{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T19:44:33Z","timestamp":1765568673964,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","funder":[{"name":"National Science Foundation (NSF)","award":["IIS-1954644"],"award-info":[{"award-number":["IIS-1954644"]}]},{"name":"National Science Foundation (NSF)","award":["IIS-2046236"],"award-info":[{"award-number":["IIS-2046236"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,3]]},"DOI":"10.1145\/3748636.3762714","type":"proceedings-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T19:11:30Z","timestamp":1765566690000},"page":"107-119","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SynopsisLake: Quality-aware Approximate Spatial Query Processing Using Data Synopses"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0567-0129","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University of California, Riverside, Riverside, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6584-1455","authenticated-orcid":false,"given":"Ahmed","family":"Eldawy","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of California, Riverside, Riverside, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183761"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2745754.2745772"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2500128"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465355"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733085.2733096"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/2831360.2831361"},{"key":"e_1_3_2_1_7_1","unstructured":"Amazon. [n. d.]. Amazon AWS Data Lake. https:\/\/aws.amazon.com\/big-data\/datalakes-and-analytics\/"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings 17th International Conference on Data Engineering. IEEE, 368\u2013375","author":"An Ning","year":"2001","unstructured":"Ning An, Zhen-Yu Yang, and Anand Sivasubramaniam. 2001. Selectivity estimation for spatial joins. In Proceedings 17th International Conference on Data Engineering. IEEE, 368\u2013375."},{"key":"e_1_3_2_1_9_1","unstructured":"Apache Hudi. 2021. Apache Hudi. https:\/\/hudi.apache.org"},{"key":"e_1_3_2_1_10_1","unstructured":"Apache Iceberg. 2017. Apache Iceberg. https:\/\/iceberg.apache.org"},{"key":"e_1_3_2_1_11_1","unstructured":"Apache ORC. 2013. Apache ORC. https:\/\/orc.apache.org"},{"key":"e_1_3_2_1_12_1","unstructured":"Apache Parquet. 2013. Apache Parquet. https:\/\/parquet.apache.org"},{"key":"e_1_3_2_1_13_1","unstructured":"Apache Puffin. 2022. Apache Puffin. https:\/\/iceberg.apache.org\/puffin-spec\/#blobmetadata"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415560"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of CIDR","volume":"8","author":"Armbrust Michael","year":"2021","unstructured":"Michael Armbrust, Ali Ghodsi, Reynold Xin, and Matei Zaharia. 2021. Lakehouse: a new generation of open platforms that unify data warehousing and advanced analytics. In Proceedings of CIDR, Vol. 8."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066172"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526054"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0054333"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00067"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/767141.767147"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242524.1242526"},{"key":"e_1_3_2_1_22_1","volume-title":"Data Lakes: A Survey Paper. In Innovations in Smart Cities Applications Volume 5: The Proceedings of the 6th International Conference on Smart City Applications","author":"Cherradi Mohamed","year":"2022","unstructured":"Mohamed Cherradi and Anass EL Haddadi. 2022. Data Lakes: A Survey Paper. In Innovations in Smart Cities Applications Volume 5: The Proceedings of the 6th International Conference on Smart City Applications. Springer, 823\u2013835."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Graham Cormode Minos Garofalakis Peter J Haas Chris Jermaine et al. 2011. Synopses for massive data: Samples histograms wavelets sketches. Foundations and Trends\u00ae in Databases 4 1\u20133 (2011) 1\u2013294.","DOI":"10.1561\/1900000004"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452021.3458316"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2003.12.001"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007646"},{"key":"e_1_3_2_1_27_1","volume-title":"Conference On Learning Theory. PMLR, 819\u2013842","author":"Diakonikolas Ilias","year":"2018","unstructured":"Ilias Diakonikolas, Jerry Li, and Ludwig Schmidt. 2018. Fast and sample near-optimal algorithms for learning multidimensional histograms. In Conference On Learning Theory. PMLR, 819\u2013842."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487664.3487783"},{"key":"e_1_3_2_1_29_1","unstructured":"James Dixon. 2010. Pentaho Hadoop and Data Lakes. https:\/\/jamesdixon.wordpress.com\/2010\/10\/14\/pentaho-hadoop-and-data-lakes"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00046"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.6086\/N100004J"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.6086\/N1668B70"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.6086\/N1RX994T"},{"key":"e_1_3_2_1_34_1","volume-title":"Hyperloglog: the analysis of a near-optimal cardinality estimation algorithm. Discrete mathematics & theoretical computer science Proceedings","author":"Flajolet Philippe","year":"2007","unstructured":"Philippe Flajolet, \u00c9ric Fusy, Olivier Gandouet, and Fr\u00e9d\u00e9ric Meunier. 2007. Hyperloglog: the analysis of a near-optimal cardinality estimation algorithm. Discrete mathematics & theoretical computer science Proceedings (2007)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407817"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183746"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/304181.304208"},{"key":"e_1_3_2_1_38_1","volume-title":"Data Lakes: A Survey of Functions and Systems","author":"Hai Rihan","year":"2023","unstructured":"Rihan Hai, Christos Koutras, Christoph Quix, and Matthias Jarke. 2023. Data Lakes: A Survey of Functions and Systems. IEEE Transactions on Knowledge and Data Engineering (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389741"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3452805"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452456"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0865-5_26"},{"key":"e_1_3_2_1_43_1","unstructured":"IBM. [n. d.]. IBM Data Lake and Lakehouse. https:\/\/www.ibm.com\/data-lake"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/568271.223841"},{"key":"e_1_3_2_1_45_1","first-page":"24","article-title":"Optimal histograms with quality guarantees","volume":"98","author":"Jagadish Hosagrahar Visvesvaraya","year":"1998","unstructured":"Hosagrahar Visvesvaraya Jagadish, Nick Koudas, S Muthukrishnan, Viswanath Poosala, Kenneth C Sevcik, and Torsten Suel. 1998. Optimal histograms with quality guarantees. In VLDB, Vol. 98. 24\u201327.","journal-title":"VLDB"},{"key":"e_1_3_2_1_46_1","volume-title":"ITM web of conferences","author":"Khine Pwint Phyu","unstructured":"Pwint Phyu Khine and Zhao Shun Wang. 2018. Data lake: a new ideology in big data era. In ITM web of conferences, Vol. 17. EDP Sciences, 03025."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247502"},{"key":"e_1_3_2_1_48_1","volume-title":"Wolfgang Gatterbauer, Ren\u00e9e J Miller, and Mirek Riedewald.","author":"Leventidis Aristotelis","year":"2021","unstructured":"Aristotelis Leventidis, Laura Di Rocco, Wolfgang Gatterbauer, Ren\u00e9e J Miller, and Mirek Riedewald. 2021. DomainNet: Homograph Detection for Data Lake Disambiguation. arXiv preprint arXiv:2103.09940 (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00050"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-016-0424-7"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352135"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276344"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467871"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137637"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3056100"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476353"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1386118.1386121"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-020-00608-7"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006498"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342635"},{"key":"e_1_3_2_1_61_1","volume-title":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Spatial Gems (SpatialGems 2020)","author":"Singla Samriddhi","year":"2020","unstructured":"Samriddhi Singla and Ahmed Eldawy. 2020. Flexible computation of multidimensional histograms. In Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Spatial Gems (SpatialGems 2020)(Seattle, Washington, USA). ACM."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457250"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45876-X_38"},{"key":"e_1_3_2_1_64_1","unstructured":"Wenbo Tao Adam Sah Leilani Battle Remco Chang and Michael Stonebraker. 2021. Kyrix-J: Visual Discovery of Connected Datasets in a Data Lake. (2021)."},{"key":"e_1_3_2_1_65_1","volume-title":"Proceedings. 20th International Conference on Data Engineering. IEEE, 214\u2013225","author":"Tao Yufei","year":"2004","unstructured":"Yufei Tao, George Kollios, Jeffrey Considine, Feifei Li, and Dimitris Papadias. 2004. Spatio-temporal aggregation using sketches. In Proceedings. 20th International Conference on Data Engineering. IEEE, 214\u2013225."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-012-0293-7"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/304181.304199"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/288627.288645"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494150"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spasta.2012.08.001"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47724-1_10"},{"key":"e_1_3_2_1_72_1","volume-title":"Beta distribution","author":"Wikipedia","year":"2024","unstructured":"Wikipedia contributors. 2024. Beta distribution, Practical Implementations: Alpha and Beta Calculations Summary- Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Beta_distribution&oldid=1210316554. [Online; accessed 28-February-2024]."},{"key":"e_1_3_2_1_73_1","volume-title":"The Free Encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Skewness&oldid=1272988155 [Online","author":"Wikipedia Wikipedia","year":"2025","unstructured":"Wikipedia contributors. 2025. Skewness \u2014 Wikipedia, The Free Encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Skewness&oldid=1272988155 [Online; accessed 24-February-2025]."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531759"},{"key":"e_1_3_2_1_75_1","unstructured":"Yaming Zhang and Ahmed Eldawy. [n. d.]. OpenStreetMap Points of Interest."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389726"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.14778\/3450980.3450990"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389717"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300065"}],"event":{"name":"SIGSPATIAL '25: 33rd ACM International Conference on Advances in Geographic Information Systems","location":"The Graduate Hotel Minneapolis Minneapolis MN USA","acronym":"SIGSPATIAL '25","sponsor":["SIGSPATIAL ACM Special Interest Group on Spatial Information"]},"container-title":["Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748636.3762714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T19:11:44Z","timestamp":1765566704000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748636.3762714"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":79,"alternative-id":["10.1145\/3748636.3762714","10.1145\/3748636"],"URL":"https:\/\/doi.org\/10.1145\/3748636.3762714","relation":{},"subject":[],"published":{"date-parts":[[2025,11,3]]},"assertion":[{"value":"2025-12-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}