{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T08:15:17Z","timestamp":1768896917434,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,14]]},"DOI":"10.1145\/3447548.3467190","type":"proceedings-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T06:12:05Z","timestamp":1628748725000},"page":"3948-3958","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["HALO: Hierarchy-aware Fault Localization for Cloud Systems"],"prefix":"10.1145","author":[{"given":"Xu","family":"Zhang","sequence":"first","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"given":"Chao","family":"Du","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"given":"Yifan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"given":"Hongyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Newcastle, Newcastle, Australia"}]},{"given":"Si","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"given":"Ze","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Azure, Redmond, WA, USA"}]},{"given":"Qingwei","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"given":"Yingnong","family":"Dang","sequence":"additional","affiliation":[{"name":"Microsoft Azure, Redmond, WA, USA"}]},{"given":"Andrew","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft 365, Suzhou, China"}]},{"given":"Saravanakumar","family":"Rajmohan","sequence":"additional","affiliation":[{"name":"Microsoft 365, Redmond, WA, USA"}]},{"given":"Dongmei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Kusto. https:\/\/docs.microsoft.com\/en-us\/azure\/data-explorer\/kusto\/query\/.  Kusto. https:\/\/docs.microsoft.com\/en-us\/azure\/data-explorer\/kusto\/query\/."},{"key":"e_1_3_2_2_2_1","unstructured":"Observability telemetry and monitoring. https:\/\/cloud.ibm.com\/docs\/java?topic=cloud-native-observability-cn.  Observability telemetry and monitoring. https:\/\/cloud.ibm.com\/docs\/java?topic=cloud-native-observability-cn."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377813.3381353"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/312129.312263"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011429418057"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1133905.1133907"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106306"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00020"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2004.1301345"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion.2019.00023"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.115"},{"key":"e_1_3_2_2_12_1","volume-title":"Fail-slow at scale: Evidence of hardware performance faults in large production systems. ACM Transactions on Storage (TOS), 14(3):1--26","author":"Gunawi H. S.","year":"2018","unstructured":"H. S. Gunawi , R. O. Suminto , R. Sears , C. Golliher , S. Sundararaman , X. Lin , T. Emami , W. Sheng , N. Bidokhti , C. McCaffrey , Fail-slow at scale: Evidence of hardware performance faults in large production systems. ACM Transactions on Storage (TOS), 14(3):1--26 , 2018 . H. S. Gunawi, R. O. Suminto, R. Sears, C. Golliher, S. Sundararaman, X. Lin, T. Emami, W. Sheng, N. Bidokhti, C. McCaffrey, et al. Fail-slow at scale: Evidence of hardware performance faults in large production systems. ACM Transactions on Storage (TOS), 14(3):1--26, 2018."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:DAMI.0000005258.31418.83"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-014-0145-3"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3102980.3103005"},{"key":"e_1_3_2_2_16_1","first-page":"346","volume-title":"The International Conference on Information Networking 2014 (ICOIN2014)","author":"Kim J.","year":"2014","unstructured":"J. Kim and E. Lee . Empirical evaluation of existing algorithms of spectrum based fault localization . In The International Conference on Information Networking 2014 (ICOIN2014) , pages 346 -- 351 . IEEE, 2014 . J. Kim and E. Lee. Empirical evaluation of existing algorithms of spectrum based fault localization. In The International Conference on Information Networking 2014 (ICOIN2014), pages 346--351. IEEE, 2014."},{"key":"e_1_3_2_2_17_1","first-page":"389","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Li Z.","year":"2020","unstructured":"Z. Li , Q. Cheng , K. Hsieh , Y. Dang , P. Huang , P. Singh , X. Yang , Q. Lin , Y. Wu , S. Levy , : An intelligent, end-to-end analytics service for safe deployment in large-scale cloud infrastructure . In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20) , pages 389 -- 402 , 2020 . Z. Li, Q. Cheng, K. Hsieh, Y. Dang, P. Huang, P. Singh, X. Yang, Q. Lin, Y. Wu, S. Levy, et al. Gandalf: An intelligent, end-to-end analytics service for safe deployment in large-scale cloud infrastructure. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), pages 389--402, 2020."},{"issue":"1","key":"e_1_3_2_2_18_1","first-page":"23","article-title":"Fast dimensional analysis for root cause investigation in a large-scale service environment","volume":"4","author":"Lin F.","year":"2020","unstructured":"F. Lin , K. Muzumdar , N. Laptev , M.-V. Curelea , S. Lee , and S. Sankar . Fast dimensional analysis for root cause investigation in a large-scale service environment . Proceedings of the ACM on Measurement and Analysis of Computing Systems , 4 : 1 -- 23 , 2020 . F. Lin, K. Muzumdar, N. Laptev, M.-V. Curelea, S. Lee, and S. Sankar. Fast dimensional analysis for root cause investigation in a large-scale service environment. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 4:1 -- 23, 2020.","journal-title":"Proceedings of the ACM on Measurement and Analysis of Computing Systems"},{"issue":"21","key":"e_1_3_2_2_19_1","first-page":"21","article-title":"Cancer characterization and feature set extraction by discriminative margin clustering","volume":"5","author":"Munagala K.","year":"2003","unstructured":"K. Munagala , R. Tibshirani , and P. Brown . Cancer characterization and feature set extraction by discriminative margin clustering . BMC Bioinformatics , 5 : 21 -- 21 , 2003 . K. Munagala, R. Tibshirani, and P. Brown. Cancer characterization and feature set extraction by discriminative margin clustering. BMC Bioinformatics, 5:21 -- 21, 2003.","journal-title":"BMC Bioinformatics"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788624"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403306"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7840800"},{"key":"e_1_3_2_2_23_1","volume-title":"Speech understanding systems: A summary of results of the five-year research effort. department of computer science","author":"Reddy D. R.","year":"1977","unstructured":"D. R. Reddy Speech understanding systems: A summary of results of the five-year research effort. department of computer science , 1977 . D. R. Reddy et al. Speech understanding systems: A summary of results of the five-year research effort. department of computer science, 1977."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.1631315"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-020-00660-9"}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event Singapore","acronym":"KDD '21","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467190","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3467190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:27Z","timestamp":1750191507000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":25,"alternative-id":["10.1145\/3447548.3467190","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3467190","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}