{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:22:14Z","timestamp":1750306934813,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,6,24]],"date-time":"2013-06-24T00:00:00Z","timestamp":1372032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100004316","name":"International Business Machines Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004316","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000811","name":"European Institute of Innovation and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000811","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2013,6,24]]},"DOI":"10.1145\/2479440.2482677","type":"proceedings-article","created":{"date-parts":[[2013,6,25]],"date-time":"2013-06-25T19:13:21Z","timestamp":1372187601000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Issues in big data testing and benchmarking"],"prefix":"10.1145","author":[{"given":"Alexander","family":"Alexandrov","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Br\u00fccke","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Markl","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2013,6,24]]},"reference":[{"issue":"2","key":"e_1_3_2_1_1_1","first-page":"1625","article-title":"Massively Parallel Data Analysis with PACTs on Nephele","volume":"3","author":"Alexandrov A.","year":"2010","unstructured":"{ABE+10} A. Alexandrov , D. Battr\u00e9 , S. Ewen , M. Heimel , F. Hueske , O. Kao , V. Markl , E. Nijkamp , D. Warneke : Massively Parallel Data Analysis with PACTs on Nephele . PVLDB Vol. 3 , No. 2 , pp. 1625 -- 1628 ( 2010 ) {ABE+10} A. Alexandrov, D. Battr\u00e9, S. Ewen, M. Heimel, F. Hueske, O. Kao, V. Markl, E. Nijkamp, D. Warneke: Massively Parallel Data Analysis with PACTs on Nephele. PVLDB Vol. 3, No. 2, pp. 1625--1628 (2010)","journal-title":"PVLDB"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2331801.2331803"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989395"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2377978.2377983"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367530"},{"key":"e_1_3_2_1_6_1","first-page":"668","article-title":"BHUNT","volume":"2003","author":"Brown P.","unstructured":"{BH03} P. Brown , P. Haas : BHUNT : Automatic Discovery of Fuzzy Algebraic Constraints in Relational Data. VLDB 2003 : 668 -- 679 {BH03} P. Brown, P. Haas: BHUNT: Automatic Discovery of Fuzzy Algebraic Constraints in Relational Data. VLDB 2003: 668--679","journal-title":"VLDB"},{"volume-title":"Proc. of VLDB Conference. (2011)","author":"Beyer K. S.","key":"e_1_3_2_1_7_1","unstructured":"{BEG+11} K. S. Beyer , V. Ercegovac , R. Gemulla , A. Balmin , M. Eltabakh , C.-C. Kanne , E. J. Shekita : Jaql: A scripting language for large scale semistructured data analysis . In Proc. of VLDB Conference. (2011) {BEG+11} K. S. Beyer, V. Ercegovac, R. Gemulla, A. Balmin, M. Eltabakh, C.-C. Kanne, E. J. Shekita: Jaql: A scripting language for large scale semistructured data analysis. In Proc. of VLDB Conference. (2011)"},{"key":"e_1_3_2_1_8_1","first-page":"137","volume-title":"OSDI","author":"Dean J.","year":"2004","unstructured":"{DG04} J. Dean , S. Ghemawat : MapReduce: simplified data processing on large clusters , In OSDI , pp. 137 -- 150 ( 2004 ) {DG04} J. Dean, S. Ghemawat: MapReduce: simplified data processing on large clusters, In OSDI, pp. 137--150 (2004)"},{"issue":"1","key":"e_1_3_2_1_9_1","first-page":"28","article-title":"The SAP HANA Database -- An Architecture Overview","volume":"35","author":"F\u00e4rber F.","year":"2012","unstructured":"{FML+12} F. F\u00e4rber , N. May , W. Lehner , P. Gro\u00dfe , I. M\u00fcller , H. Rauhe , J. Dees : The SAP HANA Database -- An Architecture Overview . IEEE Data Eng. Bull. 35 ( 1 ): 28 -- 33 ( 2012 ) {FML+12} F. F\u00e4rber, N. May, W. Lehner, P. Gro\u00dfe, I. M\u00fcller, H. Rauhe, J. Dees: The SAP HANA Database -- An Architecture Overview. IEEE Data Eng. Bull. 35(1): 28--33 (2012)","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2188286.2188315"},{"key":"e_1_3_2_1_11_1","volume-title":"Achieving extreme performance with Oracle Exadata","author":"Greenwald R.","year":"2011","unstructured":"{GSA+11} R. Greenwald , R. Stackowiak , M. Alam , M. Bhuller .. Achieving extreme performance with Oracle Exadata . McGraw-Hill Osborne Media ( 2011 ) {GSA+11} R. Greenwald, R. Stackowiak, M. Alam, M. Bhuller.. Achieving extreme performance with Oracle Exadata. McGraw-Hill Osborne Media (2011)"},{"key":"e_1_3_2_1_12_1","unstructured":"{Had13} http:\/\/hadoop.apache.org\/ last accessed 05-10-2013 {Had13} http:\/\/hadoop.apache.org\/ last accessed 05-10-2013"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/sam.v1:4"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10424-4_3"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007641"},{"key":"e_1_3_2_1_16_1","unstructured":"{Imp13} https:\/\/github.com\/cloudera\/impala last accessed 05-10-2013 {Imp13} https:\/\/github.com\/cloudera\/impala last accessed 05-10-2013"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"key":"e_1_3_2_1_18_1","unstructured":"{Mah13} Mahout: http:\/\/mahout.apache.org\/ last accessed 04-21-2013 {Mah13} Mahout: http:\/\/mahout.apache.org\/ last accessed 04-21-2013"},{"key":"e_1_3_2_1_19_1","unstructured":"{Myr13} https:\/\/github.com\/TU-Berlin-DIMA\/myriad-toolkit\/wiki last accessed 05-10-2013 {Myr13} https:\/\/github.com\/TU-Berlin-DIMA\/myriad-toolkit\/wiki last accessed 05-10-2013"},{"key":"e_1_3_2_1_20_1","unstructured":"{Nau13} http:\/\/www.hpi.uni-potsdam.de\/naumann\/publications\/publications_by_type\/year\/2013\/2276\/Nau13.html SIGMOD Record (2013) {Nau13} http:\/\/www.hpi.uni-potsdam.de\/naumann\/publications\/publications_by_type\/year\/2013\/2276\/Nau13.html SIGMOD Record (2013)"},{"key":"e_1_3_2_1_21_1","unstructured":"{Oli13} https:\/\/github.com\/TU-Berlin-DIMA\/myriad-toolkit\/wiki\/Using-Oligos-Guide last accessed 05-10-2013 {Oli13} https:\/\/github.com\/TU-Berlin-DIMA\/myriad-toolkit\/wiki\/Using-Oligos-Guide last accessed 05-10-2013"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_3_2_1_23_1","unstructured":"{PDG13} http:\/\/www.paralleldatageneration.org\/drupal6\/ last accessed 05-10-2013 {PDG13} http:\/\/www.paralleldatageneration.org\/drupal6\/ last accessed 05-10-2013"},{"volume-title":"H. Kosch: A Data Generator for Cloud-Scale Benchmarking. TPCTC 2010:  41--56","author":"Rabl T.","key":"e_1_3_2_1_24_1","unstructured":"{RFS+10} T. Rabl , M. Frank , H. Sergieh , H. Kosch: A Data Generator for Cloud-Scale Benchmarking. TPCTC 2010: 41--56 {RFS+10} T. Rabl, M. Frank, H. Sergieh, H. Kosch: A Data Generator for Cloud-Scale Benchmarking. TPCTC 2010: 41--56"},{"key":"e_1_3_2_1_25_1","first-page":"691","article-title":"GORDIAN","volume":"2006","author":"Sismanis Y.","unstructured":"{SBH+06} Y. Sismanis , P. Brown , P. Haas , B. Reinwald : GORDIAN : Efficient and Scalable Discovery of Composite Keys. VLDB 2006 : 691 -- 702 {SBH+06} Y. Sismanis, P. Brown, P. Haas, B. Reinwald: GORDIAN: Efficient and Scalable Discovery of Composite Keys. VLDB 2006: 691--702","journal-title":"Efficient and Scalable Discovery of Composite Keys. VLDB"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2006.84"},{"key":"e_1_3_2_1_27_1","unstructured":"{Spa13} http:\/\/spark-project.org\/ last accessed 05-10-2013 {Spa13} http:\/\/spark-project.org\/ last accessed 05-10-2013"},{"key":"e_1_3_2_1_28_1","unstructured":"{Str13} http:\/\/www.stratosphere.eu\/ last accessed 05-10-2013 {Str13} http:\/\/www.stratosphere.eu\/ last accessed 05-10-2013"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393596.2393637"},{"key":"e_1_3_2_1_30_1","unstructured":"{TPC13} http:\/\/www.tpc.org last accessed 05-10-2013 {TPC13} http:\/\/www.tpc.org last accessed 05-10-2013"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687609"},{"key":"e_1_3_2_1_32_1","unstructured":"{XML13} http:\/\/www.xml-benchmark.org\/ last accessed 05-10-2013 {XML13} http:\/\/www.xml-benchmark.org\/ last accessed 05-10-2013"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"issue":"1","key":"e_1_3_2_1_34_1","first-page":"518","article-title":"Hadoop++: Making a Yellow Elephant Run Like a Cheetah (Without It Even Noticing)","volume":"3","author":"Dittrich J.","year":"2010","unstructured":"{DQJ+10} J. Dittrich , J. Quian\u00e9-Ruiz , A. Jindal , Y. Kargin , V. Setty , J. Schad : Hadoop++: Making a Yellow Elephant Run Like a Cheetah (Without It Even Noticing) . PVLDB 3 ( 1 ): 518 -- 529 ( 2010 ) {DQJ+10} J. Dittrich, J. Quian\u00e9-Ruiz, A. Jindal, Y. Kargin, V. Setty, J. Schad: Hadoop++: Making a Yellow Elephant Run Like a Cheetah (Without It Even Noticing). PVLDB 3(1): 518--529 (2010)","journal-title":"PVLDB"},{"issue":"1","key":"e_1_3_2_1_35_1","first-page":"472","article-title":"The Performance of MapReduce","volume":"3","author":"Jiang D.","year":"2010","unstructured":"{JOS+10} D. Jiang , B. C. Ooi , L. Shi , S. Wu : The Performance of MapReduce : An In-depth Study. PVLDB 3 ( 1 ): 472 -- 483 ( 2010 ) {JOS+10} D. Jiang, B. C. Ooi, L. Shi, S. Wu: The Performance of MapReduce: An In-depth Study. PVLDB 3(1):472--483 (2010)","journal-title":"An In-depth Study. PVLDB"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/11564126_17"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2009.14"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1921632.1921634"}],"event":{"name":"SIGMOD\/PODS'13: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"New York New York","acronym":"SIGMOD\/PODS'13"},"container-title":["Proceedings of the Sixth International Workshop on Testing Database Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2479440.2482677","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2479440.2482677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:35:42Z","timestamp":1750235742000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2479440.2482677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,24]]},"references-count":38,"alternative-id":["10.1145\/2479440.2482677","10.1145\/2479440"],"URL":"https:\/\/doi.org\/10.1145\/2479440.2482677","relation":{},"subject":[],"published":{"date-parts":[[2013,6,24]]},"assertion":[{"value":"2013-06-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}