{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T08:40:01Z","timestamp":1748767201386,"version":"3.41.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,1,30]],"date-time":"2016-01-30T00:00:00Z","timestamp":1454112000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s00778-016-0422-9","type":"journal-article","created":{"date-parts":[[2016,1,30]],"date-time":"2016-01-30T04:01:31Z","timestamp":1454126491000},"page":"399-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decorating the cloud: enabling annotation management in MapReduce"],"prefix":"10.1007","volume":"25","author":[{"given":"Yue","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuguan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed Y.","family":"Eltabakh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,1,30]]},"reference":[{"key":"422_CR1","doi-asserted-by":"crossref","unstructured":"Abouzeid, A., et al.: HadoopDB: an architectural hybrid of MapReduce and DBMS technologies for analytical workloads. In: VLDB, pp. 922\u2013933 (2009)","DOI":"10.14778\/1687627.1687731"},{"key":"422_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, R., Imran, A., Seay, C., Walker, J.: A layer based architecture for provenance in big data. In: Big Data, pp. 1\u20137 (2014)","DOI":"10.1109\/BigData.2014.7004468"},{"key":"422_CR3","unstructured":"Akoush, S., Carata, L., Sohan, R., Hopper, A.: MrLazy: Lazy runtime label propagation for MapReduce. In: HotCloud (2014)"},{"key":"422_CR4","unstructured":"Akoush, S., Sohan, R., Hopper, A.: HadoopProv: towards provenance as a first class citizen in MapReduce. In: USENIX Workshop on the Theory and Practice of Provenance (2013)"},{"key":"422_CR5","unstructured":"Amazon Elastic MapReduce. Developer Guide, API Version 2009-03-31 (2009)"},{"key":"422_CR6","doi-asserted-by":"crossref","unstructured":"Amsterdamer, Y., Davidson, S.B., Deutch, D., et al.: Putting lipstick on pig: enabling database-style workflow provenance. In: PVLDB, pp. 346\u2013357 (2011)","DOI":"10.14778\/2095686.2095693"},{"key":"422_CR7","doi-asserted-by":"crossref","unstructured":"Bhagwat, D., Chiticariu, L., Tan, W.: An annotation management system for relational databases. In: VLDB, pp. 900\u2013911 (2004)","DOI":"10.1016\/B978-012088469-8.50079-6"},{"issue":"1\u20132","key":"422_CR8","doi-asserted-by":"crossref","first-page":"285","DOI":"10.14778\/1920841.1920881","volume":"3","author":"Y Bu","year":"2010","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.D.: Haloop: efficient iterative data processing on large clusters. Proc. VLDB Endow. 3(1\u20132), 285\u2013296 (2010)","journal-title":"Proc. VLDB Endow."},{"key":"422_CR9","doi-asserted-by":"crossref","unstructured":"Buneman, P., Chapman, A., Cheney, J.: Provenance management in curated databases. In: SIGMOD, pp. 539\u2013550 (2006)","DOI":"10.1145\/1142473.1142534"},{"key":"422_CR10","doi-asserted-by":"crossref","unstructured":"Buneman, P., Cheney, J., Tan, W.-C., Vansummeren, S.: Curated databases. In: Proceedings of the 27th ACM Symposium on Principles of Database Systems (PODS), pp. 1\u201312 (2008)","DOI":"10.1145\/1376916.1376918"},{"key":"422_CR11","doi-asserted-by":"crossref","unstructured":"Buneman, P., et al.: On propagation of deletions and annotations through views. In: PODS, pp. 150\u2013158 (2002)","DOI":"10.1145\/543613.543633"},{"key":"422_CR12","doi-asserted-by":"crossref","unstructured":"Buneman, P., Khanna, S., Tan, W.: Why and where: a characterization of data provenance. Lecture Notes in Computer Science, vol. 1973, pp. 316\u2013333 (2001)","DOI":"10.1007\/3-540-44503-X_20"},{"key":"422_CR13","doi-asserted-by":"crossref","unstructured":"Buneman, P., Kostylev, E.V., Vansummeren, S.: Annotations are relative. In: Proceedings of the 16th International Conference on Database Theory, ICDT \u201913, pp. 177\u2013188 (2013)","DOI":"10.1145\/2448496.2448518"},{"key":"422_CR14","doi-asserted-by":"crossref","unstructured":"Buyya, R.: Market-oriented cloud computing: vision, hype, and reality of delivering computing as the 5th utility. In: Proceedings of the 2009 9th IEEE\/ACM International Symposium on Cluster Computing and the Grid, pp. 1\u201315 (2009)","DOI":"10.1109\/CCGRID.2009.97"},{"key":"422_CR15","doi-asserted-by":"crossref","unstructured":"Crawl, D., Wang, J., Altintas, I.: Provenance for MapReduce-based data-intensive workflows. In: WORKS Workshop, pp. 21\u201330 (2011)","DOI":"10.1145\/2110497.2110501"},{"key":"422_CR16","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: OSDI, pp. 137\u2013150 (2004)"},{"key":"422_CR17","doi-asserted-by":"crossref","unstructured":"Dias, J., Ogasawara, et al. E.: Algebraic dataflows for big data analysis. In: International Conference on Big Data, pp. 150\u2013155 (2013)","DOI":"10.1109\/BigData.2013.6691567"},{"issue":"11","key":"422_CR18","first-page":"1591","volume":"5","author":"J Dittrich","year":"2012","unstructured":"Dittrich, J., Quian\u00e9-Ruiz, J.-A., Richter, S., Schuh, S., Jindal, A., Schad, J.: Only aggressive elephants are fast elephants. PVLDB 5(11), 1591\u20131602 (2012)","journal-title":"PVLDB"},{"key":"422_CR19","doi-asserted-by":"crossref","unstructured":"Eltabakh, M.Y., Aref, W.G., Elmagarmid, A.K., Ouzzani, M., Silva, Y.N.: Supporting annotations on relations. In: EDBT, pp. 379\u2013390 (2009)","DOI":"10.1145\/1516360.1516405"},{"key":"422_CR20","doi-asserted-by":"crossref","unstructured":"Eltabakh, M.Y., \u00d6zcan, F., Sismanis, Y., Haas, P., Pirahesh, H., Vondrak, J.: Eagle-eyed elephant: split-oriented indexing in hadoop. In: EDBT, pp. 89\u2013100 (2013)","DOI":"10.1145\/2452376.2452388"},{"issue":"9","key":"422_CR21","first-page":"575","volume":"4","author":"MY Eltabakh","year":"2011","unstructured":"Eltabakh, M.Y., Tian, Y., \u00d6zcan, F., Gemulla, R., Krettek, A., McPherson, J.: Cohadoop: flexible data placement and its exploitation in hadoop. PVLDB 4(9), 575\u2013585 (2011)","journal-title":"PVLDB"},{"issue":"1","key":"422_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.14778\/1687627.1687629","volume":"2","author":"W Gatterbauer","year":"2009","unstructured":"Gatterbauer, W., Balazinska, M., Khoussainova, N., Suciu, D.: Believe it or not: adding belief annotations to databases. Proc. VLDB Endow. 2(1), 1\u201312 (2009)","journal-title":"Proc. VLDB Endow."},{"key":"422_CR23","doi-asserted-by":"crossref","unstructured":"Geerts, F., et al.: Mondrian: annotating and querying databases through colors and blocks. In: ICDE, p. 82 (2006)","DOI":"10.1109\/ICDE.2006.102"},{"key":"422_CR24","doi-asserted-by":"crossref","unstructured":"Geerts, F., Van Den Bussche, J.: Relational completeness of query languages for annotated databases. In: DBPL, pp. 127\u2013137 (2007)","DOI":"10.1007\/978-3-540-75987-4_9"},{"key":"422_CR25","doi-asserted-by":"crossref","unstructured":"Gunarathne, T., Wu, T.-L., Qiu, J., Fox, G.: MapReduce in the clouds for science. In: CloudCom Conference, pp. 565\u2013572 (2010)","DOI":"10.1109\/CloudCom.2010.107"},{"key":"422_CR26","unstructured":"Hive. http:\/\/hadoop.apache.org\/hive"},{"key":"422_CR27","unstructured":"IBM InfoSphere BigInsights. http:\/\/www-01.ibm.com\/software\/data\/infosphere\/biginsights"},{"issue":"3","key":"422_CR28","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/2380776.2380778","volume":"41","author":"G Karvounarakis","year":"2012","unstructured":"Karvounarakis, G., Green, T.J.: Semiring-annotated data: queries and provenance. SIGMOD Rec. 41(3), 5\u201314 (2012)","journal-title":"SIGMOD Rec."},{"key":"422_CR29","doi-asserted-by":"crossref","unstructured":"Lang, W., Nehme, R.V., Robinson, E., Naughton, J.F.: Partial results in database systems. In: SIGMOD, pp. 1275\u20131286 (2014)","DOI":"10.1145\/2588555.2612176"},{"key":"422_CR30","doi-asserted-by":"crossref","unstructured":"Li, B., Mazur, E., Diao, Y., McGregor, A., Shenoy, P.: A platform for scalable one-pass analytics using mapreduce. In: SIGMOD, pp. 985\u2013996 (2011)","DOI":"10.1145\/1989323.1989426"},{"issue":"11","key":"422_CR31","first-page":"1196","volume":"5","author":"H Lim","year":"2012","unstructured":"Lim, H., Herodotou, H., Babu, S.: Stubby: a transformation-based optimizer for MapReduce workflows. PVLDB 5(11), 1196\u20131207 (2012)","journal-title":"PVLDB"},{"key":"422_CR32","doi-asserted-by":"crossref","unstructured":"Logothetis, D., De, S., Yocum, K.: Scalable lineage capture for debugging DISC analytics. In: SOCC, pp. 17:1\u201317:15 (2013)","DOI":"10.1145\/2523616.2523619"},{"key":"422_CR33","unstructured":"Logothetis, D., Trezzo, C., Webb, K.C.: In-situ mapreduce for log processing. In: USENIXATC, pp. 9\u20139 (2011)"},{"key":"422_CR34","unstructured":"Milieu: Lightweight and Configurable Big Data Provenance for Science, Santa Clara, CA. IEEE (2013)"},{"key":"422_CR35","doi-asserted-by":"crossref","first-page":"494","DOI":"10.14778\/1920841.1920906","volume":"3","author":"T Nykiel","year":"2010","unstructured":"Nykiel, T., Potamias, M., Mishra, C., Kollios, G., Koudas, N.: Mrshare: sharing across multiple queries in mapreduce. Proc. VLDB Endow. 3, 494\u2013505 (2010)","journal-title":"Proc. VLDB Endow."},{"key":"422_CR36","doi-asserted-by":"crossref","unstructured":"Olston, C., et al.: Nova: continuous pig\/hadoop workflows. In: SIGMOD Conference, pp. 1081\u20131090 (2011)","DOI":"10.1145\/1989323.1989439"},{"key":"422_CR37","unstructured":"Park, H., Ikeda, R., Widom, J.: Ramp: a system for capturing and tracing provenance in mapreduce workflows. In: VLDB. Stanford InfoLab (August, 2011)"},{"key":"422_CR38","unstructured":"Pig. http:\/\/hadoop.apache.org\/pig"},{"key":"422_CR39","unstructured":"Russell, J.: Couldera-Impala. O\u2019Reilly Media (2013)"},{"key":"422_CR40","unstructured":"Spark: Lightning-fast cluster computing. https:\/\/spark.apache.org"},{"key":"422_CR41","doi-asserted-by":"crossref","unstructured":"Tan, W.-C.: Containment of relational queries with annotation propagation. In: DBPL (2003)","DOI":"10.1007\/978-3-540-24607-7_4"},{"key":"422_CR42","unstructured":"The Apache Foundation. Hadoop. http:\/\/hadoop.apache.org"},{"key":"422_CR43","unstructured":"The Apache Foundation. Hbase. http:\/\/hbase.apache.org\/"},{"key":"422_CR44","unstructured":"The Apache Software Foundation. HDFS architecture guide. http:\/\/hadoop.apache.org\/hdfs\/docs\/current\/hdfs-design.html"},{"key":"422_CR45","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Murthy, R., Sarma, J.S., Shao, Z., Jain, N., Chakka, P., Anthony, S., Liu, H., Zhang, N.: Hive\u2014a petabyte scale data warehousing using hadoop. In: ICDE (2010)","DOI":"10.1109\/ICDE.2010.5447738"},{"key":"422_CR46","unstructured":"Traverso, M.: Presto: Interacting with petabytes of data at Facebook (2013)"},{"key":"422_CR47","doi-asserted-by":"crossref","unstructured":"Ullman, J.: Principles of database and knowledge-base systems, vol. 1 (1988)","DOI":"10.1145\/28659.28660"},{"key":"422_CR48","volume-title":"Hadoop: The Definitive Guide","author":"T White","year":"2012","unstructured":"White, T.: Hadoop: The Definitive Guide, 3rd edn. O\u2019Reilly Media Inc, Sebastopol (2012)","edition":"3"},{"key":"422_CR49","doi-asserted-by":"crossref","unstructured":"Wu, E., Madden, S., Stonebraker, M.: SubZero: a fine-grained lineage system for scientific databases. In: ICDE, pp. 865\u2013876 (2013)","DOI":"10.1109\/ICDE.2013.6544881"},{"key":"422_CR50","doi-asserted-by":"crossref","unstructured":"Xiao, D., Eltabakh, M.Y.: InsightNotes: summary-based annotation management in relational databases. In: SIGMOD Conference, pp. 661\u2013672 (2014)","DOI":"10.1145\/2588555.2610501"},{"key":"422_CR51","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster Computing with Working Sets. In: 2nd USENIX Workshop on Hot Topics in Cloud Computing, HotCloud\u201910, Boston, MA, USA, June 22, 2010 (2010)"},{"key":"422_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, C., Naughton, J., Dewitt, D., Luo, Q.: On supporting containment queries in relational database management systems. In: In SIGMOD, pp. 425\u2013436 (2001)","DOI":"10.1145\/375663.375722"},{"key":"422_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, C., Sterck, H.D., Aboulnaga, A., Djambazian, H., Sladek, R.: Case Study of Scientific Data Processing on a Cloud Using Hadoop. In: HPCS, pp. 400\u2013415 (2009)","DOI":"10.1007\/978-3-642-12659-8_29"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-016-0422-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-016-0422-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-016-0422-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T08:07:42Z","timestamp":1748765262000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-016-0422-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1,30]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["422"],"URL":"https:\/\/doi.org\/10.1007\/s00778-016-0422-9","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"type":"print","value":"1066-8888"},{"type":"electronic","value":"0949-877X"}],"subject":[],"published":{"date-parts":[[2016,1,30]]}}}