{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:49:37Z","timestamp":1772041777949,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T00:00:00Z","timestamp":1707177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1804002"],"award-info":[{"award-number":["2019YFB1804002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["62272495"],"award-info":[{"award-number":["62272495"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023B1515020054"],"award-info":[{"award-number":["2023B1515020054"]}]},{"name":"Australian Research Council Discovery Projects","award":["DP200102940"],"award-info":[{"award-number":["DP200102940"]}]},{"name":"Australian Research Council Discovery Projects","award":["DP220103044"],"award-info":[{"award-number":["DP220103044"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202206380116"],"award-info":[{"award-number":["202206380116"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,2,6]]},"DOI":"10.1145\/3597503.3608129","type":"proceedings-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:53:16Z","timestamp":1707252796000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["LogShrink: Effective Log Compression by Leveraging Commonality and Variability of Log Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5730-2972","authenticated-orcid":false,"given":"Xiaoyun","family":"Li","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-9425","authenticated-orcid":false,"given":"Hongyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7651-9154","authenticated-orcid":false,"given":"Van-Hoang","family":"Le","sequence":"additional","affiliation":[{"name":"The University of Newcastle, Newcastle, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-6900","authenticated-orcid":false,"given":"Pengfei","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, Guangdong, China"}]}],"member":"320","published-online":{"date-parts":[[2024,2,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.1998.732614"},{"key":"e_1_3_2_1_2_1","first-page":"305","volume-title":"Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering.","author":"Boyuan","year":"2018","unstructured":"Boyuan Chen et al. \"An automated approach to estimating code coverage measures via execution logs\". In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering. 2018, pp. 305--316."},{"key":"e_1_3_2_1_3_1","first-page":"276","volume-title":"2018 IEEE Fourth International Conference on Big Data Computing Service and Applications (BigDataService). IEEE.","author":"Vaibhav","year":"2018","unstructured":"Vaibhav Agrawal et al. \"Log-based cloud monitoring system for OpenStack\". In: 2018 IEEE Fourth International Conference on Big Data Computing Service and Applications (BigDataService). IEEE. 2018, pp. 276--281."},{"key":"e_1_3_2_1_4_1","first-page":"127","volume-title":"Proceedings of the 2018 ACM\/SPEC International Conference on Performance Engineering.","author":"Kundi","year":"2018","unstructured":"Kundi Yao et al. \"Log4perf: Suggesting logging locations for web-based systems' performance monitoring\". In: Proceedings of the 2018 ACM\/SPEC International Conference on Performance Engineering. 2018, pp. 127--138."},{"key":"e_1_3_2_1_5_1","first-page":"60","volume-title":"Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering.","author":"Shilin","year":"2018","unstructured":"Shilin He et al. \"Identifying impactful service system problems via log analysis\". In: Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2018, pp. 60--70."},{"key":"e_1_3_2_1_6_1","first-page":"1285","volume-title":"SIGSAC'17: Proc. of the 2017 ACM SIGSAC Conference on Computer and Communications Security. ACM.","author":"Min","year":"2017","unstructured":"Min Du et al. \"Deeplog: Anomaly detection and diagnosis from system logs through deep learning\". In: SIGSAC'17: Proc. of the 2017 ACM SIGSAC Conference on Computer and Communications Security. ACM. 2017, pp. 1285--1298."},{"key":"e_1_3_2_1_7_1","first-page":"4739","volume-title":"19: Proc. of the 28th International Joint Conference on Artificial Intelligence.","author":"Weibin","year":"2019","unstructured":"Weibin Meng et al. \"LogAnomaly: Unsupervised Detection of Sequential and Quantitative Anomalies in Unstructured Logs.\" In: IJCAI'19: Proc. of the 28th International Joint Conference on Artificial Intelligence. 2019, pp. 4739--4745."},{"key":"e_1_3_2_1_8_1","first-page":"623","volume-title":"Proceedings of the 44th International Conference on Software Engineering.","author":"Chenxi","year":"2022","unstructured":"Chenxi Zhang et al. \"DeepTraLog: Trace-log combined microservice anomaly detection through graph-based deep learning\". In: Proceedings of the 44th International Conference on Software Engineering. 2022, pp. 623--634."},{"key":"e_1_3_2_1_9_1","first-page":"683","volume-title":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering.","author":"Xiang","year":"2019","unstructured":"Xiang Zhou et al. \"Latent error prediction and fault localization for microservice applications by learning from system trace logs\". In: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2019, pp. 683--694."},{"key":"e_1_3_2_1_10_1","first-page":"21","volume-title":"2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing. IEEE.","author":"Hao","year":"2015","unstructured":"Hao Lin et al. \"Cowic: A column-wise independent compression for log stream analysis\". In: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing. IEEE. 2015, pp. 21--30."},{"key":"e_1_3_2_1_11_1","first-page":"249","volume-title":"19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Junyu","year":"2021","unstructured":"Junyu Wei et al. \"On the Feasibility of Parser-based Log Compression in {Large-Scale} Cloud Systems\". In: 19th USENIX Conference on File and Storage Technologies (FAST 21). USENIX Association, 2021, pp. 249--262."},{"key":"e_1_3_2_1_12_1","volume-title":"https:\/\/cloud.google.com\/stackdriver\/pricing. [Online]","author":"Pricing Logging Storage","year":"2023","unstructured":"Logging Storage Pricing. https:\/\/cloud.google.com\/stackdriver\/pricing. [Online]. 2023."},{"key":"e_1_3_2_1_13_1","first-page":"139","volume-title":"2015 USENIX Annual Technical Conference, USENIX ATC '15","author":"Rui","year":"2015","unstructured":"Rui Ding et al. \"Log2: A Cost-Aware Logging Mechanism for Performance Diagnosis\". In: 2015 USENIX Annual Technical Conference, USENIX ATC '15. USENIX Association, 2015, pp. 139--150."},{"key":"e_1_3_2_1_14_1","first-page":"1763","volume-title":"2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE.","author":"Guangba","year":"2023","unstructured":"Guangba Yu et al. \"LogReducer: Identify and Reduce Log Hotspots in Kernel on the Fly\". In: 2023 IEEE\/ACM 45th International Conference on Software Engineering (ICSE). IEEE. 2023, pp. 1763--1775."},{"key":"e_1_3_2_1_15_1","first-page":"565","volume-title":"Proceedings of the 26th Symposium on Operating Systems Principles.","author":"Xu","year":"2017","unstructured":"Xu Zhao et al. \"Log20: Fully automated optimal placement of log printing statements under specified overhead threshold\". In: Proceedings of the 26th Symposium on Operating Systems Principles. 2017, pp. 565--581."},{"key":"e_1_3_2_1_16_1","volume-title":"https:\/\/linux.die.net\/man\/1\/7za. [Online]","year":"2023","unstructured":"7za tool. https:\/\/linux.die.net\/man\/1\/7za. [Online]. 2023."},{"key":"e_1_3_2_1_17_1","volume-title":"https:\/\/www.gzip.org. [Online]","author":"The","year":"2023","unstructured":"The gzip home page. https:\/\/www.gzip.org. [Online]. 2023."},{"key":"e_1_3_2_1_18_1","volume-title":"https:\/\/sourceware.org\/bzip2\/. [Online]","author":"The","year":"2023","unstructured":"The bzip2 home page. https:\/\/sourceware.org\/bzip2\/. [Online]. 2023."},{"key":"e_1_3_2_1_19_1","first-page":"3023","article-title":"ELISE: A Storage Efficient Logging System Powered by Redundancy Reduction and Representation Learning","author":"Hailun Ding","year":"2021","unstructured":"Hailun Ding et al. \"ELISE: A Storage Efficient Logging System Powered by Redundancy Reduction and Representation Learning.\" In: USENIX Security Symposium. 2021, pp. 3023--3040.","journal-title":"USENIX Security Symposium."},{"key":"e_1_3_2_1_20_1","first-page":"863","volume-title":"34th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2019","author":"Jinyang","year":"2019","unstructured":"Jinyang Liu et al. \"Logzip: Extracting Hidden Structures via Iterative Clustering for Log Compression\". In: 34th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2019. IEEE, 2019, pp. 863--873."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465341"},{"issue":"8","key":"e_1_3_2_1_22_1","first-page":"2748","article-title":"Improving state-of-the-art compression techniques for log management tools","volume":"48","author":"Kundi Yao","year":"2021","unstructured":"Kundi Yao et al. \"Improving state-of-the-art compression techniques for log management tools\". In: IEEE Transactions on Software Engineering 48.8 (2021), pp. 2748--2760.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_1_23_1","volume-title":"https:\/\/zenodo.org\/record\/3227177. [Online]","author":"Datasets LogHub","year":"2023","unstructured":"LogHub Datasets. https:\/\/zenodo.org\/record\/3227177. [Online]. 2023."},{"key":"e_1_3_2_1_24_1","volume-title":"arXiv preprint arXiv:2301.04234","author":"Foalem Patrick Loic","year":"2023","unstructured":"Patrick Loic Foalem, Foutse Khomh, and Heng Li. \"Studying Logging Practice in Machine Learning-based Applications\". In: arXiv preprint arXiv:2301.04234 (2023)."},{"key":"e_1_3_2_1_25_1","first-page":"24","volume-title":"Companion Proceedings of the 36th International Conference on Software Engineering. ACM","author":"Qiang","year":"2014","unstructured":"Qiang Fu et al. \"Where do developers log? an empirical study on logging practices in industry\". In: Companion Proceedings of the 36th International Conference on Software Engineering. ACM, 2014, pp. 24--33."},{"key":"e_1_3_2_1_26_1","first-page":"102","volume-title":"2012 34th International Conference on Software Engineering (ICSE). IEEE.","author":"Yuan Ding","year":"2012","unstructured":"Ding Yuan, Soyeon Park, and Yuanyuan Zhou. \"Characterizing logging practices in open-source software\". In: 2012 34th International Conference on Software Engineering (ICSE). IEEE. 2012, pp. 102--112."},{"key":"e_1_3_2_1_27_1","first-page":"178","volume-title":"Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering. ACM","author":"Pinjia","year":"2018","unstructured":"Pinjia He et al. \"Characterizing the natural language descriptions in software logging statements\". In: Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering. ACM, 2018, pp. 178--189."},{"key":"e_1_3_2_1_28_1","first-page":"92","volume-title":"2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE). IEEE.","author":"Xiaoyun","year":"2020","unstructured":"Xiaoyun Li et al. \"SwissLog: Robust and Unified Deep Learning Based Log Anomaly Detection for Diverse Faults\". In: 2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE). IEEE. 2020, pp. 92--103."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3162857"},{"key":"e_1_3_2_1_30_1","first-page":"121","volume-title":"2022 IEEE 33rd International Symposium on Software Reliability Engineering (ISSRE). IEEE.","author":"Xiaoyun","year":"2022","unstructured":"Xiaoyun Li et al. \"Going through the Life Cycle of Faults in Clouds: Guidelines on Fault Handling\". In: 2022 IEEE 33rd International Symposium on Software Reliability Engineering (ISSRE). IEEE. 2022, pp. 121--132."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510155"},{"issue":"9","key":"e_1_3_2_1_32_1","first-page":"2012","article-title":"Which variables should i log?","volume":"47","author":"Zhongxin Liu","year":"2019","unstructured":"Zhongxin Liu et al. \"Which variables should i log?\" In: IEEE Transactions on Software Engineering 47.9 (2019), pp. 2012--2031.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2110356.2110360"},{"key":"e_1_3_2_1_34_1","first-page":"335","volume-title":"2018 USENIX Annual Technical Conference, USENIX ATC 2018","author":"Yang Stephen","year":"2018","unstructured":"Stephen Yang, Seo Jin Park, and John K. Ousterhout. \"NanoLog: A Nanosecond Scale Logging System\". In: 2018 USENIX Annual Technical Conference, USENIX ATC 2018, Boston, MA, USA, July 11--13, 2018. USENIX Association, 2018, pp. 335--350."},{"key":"e_1_3_2_1_35_1","first-page":"2438","volume-title":"45th IEEE\/ACM International Conference on Software Engineering. IEEE","author":"Le Van-Hoang","year":"2023","unstructured":"Van-Hoang Le and Hongyu Zhang. \"Log Parsing with Prompt-based Few-shot Learning\". In: 45th IEEE\/ACM International Conference on Software Engineering. IEEE, 2023, pp. 2438--2449."},{"key":"e_1_3_2_1_36_1","volume-title":"multiple US agencies were hit","author":"Sanger David E","year":"2021","unstructured":"David E Sanger, Nicole Perlroth, and Eric Schmitt. \"Scope of Russian hacking becomes clear: multiple US agencies were hit\". In: The New York Times (2021)."},{"key":"e_1_3_2_1_37_1","volume-title":"Reuters","author":"Bing Christopher","year":"2020","unstructured":"Christopher Bing. \"Suspected Russian hackers spied on US Treasury emails-sources\". In: Reuters, Dec 13 (2020)."},{"key":"e_1_3_2_1_38_1","volume-title":"https:\/\/www.elastic.co\/elastic-stack. [Online]","author":"Stack ELK","year":"2023","unstructured":"ELK Stack. https:\/\/www.elastic.co\/elastic-stack. [Online]. 2023."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/214762.214771"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1984.1096090"},{"key":"e_1_3_2_1_43_1","first-page":"575","volume-title":"Data Compression Conference, DCC 2019","author":"Mohit","year":"2019","unstructured":"Mohit Goyal et al. \"DeepZip: Lossless Data Compression Using Recurrent Neural Networks\". In: Data Compression Conference, DCC 2019. IEEE, 2019, p. 575."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09822-x"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom.2016.0215"},{"key":"e_1_3_2_1_46_1","first-page":"183","article-title":"CLP: Efficient and Scalable Search on Compressed Text Logs","author":"Rodrigues Kirk","year":"2021","unstructured":"Kirk Rodrigues, Yu Luo, and Ding Yuan. \"CLP: Efficient and Scalable Search on Compressed Text Logs.\" In: OSDI. 2021, pp. 183--198.","journal-title":"OSDI."},{"key":"e_1_3_2_1_47_1","first-page":"452","volume-title":"Proceedings of the 18th European Conference on Computer Systems.","author":"Junyu","year":"2023","unstructured":"Junyu Wei et al. \"LogGrep: Fast and Cheap Cloud Log Storage by Exploiting both Static and Runtime Patterns\". In: Proceedings of the 18th European Conference on Computer Systems. 2023, pp. 452--468."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPOM.2003.1251233"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2004.1281456"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.1996.488311"},{"key":"e_1_3_2_1_51_1","first-page":"207","volume-title":"ISSRE'16: Proc. of the 27th International Symposium on Software Reliability Engineering. IEEE.","author":"Shilin","year":"2016","unstructured":"Shilin He et al. \"Experience report: system log analysis for anomaly detection\". In: ISSRE'16: Proc. of the 27th International Symposium on Software Reliability Engineering. IEEE. 2016, pp. 207--218."},{"key":"e_1_3_2_1_52_1","first-page":"195","volume-title":"2020 International Symposium on Reliable Distributed Systems (SRDS). IEEE.","author":"Bo","year":"2020","unstructured":"Bo Zhang et al. \"Anomaly detection via mining numerical workflow relations from logs\". In: 2020 International Symposium on Reliable Distributed Systems (SRDS). IEEE. 2020, pp. 195--204."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-022-00370-w"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0103"},{"key":"e_1_3_2_1_55_1","first-page":"1573","volume-title":"CIKM'16: Proc. of the 25th ACM International on Conference on Information and Knowledge Management. ACM.","author":"Hossein","year":"2016","unstructured":"Hossein Hamooni et al. \"Logmine: Fast pattern recognition for log analytics\". In: CIKM'16: Proc. of the 25th ACM International on Conference on Information and Knowledge Management. ACM. 2016, pp. 1573--1582."},{"key":"e_1_3_2_1_56_1","first-page":"33","volume-title":"ICWS'17:  2017 IEEE International Conference on Web Services. IEEE.","author":"Pinjia","year":"2017","unstructured":"Pinjia He et al. \"Drain: An online log parsing approach with fixed depth tree\". In: ICWS'17: 2017 IEEE International Conference on Web Services. IEEE. 2017, pp. 33--40."},{"key":"e_1_3_2_1_57_1","volume-title":"A directed acyclic graph approach to online log parsing\". In: arXiv preprint arXiv:1806.04356","author":"Pinjia He","year":"2018","unstructured":"Pinjia He et al. \"A directed acyclic graph approach to online log parsing\". In: arXiv preprint arXiv:1806.04356 (2018)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC1952"},{"key":"e_1_3_2_1_59_1","volume-title":"htttps:\/\/docs.python.org\/3\/library\/tarfile.html. [Online]","author":"Python Library","year":"2023","unstructured":"Python Library tarfile. htttps:\/\/docs.python.org\/3\/library\/tarfile.html. [Online]. 2023."},{"key":"e_1_3_2_1_60_1","volume-title":"https:\/\/github.com\/logpai\/logzip. [Online]","author":"LogZip Open","year":"2023","unstructured":"Open source code of LogZip. https:\/\/github.com\/logpai\/logzip. [Online]. 2023."},{"key":"e_1_3_2_1_61_1","volume-title":"https:\/\/github.com\/THUBear-wjy\/LogReducer. [Online]","author":"LogReducer Open","year":"2023","unstructured":"Open source code of LogReducer. https:\/\/github.com\/THUBear-wjy\/LogReducer. [Online]. 2023."},{"key":"e_1_3_2_1_62_1","volume-title":"https:\/\/github.com\/niklas-heer\/speed-comparison. [Online]","author":"Speed","year":"2023","unstructured":"Speed comparison of programming languages. https:\/\/github.com\/niklas-heer\/speed-comparison. [Online]. 2023."}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3608129","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3608129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:45Z","timestamp":1750182525000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3608129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,6]]},"references-count":62,"alternative-id":["10.1145\/3597503.3608129","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3608129","relation":{},"subject":[],"published":{"date-parts":[[2024,2,6]]},"assertion":[{"value":"2024-02-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}