{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T13:19:13Z","timestamp":1775135953150,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584161","type":"print"},{"value":"9789819584178","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-8417-8_12","type":"book-chapter","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:30:16Z","timestamp":1775133016000},"page":"157-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DAGLoc: End-to-End Troubleshooting Approach for\u00a0Big Data Scheduling System"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1998-7100","authenticated-orcid":false,"given":"Xueyong","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shipeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4641-1326","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/TIFS.2019.2923577","volume":"15","author":"P Krishnamurthy","year":"2019","unstructured":"Krishnamurthy, P., Karri, R., Khorrami, F.: Anomaly detection in real-time multi-threaded processes using hardware performance counters. IEEE Trans. Inf. Forensics Secur. 15, 666\u2013680 (2019). https:\/\/doi.org\/10.1109\/TIFS.2019.2923577","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"12_CR2","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/j.future.2018.12.002","volume":"95","author":"S Lu","year":"2019","unstructured":"Lu, S., Wei, X., Rao, B., et al.: LADRA: log-based abnormal task detection and root-cause analysis in big data processing with Spark. Futur. Gener. Comput. Syst. 95, 392\u2013403 (2019). https:\/\/doi.org\/10.1016\/j.future.2018.12.002","journal-title":"Futur. Gener. Comput. Syst."},{"issue":"4","key":"12_CR3","doi-asserted-by":"publisher","first-page":"4255","DOI":"10.1109\/TNSM.2024.3387552","volume":"21","author":"J Yang","year":"2024","unstructured":"Yang, J., Guo, Y., Chen, Y., et al.: MicroNet: operation aware root cause identification of microservice system anomalies. IEEE T. Netw. Serv. Man. 21(4), 4255\u20134267 (2024). https:\/\/doi.org\/10.1109\/TNSM.2024.3387552","journal-title":"IEEE T. Netw. Serv. Man."},{"issue":"3","key":"12_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3501297","volume":"55","author":"J Soldani","year":"2022","unstructured":"Soldani, J., Brogi, A.: Anomaly detection and failure root cause analysis in (micro) service-based cloud applications: a survey. ACM Comput. Surv. 55(3), 1\u201339 (2022). https:\/\/doi.org\/10.1145\/3501297","journal-title":"ACM Comput. Surv."},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Zhao, N., et al.: Understanding and handling alert storm for online service systems. In: the ACM\/IEEE 42nd International Conference on Software Engineering: Software Engineering in Practice. In: ACM\/IEEE, pp. 162-171 (2020). https:\/\/doi.org\/10.1145\/3377813.3381363","DOI":"10.1145\/3377813.3381363"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Graph-based incident aggregation for large-scale online service systems. In: 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 430-442 (2021). https:\/\/doi.org\/10.1109\/ASE51524.2021.9678746","DOI":"10.1109\/ASE51524.2021.9678746"},{"issue":"12","key":"12_CR7","doi-asserted-by":"publisher","first-page":"9179","DOI":"10.1109\/JIOT.2021.3100509","volume":"9","author":"Z Chen","year":"2021","unstructured":"Chen, Z., Chen, D., Zhang, X., Yuan, Z., Cheng, X.: Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Internet Things. 9(12), 9179\u20139189 (2021). https:\/\/doi.org\/10.1109\/JIOT.2021.3100509","journal-title":"IEEE Internet Things."},{"key":"12_CR8","unstructured":"Li, L., et al.: Fighting the fog of war: Automated incident detection for cloud systems. In: 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp. 131\u2013146 (2021)"},{"key":"12_CR9","doi-asserted-by":"publisher","unstructured":"Liu, D., et al.: Microhecl: High-efficient root cause localization in large-scale microservice systems. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), pp. 338\u2013347 (2021). https:\/\/doi.org\/10.1109\/ICSE-SEIP52600.2021.00043","DOI":"10.1109\/ICSE-SEIP52600.2021.00043"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Wu, L., Tordsson, J., Elmroth, E., Kao, O.: Microrca: root cause localization of performance issues in microservices. In: NOMS 2020-2020 IEEE\/IFIP Network Operations and Management Symposium, pp. 1\u20139 (2020). https:\/\/doi.org\/10.1109\/NOMS47738.2020.9110353","DOI":"10.1109\/NOMS47738.2020.9110353"},{"key":"12_CR11","doi-asserted-by":"publisher","unstructured":"Ma, M., Xu, J., Wang, Y., Chen, P., Zhang, Z., Wang, P.: Automap: diagnose your microservice-based web applications automatically. In: Proceedings of the Web Conference, pp. 246\u2013258 (2020). https:\/\/doi.org\/10.1145\/3366423.3380111","DOI":"10.1145\/3366423.3380111"},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Yu, G., et al.: Microrank: End-to-end latency issue localization with extended spectrum analysis in microservice environments. In: Proceedings of the Web Conference 2021, pp. 3087\u20133098 (2021). https:\/\/doi.org\/10.1145\/3442381.3449905","DOI":"10.1145\/3442381.3449905"},{"key":"12_CR13","doi-asserted-by":"publisher","unstructured":"Zhang, S., Liu, J.: Multivariate time series anomaly detection based on graph neural network for big data scheduling system. In: International Conference on Web Information Systems Engineering, pp. 791\u2013800 (2023). https:\/\/doi.org\/10.1007\/978-981-99-7254-8-61","DOI":"10.1007\/978-981-99-7254-8-61"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Liu, P., Chen, Y., Nie, X., Zhu, J., Zhang, S., Sui, K., Pei, D.: Fluxrank: a widely-deployable framework to automatically localizing root cause machines for software service failure mitigation. In: 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE), pp. 35-46 (2019). https:\/\/doi.org\/10.1109\/ISSRE.2019.00014","DOI":"10.1109\/ISSRE.2019.00014"},{"key":"12_CR15","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: Generic and robust localization of multi-dimensional root causes. In: 2019 IEEE 30th International Symposium on Software Reliability Engineering (ISSRE), pp. 47\u201357 (2019). https:\/\/doi.org\/10.1109\/ISSRE.2019.00015","DOI":"10.1109\/ISSRE.2019.00015"},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: Outage prediction and diagnosis for cloud service systems. In: The world wide web conference, pp. 2659\u20132665 (2019). https:\/\/doi.org\/10.1145\/3308558.3313501","DOI":"10.1145\/3308558.3313501"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Colombo, D., Maathuis, M.H., Kalisch, M., Richardson, T.S.: Learning high-dimensional directed acyclic graphs with latent and selection variables. Ann. Stat. 40(1), 294\u2013321 (2012)","DOI":"10.1214\/11-AOS940"},{"key":"12_CR18","doi-asserted-by":"publisher","unstructured":"Chen, T., Guestrin, C.: Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794 (2016). https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"12_CR19","unstructured":"Li, L., et al.: Fighting the fog of war: Automated incident detection for cloud systems. In: 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp. 131\u2013146 (2021)"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Nick, T.G., Campbell, K.M.: Logistic regression. Topics Biostat. 404(1), 273\u2013301 (2007). https:\/\/doi.org\/10.1007\/978-1-59745-530-5-14","DOI":"10.1007\/978-1-59745-530-5-14"},{"key":"12_CR21","doi-asserted-by":"publisher","unstructured":"Cover. T., Hart. P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21\u201327 (1967). https:\/\/doi.org\/10.1109\/TIT 1967.1053964","DOI":"10.1109\/TIT"},{"key":"12_CR22","unstructured":"Liaw, A., Wiener, M.: Classification and regression by RandomForest. R News 2(3), 18\u201322 (2002)"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189\u20131232 (2001). https:\/\/doi.org\/10.2307\/2699986","DOI":"10.2307\/2699986"},{"issue":"1","key":"12_CR24","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1145\/2494232.2465753","volume":"41","author":"M Kim","year":"2013","unstructured":"Kim, M., Sumbaly, R., Shah, S.: Root cause detection in a service-oriented architecture. ACM SIGMETRICS Perform. Eval. Rev. 41(1), 93\u2013104 (2013). https:\/\/doi.org\/10.1145\/2494232.2465753","journal-title":"ACM SIGMETRICS Perform. Eval. Rev."},{"key":"12_CR25","unstructured":"Bhagwan, Ret al.: Adtributor: Revenue debugging in advertising systems. In: 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14), pp. 43-55 (2014)"},{"key":"12_CR26","unstructured":"Persson, M., Rudenius, L.: Anomaly detection and fault localization an automated process for advertising systems, pp. 1\u201390 (2018)"},{"key":"12_CR27","doi-asserted-by":"publisher","first-page":"10909","DOI":"10.1109\/ACCESS.2018.2804764","volume":"6","author":"Y Sun","year":"2018","unstructured":"Sun, Y., et al.: Hotspot: Anomaly localization for additive kpis with multi-dimensional attributes. IEEE Access 6, 10909\u201310923 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2018.2804764","journal-title":"IEEE Access"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Jing, P., Han, Y., Sun, J., Lin, T., Hu, Y.: AutoRoot: A novel fault localization schema of multi-dimensional root causes. In: 2021 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1\u20137 (2021). https:\/\/doi.org\/10.1109\/ WCNC49053.2021.9417302","DOI":"10.1109\/WCNC49053.2021.9417302"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8417-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:30:19Z","timestamp":1775133019000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8417-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584161","9789819584178"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8417-8_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"3 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}