer-Labeled Commit Messages 2015 IEEE\/ACM 12th Working Conference on Mining Software Repositories 2015 Florence Italy IEEE 490\u2013493.","DOI":"10.1109\/MSR.2015.71"},{"key":"e_1_2_14_39_2","doi-asserted-by":"crossref","unstructured":"AlOmarE. MkaouerM. W. andOuniA. Can Refactoring be Self-Affirmed? An Exploratory Study on how Developers Document Their Refactoring Activities in Commit Messages 2019 IEEE\/ACM 3rd International Workshop on Refactoring (IWoR) 2019 Montreal QC Canada IEEE 51\u201358.","DOI":"10.1109\/IWoR.2019.00017"},{"key":"e_1_2_14_40_2","doi-asserted-by":"crossref","unstructured":"ZhangH. ZhangX. HuangH. andYuL. Prompt-Based Meta-Learning for Few-Shot Text Classification Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing 2022 Abu Dhabi United Arab Emirates Association for Computational Linguistics 1342\u20131357.","DOI":"10.18653\/v1\/2022.emnlp-main.87"},{"key":"e_1_2_14_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_2_14_42_2","unstructured":"TongJ.andRuiX. Incorprating Prompt Tuning for Commit Classification With Prior Knowledge 2023 arXiv preprint arXiv: 230810576."}],"container-title":["IET Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/sfw2\/5566134","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/sfw2\/5566134","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/sfw2\/5566134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T04:12:46Z","timestamp":1773029566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/sfw2\/5566134"}},"subtitle":[],"editor":[{"given":"Antonio","family":"Galli","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/sfw2\/5566134"],"URL":"https:\/\/doi.org\/10.1049\/sfw2\/5566134","archive":["Portico"],"relation":{},"ISSN":["1751-8806","1751-8814"],"issn-type":[{"value":"1751-8806","type":"print"},{"value":"1751-8814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2023-12-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5566134"}}