{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:11:51Z","timestamp":1765231911527},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2011,3,31]],"date-time":"2011-03-31T00:00:00Z","timestamp":1301529600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Distrib Parallel Databases"],"published-print":{"date-parts":[[2011,6]]},"DOI":"10.1007\/s10619-011-7082-y","type":"journal-article","created":{"date-parts":[[2011,3,30]],"date-time":"2011-03-30T14:55:33Z","timestamp":1301496933000},"page":"185-216","source":"Crossref","is-referenced-by-count":76,"title":["ASTERIX: towards a scalable, semistructured data platform for evolving-world models"],"prefix":"10.1007","volume":"29","author":[{"given":"Alexander","family":"Behm","sequence":"first","affiliation":[]},{"given":"Vinayak R.","family":"Borkar","sequence":"additional","affiliation":[]},{"given":"Michael J.","family":"Carey","sequence":"additional","affiliation":[]},{"given":"Raman","family":"Grover","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Onose","sequence":"additional","affiliation":[]},{"given":"Rares","family":"Vernica","sequence":"additional","affiliation":[]},{"given":"Alin","family":"Deutsch","sequence":"additional","affiliation":[]},{"given":"Yannis","family":"Papakonstantinou","sequence":"additional","affiliation":[]},{"given":"Vassilis J.","family":"Tsotras","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,3,31]]},"reference":[{"key":"7082_CR1","volume-title":"Data on the Web: From Relations to Semistructured Data and XML","author":"S. Abiteboul","year":"1999","unstructured":"Abiteboul, S., Buneman, P., Suciu, D.: Data on the Web: From Relations to Semistructured Data and XML. Morgan Kaufmann, San Mateo (1999)"},{"key":"7082_CR2","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-51171-7","volume-title":"Nested Relations and Complex Objects in Databases (LNCS)","author":"S. Abiteboul","year":"1989","unstructured":"Abiteboul, S., Fischer, P.C., Schek, H.-J.: Nested Relations and Complex Objects in Databases (LNCS). Springer, Berlin (1989)"},{"key":"7082_CR3","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1109\/ICDE.2008.4497469","volume-title":"ICDE \u201908: Proceedings of the 2008 IEEE 24th International Conference on Data Engineering","author":"S. Abiteboul","year":"2008","unstructured":"Abiteboul, S., Manolescu, I., Polyzotis, N., Preda, N., Sun, C.: Xml processing in dht networks. In: ICDE \u201908: Proceedings of the 2008 IEEE 24th International Conference on Data Engineering, pp.\u00a0606\u2013615. IEEE Computer Society, Washington (2008)"},{"issue":"6","key":"7082_CR4","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/1516046.1516062","volume":"52","author":"R. Agrawal","year":"2009","unstructured":"Agrawal, R., et al.: The Claremont report on database research. Commun. ACM 52(6), 56\u201365 (2009)","journal-title":"Commun. ACM"},{"key":"7082_CR5","unstructured":"Amer-Yahia, S., Botev, C., Buxton, S., Case, P., Doerre, J., Dyck, M., Holstege, M., Melton, J., Rys, M., Shanmugasundaram, J.: XQuery and XPath full text 1.0. W3C Candidate Recommendation, July 9 (2009)"},{"key":"7082_CR6","unstructured":"Apache Avro, http:\/\/hadoop.apache.org\/avro\/"},{"key":"7082_CR7","unstructured":"Apache Hadoop, http:\/\/hadoop.apache.org"},{"key":"7082_CR8","unstructured":"Ballinger, C.: Born to be parallel. Why parallel origins give teradata. Database an enduring performance edge. http:\/\/www.teradata.com\/library\/pdf\/eb3053.pdf"},{"key":"7082_CR9","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1145\/1807128.1807148","volume-title":"SoCC \u201910: Proceedings of the 1st ACM Symposium on Cloud Computing","author":"D. Battr\u00e9","year":"2010","unstructured":"Battr\u00e9, D., Ewen, S., Hueske, F., Kao, O., Markl, V., Warneke, D.: Nephele\/pacts: a programming model and execution framework for web-scale analytical processing. In: SoCC \u201910: Proceedings of the 1st ACM Symposium on Cloud Computing, pp. 119\u2013130. ACM, New York (2010)"},{"key":"7082_CR10","volume-title":"ICDE","author":"A. Behm","year":"2009","unstructured":"Behm, A., Ji, S., Li, C., Lu, J.: Space-constrained gram-based indexing for efficient approximate string search. In: ICDE (2009)"},{"key":"7082_CR11","doi-asserted-by":"crossref","unstructured":"Behm, A., Li, C., Carey, M.: Answering approximate string queries on large data sets using external memory. Technical report, Department of Computer Science, UC Irvine (under submission) (July 2010)","DOI":"10.1109\/ICDE.2011.5767856"},{"key":"7082_CR12","volume-title":"ICDE","author":"V. Borkar","year":"2011","unstructured":"Borkar, V., Carey, M., Grover, R., Onose, N., Vernica, R.: Hyracks: a flexible and extensible foundation for data-intensive computing. In: ICDE (2011)"},{"key":"7082_CR13","first-page":"349","volume-title":"EDBT","author":"C. Botev","year":"2006","unstructured":"Botev, C., Amer-Yahia, S., Shanmugasundaram, J.: Expressiveness and performance of full-text search languages. In: EDBT, pp. 349\u2013367 (2006)"},{"issue":"4","key":"7082_CR14","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1145\/6513.6517","volume":"4","author":"M.J. Carey","year":"1986","unstructured":"Carey, M.J., Muhanna, W.A.: The performance of multiversion concurrency control algorithms. ACM Trans. Comput. Syst. 4(4), 338\u2013378 (1986)","journal-title":"ACM Trans. Comput. Syst."},{"issue":"2","key":"7082_CR15","first-page":"1265","volume":"1","author":"R. Chaiken","year":"2008","unstructured":"Chaiken, R., Jenkins, B., Larson, P.-\u00c5., Ramsey, B., Shakib, D., Weaver, S., Zhou, J.: SCOPE: easy and efficient parallel processing of massive data sets. PVLDB 1(2), 1265\u20131276 (2008)","journal-title":"PVLDB"},{"key":"7082_CR16","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1145\/1806596.1806638","volume-title":"PLDI","author":"C. Chambers","year":"2010","unstructured":"Chambers, C., Raniwala, A., Perry, F., Adams, S., Henry, R.R., Bradshaw, R., Weizenbaum, N.: Flumejava: easy, efficient data-parallel pipelines. In: PLDI, pp. 363\u2013375 (2010)"},{"key":"7082_CR17","doi-asserted-by":"crossref","unstructured":"Chang, F., Dean, J., Ghemawat, S., Hsieh, W.C., Wallach, D.A., Burrows, M., Chandra, T., Fikes, A., Gruber, R.E.: Bigtable: a distributed storage system for structured data. ACM Trans. Comput. Syst. 26(2) (2008)","DOI":"10.1145\/1365815.1365816"},{"issue":"2","key":"7082_CR18","first-page":"1277","volume":"1","author":"B.F. Cooper","year":"2008","unstructured":"Cooper, B.F., Ramakrishnan, R., Srivastava, U., Silberstein, A., Bohannon, P., Jacobsen, H.-A., Puz, N., Weaver, D., Yerneni, R.: Pnuts: Yahoo!\u2019s hosted data serving platform. PVLDB 1(2), 1277\u20131288 (2008)","journal-title":"PVLDB"},{"issue":"1","key":"7082_CR19","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1145\/44203.44208","volume":"17","author":"U. Dayal","year":"1988","unstructured":"Dayal, U., Blaustein, B., Buchmann, A., Chakravarthy, U., Hsu, M., Ledin, R., McCarthy, D., Rosenthal, A., Sarin, S., Carey, M.J., Livny, M., Jauhari, R.: The HiPAC project: combining active databases and timing constraints. SIGMOD Rec. 17(1), 51\u201370 (1988)","journal-title":"SIGMOD Rec."},{"key":"7082_CR20","first-page":"137","volume-title":"OSDI","author":"J. Dean","year":"2004","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. In: OSDI, pp. 137\u2013150 (2004)"},{"issue":"1","key":"7082_CR21","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J. Dean","year":"2010","unstructured":"Dean, J., Ghemawat, S.: MapReduce: a flexible data processing tool. Commun. ACM 53(1), 72\u201377 (2010)","journal-title":"Commun. ACM"},{"key":"7082_CR22","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1145\/1294261.1294281","volume-title":"SOSP","author":"G. DeCandia","year":"2007","unstructured":"DeCandia, G., Hastorun, D., Jampani, M., Kakulapati, G., Lakshman, A., Pilchin, A., Sivasubramanian, S., Vosshall, P., Vogels, W.: Dynamo: Amazon\u2019s highly available key-value store. In: SOSP, pp.\u00a0205\u2013220 (2007)"},{"issue":"1","key":"7082_CR23","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/69.50905","volume":"2","author":"D.J. DeWitt","year":"1990","unstructured":"DeWitt, D.J., Ghandeharizadeh, S., Schneider, D.A., Bricker, A., Hsiao, H.-I., Rasmussen, R.: The Gamma database machine project. IEEE Trans. Knowl. Data Eng. 2(1), 44\u201362 (1990)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"6","key":"7082_CR24","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1145\/129888.129894","volume":"35","author":"D.J. DeWitt","year":"1992","unstructured":"DeWitt, D.J., Gray, J.: Parallel database systems: the future of high performance database systems. Commun. ACM 35(6), 85\u201398 (1992)","journal-title":"Commun. ACM"},{"issue":"4","key":"7082_CR25","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1145\/958942.958947","volume":"28","author":"Y. Diao","year":"2003","unstructured":"Diao, Y., Altinel, M., Franklin, M.J., Zhang, H., Fischer, P.M.: Path sharing and predicate evaluation for high-performance xml filtering. ACM Trans. Database Syst. 28(4), 467\u2013516 (2003)","journal-title":"ACM Trans. Database Syst."},{"key":"7082_CR26","unstructured":"Facebook press room\u2014statistics. http:\/\/www.facebook.com\/press\/info.php?statistics"},{"key":"7082_CR27","unstructured":"Facebook Thrift. http:\/\/incubator.apache.org\/thrift"},{"key":"7082_CR28","first-page":"296","volume-title":"VLDB","author":"M.N. Garofalakis","year":"1997","unstructured":"Garofalakis, M.N., Ioannidis, Y.E.: Parallel query scheduling and optimization with time- and space-shared resources. In: VLDB, pp. 296\u2013305 (1997)"},{"key":"7082_CR29","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1145\/945445.945450","volume-title":"SOSP","author":"S. Ghemawat","year":"2003","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.-T.: The Google file system. In: SOSP, pp. 29\u201343 (2003)"},{"key":"7082_CR30","first-page":"436","volume-title":"VLDB","author":"R. Goldman","year":"1997","unstructured":"Goldman, R., Widom, J.: Dataguides: enabling query formulation and optimization in semistructured databases. In: VLDB, pp. 436\u2013445 (1997)"},{"key":"7082_CR31","unstructured":"Google protocol buffers. http:\/\/code.google.com\/apis\/protocolbuffers\/"},{"issue":"2","key":"7082_CR32","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1145\/152610.152611","volume":"25","author":"G. Graefe","year":"1993","unstructured":"Graefe, G.: Query evaluation techniques for large databases. ACM Comput. Surv. 25(2), 73\u2013170 (1993)","journal-title":"ACM Comput. Surv."},{"key":"7082_CR33","first-page":"266","volume-title":"ICDE","author":"E.N. Hanson","year":"1999","unstructured":"Hanson, E.N., Carnes, C., Huang, L., Konyala, M., Noronha, L., Parthasarathy, S., Park, J.B., Vernon, A.: Scalable trigger processing. In: ICDE, pp. 266\u2013275 (1999)"},{"key":"7082_CR34","first-page":"132","volume-title":"CIDR","author":"P. Helland","year":"2007","unstructured":"Helland, P.: Life beyond distributed transactions: an apostate\u2019s opinion. In: CIDR, pp. 132\u2013141 (2007)"},{"key":"7082_CR35","first-page":"218","volume-title":"PDIS","author":"W. Hong","year":"1991","unstructured":"Hong, W., Stonebraker, M.: Optimization of parallel query execution plans in XPRS. In: PDIS, pp.\u00a0218\u2013225 (1991)"},{"key":"7082_CR36","unstructured":"Hyracks project on Google code. http:\/\/code.google.com\/p\/hyracks"},{"key":"7082_CR37","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1145\/1272996.1273005","volume-title":"EuroSys","author":"M. Isard","year":"2007","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. In: EuroSys, pp. 59\u201372 (2007)"},{"key":"7082_CR38","unstructured":"Jaql, http:\/\/www.jaql.org"},{"key":"7082_CR39","unstructured":"Jaql 0.1. http:\/\/www.jaql.org\/release\/0.1\/jaql-overview.html"},{"key":"7082_CR40","unstructured":"JSON. http:\/\/www.json.org\/"},{"key":"7082_CR41","volume-title":"ICDE","author":"C. Li","year":"2008","unstructured":"Li, C., Lu, J., Lu, Y.: Efficient merging and filtering algorithms for approximate string searches. In: ICDE (2008)"},{"key":"7082_CR42","unstructured":"MarketWatch, The Wall Street Journal. Will the news survive? http:\/\/www.marketwatch.com\/story\/will-the-news-survive-2009-12-08"},{"issue":"1","key":"7082_CR43","first-page":"330","volume":"3","author":"S. Melnik","year":"2010","unstructured":"Melnik, S., Gubarev, A., Long, J.J., Romer, G., Shivakumar, S., Tolton, M., Vassilakis, T.: Dremel: interactive analysis of web-scale datasets. PVLDB 3(1), 330\u2013339 (2010)","journal-title":"PVLDB"},{"key":"7082_CR44","unstructured":"Moerkotte, G.: Building query compilers. Manuscript, 2009"},{"key":"7082_CR45","unstructured":"Object database management systems. http:\/\/www.odbms.org\/odmg\/"},{"key":"7082_CR46","first-page":"1099","volume-title":"SIGMOD Conference","author":"C. Olston","year":"2008","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig Latin: a not-so-foreign language for data processing. In: SIGMOD Conference, pp. 1099\u20131110 (2008)"},{"key":"7082_CR47","unstructured":"Pew Internet & American Life Project. Twitter and status updating, Fall 2009. http:\/\/www.pewinternet.org\/Reports\/2009\/17-Twitter-and-Status-Updating-Fall-2009.aspx"},{"issue":"4","key":"7082_CR48","first-page":"277","volume":"13","author":"R. Pike","year":"2005","unstructured":"Pike, R., Dorward, S., Griesemer, R., Quinlan, S.: Interpreting the data: parallel analysis with Sawzall. Sci. Program. 13(4), 277\u2013298 (2005)","journal-title":"Sci. Program."},{"key":"7082_CR49","first-page":"549","volume-title":"SIGMOD Conference","author":"D. Quass","year":"1996","unstructured":"Quass, D., Widom, J., Goldman, R., Haas, K., Luo, Q., McHugh, J., Nestorov, S., Rajaraman, A., Rivero, H., Abiteboul, S., Ullman, J.D., Wiener, J.L.: Lore: a lightweight object repository for semistructured data. In: SIGMOD Conference, p. 549 (1996)"},{"key":"7082_CR50","volume-title":"Database Management Systems","author":"R. Ramakrishnan","year":"2002","unstructured":"Ramakrishnan, R., Gehrke, J.: Database Management Systems. WCB\/McGraw-Hill, Boston (2002)"},{"key":"7082_CR51","first-page":"236","volume-title":"SIGMOD Conference","author":"R.T. Snodgrass","year":"1985","unstructured":"Snodgrass, R.T., Ahn, I.: A taxonomy of time in databases. In: SIGMOD Conference, pp. 236\u2013246 (1985)"},{"issue":"1","key":"7082_CR52","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/1629175.1629197","volume":"53","author":"M. Stonebraker","year":"2010","unstructured":"Stonebraker, M., et al.: MapReduce and parallel DBMSs: friends or foes? Commun. ACM 53(1), 64\u201371 (2010)","journal-title":"Commun. ACM"},{"key":"7082_CR53","unstructured":"The Radicati Group Inc. Business user survey, 2009. http:\/\/www.radicati.com\/wp\/wp-content\/uploads\/2009\/11\/Business-User-Survey-2009-Executive-Summary1.pdf"},{"key":"7082_CR54","unstructured":"Thusoo, A.: Hive\u2014a petabyte scale data warehouse using Hadoop. http:\/\/www.facebook.com\/note.php?note_id=89508453919"},{"key":"7082_CR55","unstructured":"Twitter blog. Measuring tweets, Feb. 2010. http:\/\/blog.twitter.com\/2010\/02\/measuring-tweets.html"},{"key":"7082_CR56","unstructured":"U.S. Department of Commerce, Washington: Quarterly retail e-commerce sales, 4th quarter 2008. http:\/\/www2.census.gov\/retail\/releases\/historical\/ecomm\/08Q4.html"},{"key":"7082_CR57","volume-title":"SIGMOD Conference","author":"R. Vernica","year":"2010","unstructured":"Vernica, R., Carey, M., Li, C.: Efficient parallel set-similarity joins using MapReduce. In: SIGMOD Conference (2010)"},{"key":"7082_CR58","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1145\/1557670.1557677","volume-title":"KEYS","author":"R. Vernica","year":"2009","unstructured":"Vernica, R., Li, C.: Efficient top-k algorithms for fuzzy search in string collections. In: KEYS, pp.\u00a09\u201314 (2009)"},{"key":"7082_CR59","first-page":"155","volume-title":"Proceedings of the 1976 ACM SIGMOD International Conference on Management of Data, Washington, DC, June 2\u20134, 1976","author":"E. Wong","year":"1976","unstructured":"Wong, E., Youssefi, K.: Decomposition\u2014a strategy for query processing (abstract). In: Author, J.B.R. Jr. (ed.) Proceedings of the 1976 ACM SIGMOD International Conference on Management of Data, Washington, DC, June 2\u20134, 1976, p. 155. ACM, New York (1976)"},{"key":"7082_CR60","volume-title":"VLDB","author":"C. Xiao","year":"2008","unstructured":"Xiao, C., Wang, W., Lin, X.: Ed-join: an efficient algorithm for similarity joins with edit distance constraints. In: VLDB (2008)"},{"key":"7082_CR61","unstructured":"XQuery 1.0: An XML query language. http:\/\/www.w3.org\/TR\/xquery\/"},{"key":"7082_CR62","first-page":"1","volume-title":"OSDI","author":"Y. Yu","year":"2008","unstructured":"Yu, Y., Isard, M., Fetterly, D., Budiu, M., Erlingsson, \u00da., Gunda, P.K., Currey, J.: DryadLINQ: a\u00a0system for general-purpose distributed data-parallel computing using a high-level language. In: OSDI, pp.\u00a01\u201314 (2008)"}],"container-title":["Distributed and Parallel Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10619-011-7082-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10619-011-7082-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10619-011-7082-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T15:35:45Z","timestamp":1712331345000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10619-011-7082-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,3,31]]},"references-count":62,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2011,6]]}},"alternative-id":["7082"],"URL":"https:\/\/doi.org\/10.1007\/s10619-011-7082-y","relation":{},"ISSN":["0926-8782","1573-7578"],"issn-type":[{"value":"0926-8782","type":"print"},{"value":"1573-7578","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,3,31]]}}}