{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T12:40:04Z","timestamp":1756816804465,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":437,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1845638, 1740305, 2008295, 2106197, 2103794"],"award-info":[{"award-number":["1845638, 1740305, 2008295, 2106197, 2103794"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3736229.3736264","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T10:07:28Z","timestamp":1756807648000},"page":"23-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Compression for High-Performance Lineage"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6658-8287","authenticated-orcid":false,"given":"Xiaoyu","family":"Han","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4535-1926","authenticated-orcid":false,"given":"Haneen","family":"Mohammed","sequence":"additional","affiliation":[{"name":"Columbia University, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6301-9430","authenticated-orcid":false,"given":"Charlie","family":"Summers","sequence":"additional","affiliation":[{"name":"Columbia University, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4254-6688","authenticated-orcid":false,"given":"Eugene","family":"Wu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,2]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Crossfilter. http:\/\/square.github.io\/crossfilter\/."},{"key":"e_1_3_3_1_3_2","unstructured":"Rill Data. https:\/\/www.rilldata.com\/."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142548"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Kyoungsoo Bok Jieun Han Jongtae Lim and Jaesoo Yoo. 2020. Provenance compression scheme based on graph patterns for large RDF documents. J. Supercomput. 76 8 (2020) 6376\u20136398.","DOI":"10.1007\/s11227-019-02926-2"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610520"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035926"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Zaheer Chothia John Liagouris Frank McSherry and Timothy Roscoe. 2016. Explaining Outputs in Modern Data Analytics. Proc. VLDB Endow. 9 12 (2016) 1137\u20131148.","DOI":"10.14778\/2994509.2994530"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Yann Collet and Murray Kucherawy. 2021. Zstandard Compression and the \u2019application\/zstd\u2019 Media Type. RFC 8878. https:\/\/doi.org\/10.17487\/RFC8878","DOI":"10.17487\/RFC8878"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Yingwei Cui Jennifer Widom and Janet\u00a0L. Wiener. 2000. Tracing the lineage of view data in a warehousing environment. ACM Trans. Database Syst. 25 2 (2000) 179\u2013227.","DOI":"10.1145\/357775.357777"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00228"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"L.\u00a0Peter Deutsch. 1996. DEFLATE Compressed Data Format Specification version 1.3. RFC 1951. https:\/\/doi.org\/10.17487\/RFC1951","DOI":"10.17487\/rfc1951"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380574"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.15"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Heer and Dominik Moritz. 2023. Mosaic: An architecture for scalable & interoperable data views. IEEE Transactions on Visualization and Computer Graphics 30 1 (2023) 436\u2013446.","DOI":"10.1109\/TVCG.2023.3327189"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Seokki Lee Bertram Lud\u00e4scher and Boris Glavic. 2020. Approximate Summaries for Why and Why-not Provenance. Proc. VLDB Endow. 13 6 (2020) 912\u2013924.","DOI":"10.14778\/3380750.3380760"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Chenjie Li Juseung Lee Zhengjie Miao Boris Glavic and Sudeepa Roy. 2022. CaJaDE: Explaining Query Results by Augmenting Provenance with Context. Proc. VLDB Endow. 15 12 (2022) 3594\u20133597.","DOI":"10.14778\/3554821.3554852"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Zhicheng Liu Biye Jiang and Jeffrey Heer. 2013. imMens: Real-time Visual Querying of Big Data. Comput. Graph. Forum 32 3 (2013) 421\u2013430.","DOI":"10.1111\/cgf.12129"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589731"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Haneen Mohammed Alexander Yao Charlie Summers Hongbin Zhong Gromit Yeuk-Yin Chan Subrata Mitra Lampros Flokas and Eugene Wu. 2025. FaDE: More Than a Million What-ifs Per Second. Proc. VLDB Endow. (2025).","DOI":"10.14778\/3717755.3717757"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2017.104"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209900.3209904"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Fotis Psallidas and Eugene Wu. 2018. Smoke: Fine-grained Lineage at Interactive Speed. Proc. VLDB Endow. 11 6 (2018) 719\u2013732.","DOI":"10.14778\/3184470.3184475"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3320212"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Pierre Senellart Louis Jachiet Silviu Maniu and Yann Ramusat. 2018. ProvSQL: Provenance and Probability Management in PostgreSQL. Proc. VLDB Endow. 11 12 (2018) 2034\u20132037.","DOI":"10.14778\/3229863.3236253"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Hendrik Strobelt Sebastian Gehrmann Michael Behrisch Adam Perer Hanspeter Pfister and Alexander\u00a0M. Rush. 2019. Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models. IEEE Trans. Vis. Comput. Graph. 25 1 (2019) 353\u2013363.","DOI":"10.1109\/TVCG.2018.2865044"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Changda Wang Syed\u00a0Rafiul Hussain and Elisa Bertino. 2016. Dictionary Based Secure Provenance Compression for Wireless Sensor Networks. IEEE Trans. Parallel Distributed Syst. 27 2 (2016) 405\u2013418.","DOI":"10.1109\/TPDS.2015.2402156"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Eugene Wu and Samuel Madden. 2013. Scorpion: Explaining Away Outliers in Aggregate Queries. Proc. VLDB Endow. 6 8 (2013) 553\u2013564.","DOI":"10.14778\/2536354.2536356"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544881"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389696"},{"key":"e_1_3_3_1_31_2","volume-title":"TaPP","author":"Xie Yulai","year":"2011","unstructured":"Yulai Xie, Kiran-Kumar Muniswamy-Reddy, Darrell D.\u00a0E. Long, Ahmed Amer, Dan Feng, and Zhipeng Tan. 2011. Compressing Provenance Graphs. In TaPP. USENIX Association."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00047"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Jie Ying Tiantian Zhu Mingqi Lv and Tieming Chen. 2025. DEHYDRATOR: Enhancing Provenance Graph Storage via Hierarchical Encoding and Sequence Generation. CoRR abs\/2501.00446 (2025).","DOI":"10.1109\/TIFS.2025.3592824"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00281"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Jacob Ziv and Abraham Lempel. 1977. A universal algorithm for sequential data compression. IEEE Trans. Inf. Theory 23 3 (1977) 337\u2013343.","DOI":"10.1109\/TIT.1977.1055714"}],"event":{"name":"PW' 25: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Berlin Germany","acronym":"PW' 25"},"container-title":["Proceedings of the ProvenanceWeek 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736229.3736264","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736229.3736264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T11:59:16Z","timestamp":1756814356000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3736229.3736264"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":34,"alternative-id":["10.1145\/3736229.3736264","10.1145\/3736229"],"URL":"https:\/\/doi.org\/10.1145\/3736229.3736264","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-09-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}