{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:48:54Z","timestamp":1784454534671,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62102340"],"award-info":[{"award-number":["62102340"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515010145"],"award-info":[{"award-number":["2024A1515010145"]}]},{"name":"Shenzhen Research Institute of Big Data Innovation Fund","award":["SIF20240009"],"award-info":[{"award-number":["SIF20240009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3691620.3695474","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T15:39:19Z","timestamp":1729265959000},"page":"919-930","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Unlocking the Power of Numbers: Log Compression via Numeric Token Parsing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3793-7684","authenticated-orcid":false,"given":"Siyu","family":"Yu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5847-3132","authenticated-orcid":false,"given":"Yifan","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6278-2357","authenticated-orcid":false,"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3377-8129","authenticated-orcid":false,"given":"Pinjia","family":"He","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China"},{"name":"Shenzhen Research Institute of Big Data, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024-6-4. https:\/\/7-zip.org\/sdk.html."},{"key":"e_1_3_2_1_2_1","unstructured":"2024-6-4. https:\/\/cloud.google.com\/stackdriver\/pricing?hl=zh-cn."},{"key":"e_1_3_2_1_3_1","unstructured":"2024-6-4. https:\/\/github.com\/gaiusyu\/Denum."},{"key":"e_1_3_2_1_4_1","unstructured":"2024-6-4. https:\/\/git.savannah.gnu.org\/cgit\/gzip.git."},{"key":"e_1_3_2_1_5_1","unstructured":"2024-6-4. https:\/\/ppmd-cffi.readthedocs.io\/en\/latest\/index.html."},{"key":"e_1_3_2_1_6_1","unstructured":"2024-6-4. https:\/\/sourceware.org\/bzip2\/."},{"key":"e_1_3_2_1_7_1","volume-title":"Suffix Arrays, and Pattern Matching","author":"Adjeroh Donald","unstructured":"Donald Adjeroh, Timothy Bell, and Amar Mukherjee. 2008. The Burrows-Wheeler Transform:: Data Compression, Suffix Arrays, and Pattern Matching. Springer Science & Business Media."},{"key":"e_1_3_2_1_8_1","unstructured":"Boyuan Chen. 2020. Improving the Logging Practices in DevOps. (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3440756"},{"key":"e_1_3_2_1_10_1","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Chow Michael","year":"2014","unstructured":"Michael Chow, David Meisner, Jason Flinn, Daniel Peek, and Thomas F Wenisch. 2014. The mystery machine: End-to-end performance analysis of large-scale internet services. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14). 217--231."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465341"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1984.1096090"},{"key":"e_1_3_2_1_13_1","first-page":"879","article-title":"Logram: Efficient Log Parsing Using n n-Gram Dictionaries","volume":"48","author":"Dai Hetong","year":"2020","unstructured":"Hetong Dai, Heng Li, Che-Shao Chen, Weiyi Shang, and Tse-Hsun Chen. 2020. Logram: Efficient Log Parsing Using n n-Gram Dictionaries. IEEE Transactions on Software Engineering 48, 3 (2020), 879--892.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134015"},{"key":"e_1_3_2_1_16_1","volume-title":"MLC: An efficient multi-level log compression method for cloud backup systems. In 2016","author":"Feng Bo","year":"2016","unstructured":"Bo Feng, Chentao Wu, and Jie Li. 2016. MLC: An efficient multi-level log compression method for cloud backup systems. In 2016 IEEE Trustcom\/BigDataSE\/ISPA. IEEE, 1358--1365."},{"key":"e_1_3_2_1_17_1","volume-title":"Execution anomaly detection in distributed systems through unstructured log analysis. In 2009 ninth IEEE international conference on data mining","author":"Fu Qiang","unstructured":"Qiang Fu, Jian-Guang Lou, Yi Wang, and Jiang Li. 2009. Execution anomaly detection in distributed systems through unstructured log analysis. In 2009 ninth IEEE international conference on data mining. IEEE, 149--158."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558947"},{"key":"e_1_3_2_1_19_1","unstructured":"Sanjay Ghemawat and Jeff Dean. 2014. Leveldb is a fast key-value storage library written at google that provides an ordered mapping from string keys to string values."},{"key":"e_1_3_2_1_20_1","volume-title":"A comprehensive survey of logging in software: From logging statements automation to log mining and analysis. arXiv preprint arXiv:2110.12489","author":"Gholamian Sina","year":"2021","unstructured":"Sina Gholamian and Paul AS Ward. 2021. A comprehensive survey of logging in software: From logging statements automation to log mining and analysis. arXiv preprint arXiv:2110.12489 (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1966.1053907"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2017.13"},{"key":"e_1_3_2_1_23_1","volume-title":"A survey on automated log analysis for reliability engineering. ACM computing surveys (CSUR) 54, 6","author":"He Shilin","year":"2021","unstructured":"Shilin He, Pinjia He, Zhuangbin Chen, Tianyi Yang, Yuxin Su, and Michael R Lyu. 2021. A survey on automated log analysis for reliability engineering. ACM computing surveys (CSUR) 54, 6 (2021), 1--37."},{"key":"e_1_3_2_1_24_1","volume-title":"Loghub: A large collection of system log datasets towards automated log analytics. arXiv preprint arXiv:2008.06448","author":"He Shilin","year":"2020","unstructured":"Shilin He, Jieming Zhu, Pinjia He, and Michael R Lyu. 2020. Loghub: A large collection of system log datasets towards automated log analytics. arXiv preprint arXiv:2008.06448 (2020)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00082"},{"key":"e_1_3_2_1_27_1","volume-title":"Llmparser: A llm-based log parsing framework. arXiv preprint arXiv:2310.01796","author":"Jiang Zhihan","year":"2023","unstructured":"Zhihan Jiang, Jinyang Liu, Zhuangbin Chen, Yichen Li, Junjie Huang, Yintong Huo, Pinjia He, Jiazhen Gu, and Michael R Lyu. 2023. Llmparser: A llm-based log parsing framework. arXiv preprint arXiv:2310.01796 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"An Evaluation of Log Parsing with ChatGPT. arXiv preprint arXiv:2306.01590","author":"Le Van-Hoang","year":"2023","unstructured":"Van-Hoang Le and Hongyu Zhang. 2023. An Evaluation of Log Parsing with ChatGPT. arXiv preprint arXiv:2306.01590 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Log Parsing with Prompt-based Few-shot Learning. arXiv preprint arXiv:2302.07435","author":"Le Van-Hoang","year":"2023","unstructured":"Van-Hoang Le and Hongyu Zhang. 2023. Log Parsing with Prompt-based Few-shot Learning. arXiv preprint arXiv:2302.07435 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3608129"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.45"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00085"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511993"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2017.135"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/382780.382782"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67667-4_8"},{"key":"e_1_3_2_1_37_1","volume-title":"Arithmetic coding. IBM Journal of research and development 23, 2","author":"Rissanen Jorma","year":"1979","unstructured":"Jorma Rissanen and Glen G Langdon. 1979. Arithmetic coding. IBM Journal of research and development 23, 2 (1979), 149--162."},{"key":"e_1_3_2_1_38_1","volume-title":"15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21). 183--198.","author":"Rodrigues Kirk","unstructured":"Kirk Rodrigues, Yu Luo, and Ding Yuan. 2021. {CLP}: Efficient and Scalable Search on Compressed Text Logs. In 15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21). 183--198."},{"key":"e_1_3_2_1_39_1","volume-title":"Length matters: Clustering system log messages using length of words. arXiv preprint arXiv:1611.03213","author":"Shima Keiichi","year":"2016","unstructured":"Keiichi Shima. 2016. Length matters: Clustering system log messages using length of words. arXiv preprint arXiv:1611.03213 (2016)."},{"key":"e_1_3_2_1_40_1","volume-title":"Thrift: Scalable cross-language services implementation. Facebook white paper 5, 8","author":"Slee Mark","year":"2007","unstructured":"Mark Slee, Aditya Agarwal, and Marc Kwiatkowski. 2007. Thrift: Scalable cross-language services implementation. Facebook white paper 5, 8 (2007), 127."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549176"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567484"},{"key":"e_1_3_2_1_43_1","volume-title":"19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Wei Junyu","year":"2021","unstructured":"Junyu Wei, Guangyan Zhang, Yang Wang, Zhiwei Liu, Zhanyang Zhu, Junchao Chen, Tingtao Sun, and Qi Zhou. 2021. On the Feasibility of Parser-based Log Compression in {Large-Scale} Cloud Systems. In 19th USENIX Conference on File and Storage Technologies (FAST 21). 249--262."},{"key":"e_1_3_2_1_44_1","volume-title":"Prompting for Automatic Log Template Extraction. arXiv preprint arXiv:2307.09950","author":"Xu Junjielong","year":"2023","unstructured":"Junjielong Xu, Ruichun Yang, Yintong Huo, Chengyu Zhang, and Pinjia He. 2023. Prompting for Automatic Log Template Extraction. arXiv preprint arXiv:2307.09950 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3069958"},{"key":"e_1_3_2_1_46_1","volume-title":"Brain: Log Parsing with Bidirectional Parallel Tree","author":"Yu Siyu","year":"2023","unstructured":"Siyu Yu, Pinjia He, Ningjiang Chen, and Yifan Wu. 2023. Brain: Log Parsing with Bidirectional Parallel Tree. IEEE Transactions on Services Computing (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616355"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1978.1055934"}],"event":{"name":"ASE '24: 39th IEEE\/ACM International Conference on Automated Software Engineering","location":"Sacramento CA USA","acronym":"ASE '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691620.3695474","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3691620.3695474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:19Z","timestamp":1750291579000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691620.3695474"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":48,"alternative-id":["10.1145\/3691620.3695474","10.1145\/3691620"],"URL":"https:\/\/doi.org\/10.1145\/3691620.3695474","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2024-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}