{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:58:26Z","timestamp":1769727506191,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T00:00:00Z","timestamp":1574208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,11,20]]},"DOI":"10.1145\/3357223.3362736","type":"proceedings-article","created":{"date-parts":[[2019,11,11]],"date-time":"2019-11-11T18:15:00Z","timestamp":1573496100000},"page":"312-324","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Sifter"],"prefix":"10.1145","author":[{"given":"Pedro","family":"Las-Casas","sequence":"first","affiliation":[{"name":"Max Planck Institute for Software Systems"}]},{"given":"Giorgi","family":"Papakerashvili","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Software Systems"}]},{"given":"Vaastav","family":"Anand","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Software Systems"}]},{"given":"Jonathan","family":"Mace","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Software Systems"}]}],"member":"320","published-online":{"date-parts":[[2019,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Apache. Kafka: A Distributed Streaming Platform. Retrieved June 2019 from https:\/\/kafka.apache.org\/. (§2.2).  Apache. Kafka: A Distributed Streaming Platform. Retrieved June 2019 from https:\/\/kafka.apache.org\/. (§2.2)."},{"key":"e_1_3_2_1_2_1","volume-title":"Using Magpie for Request Extraction and Workload Modelling. In 6th USENIX Symposium on Operating Systems Design and Implementation (OSDI '04)","author":"Barham P."},{"key":"e_1_3_2_1_3_1","unstructured":"Y. Bengio R. Ducharme P. Vincent and C. Jauvin. A Neural Probabilistic Language Model. Journal of Machine Learning Research 3(Feb):1137--1155 2003. (§1 4.3 5.1 and 9).  Y. Bengio R. Ducharme P. Vincent and C. Jauvin. A Neural Probabilistic Language Model. Journal of Machine Learning Research 3(Feb):1137--1155 2003. (§1 4.3 5.1 and 9)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(97)00060-3"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","volume-title":"Whodunit: Transactional Profiling for Multi-Tier Applications. In 2nd ACM European Conference on Computer Systems (EuroSys '07)","author":"Chanda A.","DOI":"10.1145\/1272996.1273001"},{"key":"e_1_3_2_1_6_1","volume-title":"Path-Based Failure and Evolution Management. In 1st USENIX Symposium on Networked Systems Design and Implementation (NSDI '04)","author":"Chen M. Y."},{"key":"e_1_3_2_1_7_1","volume-title":"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)","author":"Chow M."},{"key":"e_1_3_2_1_8_1","volume-title":"X-Trace: A Pervasive Network Tracing Framework. In 4th USENIX Symposium on Networked Systems Design and Implementation (NSDI '07)","author":"Fonseca R."},{"key":"e_1_3_2_1_9_1","volume-title":"24th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '19). (§1 and 7.1).","author":"Gan Y."},{"key":"e_1_3_2_1_10_1","volume-title":"24th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '19)","author":"Gan Y."},{"key":"e_1_3_2_1_11_1","unstructured":"Jaeger. Jaeger: Open Source End-to-End Distributed Tracing. Retrieved June 2019 from https:\/\/www.jaegertracing.io\/. (§1 2.1 and 6).  Jaeger. Jaeger: Open Source End-to-End Distributed Tracing. Retrieved June 2019 from https:\/\/www.jaegertracing.io\/. (§1 2.1 and 6)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000331"},{"key":"e_1_3_2_1_13_1","unstructured":"R.Johnson. Facebook's Scribe technology now open source. Retrieved August 2017 from https:\/\/www.facebook.com\/note.php?note_id=32008268919. (§2.2).  R.Johnson. Facebook's Scribe technology now open source. Retrieved August 2017 from https:\/\/www.facebook.com\/note.php?note_id=32008268919. (§2.2)."},{"key":"e_1_3_2_1_14_1","volume-title":"Canopy: An End-to-End Performance Tracing And Analysis System. In 26th ACM Symposium on Operating Systems Principles (SOSP '17)","author":"Kaldor J."},{"key":"e_1_3_2_1_15_1","volume-title":"Black-Box Problem Diagnosis in Parallel File Systems. In 8th USENIX Conference on File and Storage Technologies (FAST '10)","author":"Kasick M. P."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/359545.359563"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","volume-title":"Weighted Sampling of Execution Traces: Capturing More Needles and Less Hay. In 10th ACM Symposium on Cloud Computing (SOCC '18)","author":"Las-Casas P.","DOI":"10.1145\/3267809.3267841"},{"key":"e_1_3_2_1_18_1","volume-title":"Distributed Representations of Sentences and Documents. In 31st International Conference on Machine Learning (ICML '14)","author":"Le Q."},{"key":"e_1_3_2_1_19_1","volume-title":"Thesis","author":"Leavitt J.","year":"2014"},{"key":"e_1_3_2_1_20_1","volume-title":"USENIX Annual Technical Conference (ATC '10)","author":"Lou J.-G."},{"key":"e_1_3_2_1_21_1","volume-title":"Project","author":"Mace J.","year":"2013"},{"key":"e_1_3_2_1_22_1","volume-title":"Universal Context Propagation for Distributed System Instrumentation. In 13th ACM European Conference on Computer Systems (EuroSys '18)","author":"Mace J."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","volume-title":"Pivot Tracing: Dynamic Causal Monitoring for Distributed Systems. In 25th ACM Symposium on Operating Systems Principles (SOSP '15)","author":"Mace J.","DOI":"10.1145\/2815400.2815415"},{"key":"e_1_3_2_1_24_1","volume-title":"Modeling the Parallel Execution of Black-Box Services. In 3rd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud '11)","author":"Mann G."},{"key":"e_1_3_2_1_25_1","volume-title":"27th Conference on Neural Information Processing Systems (NIPS '13)","author":"Mikolov T."},{"key":"e_1_3_2_1_26_1","volume-title":"9th USENIX Conference on Networked Systems Design and Implementation (NSDI '12)","author":"Nagaraj K."},{"key":"e_1_3_2_1_27_1","unstructured":"OpenTracing. OpenTracing. Retrieved January 2017 from http:\/\/opentracing.io\/. (§1 and 2.1).  OpenTracing. OpenTracing. Retrieved January 2017 from http:\/\/opentracing.io\/. (§1 and 2.1)."},{"key":"e_1_3_2_1_28_1","volume-title":"Diagnosing Latency in Multi-Tier Black-Box Services. In 5th Workshop on Large Scale Distributed Systems and Middleware (LADIS '11)","author":"Ostrowski K."},{"key":"e_1_3_2_1_29_1","volume-title":"8th USENIX Symposium on Networked Systems Design and Implementation (NSDI '11)","author":"Sambasivan R. R."},{"key":"e_1_3_2_1_30_1","unstructured":"K. Shvachko H. Kuang S. Radia and R. Chansler. The Hadoop Distributed File System. (§1 and 7.1).  K. Shvachko H. Kuang S. Radia and R. Chansler. The Hadoop Distributed File System. (§1 and 7.1)."},{"key":"e_1_3_2_1_32_1","volume-title":"2006 ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS '06)","author":"Thereska E."},{"key":"e_1_3_2_1_33_1","volume-title":"Low-Latency Continual Learning. In 10th ACM Symposium on Cloud Computing (SOCC '18)","author":"Tian H."},{"key":"e_1_3_2_1_34_1","unstructured":"Twitter. Zipkin. Retrieved July 2017 from http:\/\/zipkin.io\/. (§1 2.1 and 6).  Twitter. Zipkin. Retrieved July 2017 from http:\/\/zipkin.io\/. (§1 2.1 and 6)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","volume-title":"Apache Hadoop YARN: Yet Another Resource Negotiator. In 4th ACM Symposium on Cloud Computing (SoCC '13)","author":"Vavilapalli V. K.","DOI":"10.1145\/2523616.2523633"},{"key":"e_1_3_2_1_36_1","first-page":"1201","article-title":"Graph kernels","volume":"99","author":"Vishwanathan S.","year":"2010","journal-title":"JMLR"},{"key":"e_1_3_2_1_37_1","volume-title":"Phan. Zeno: Diagnosing Performance Problems with Temporal Provenance. In 16th USENIX Conference on Networked Systems Design and Implementation (NSDI '19)","author":"Wu Y."},{"key":"e_1_3_2_1_38_1","volume-title":"22nd ACM Symposium on Operating Systems Principles (SOSP '09)","author":"Xu W."},{"key":"e_1_3_2_1_39_1","volume-title":"Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detection. In 24th ACM Conference on Computer and Communications Security (CCS '17)","author":"Xu X."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","volume-title":"Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing. In 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI '12)","author":"Zaharia M.","DOI":"10.1145\/2886107.2886110"},{"key":"e_1_3_2_1_41_1","volume-title":"26th ACM Symposium on Operating Systems Principles (SOSP '17)","author":"Zhao X."},{"key":"e_1_3_2_1_42_1","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI '16)","author":"Zhao X."},{"key":"e_1_3_2_1_43_1","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI '14)","author":"Zhao X."}],"event":{"name":"SoCC '19: ACM Symposium on Cloud Computing","location":"Santa Cruz CA USA","acronym":"SoCC '19","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357223.3362736","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3357223.3362736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:44Z","timestamp":1750202024000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3357223.3362736"}},"subtitle":["Scalable Sampling for Distributed Traces, without Feature Engineering"],"short-title":[],"issued":{"date-parts":[[2019,11,20]]},"references-count":42,"alternative-id":["10.1145\/3357223.3362736","10.1145\/3357223"],"URL":"https:\/\/doi.org\/10.1145\/3357223.3362736","relation":{},"subject":[],"published":{"date-parts":[[2019,11,20]]},"assertion":[{"value":"2019-11-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}