{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:26:35Z","timestamp":1780442795478,"version":"3.54.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,4,18]],"date-time":"2020-04-18T00:00:00Z","timestamp":1587168000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,4,18]],"date-time":"2020-04-18T00:00:00Z","timestamp":1587168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["TIN2016-79269-R"],"award-info":[{"award-number":["TIN2016-79269-R"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Inf Syst Front"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s10796-020-10001-y","type":"journal-article","created":{"date-parts":[[2020,4,18]],"date-time":"2020-04-18T18:02:25Z","timestamp":1587232945000},"page":"9-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Quarry: A User-centered Big Data Integration Platform"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4635-6646","authenticated-orcid":false,"given":"Petar","family":"Jovanovic","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergi","family":"Nadal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oscar","family":"Romero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Abell\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Besim","family":"Bilalli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,4,18]]},"reference":[{"issue":"5","key":"10001_CR1","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1145\/2670528","volume":"58","author":"S Abiteboul","year":"2015","unstructured":"Abiteboul, S., Andr\u00e9, B., & Kaplan, D. (2015). Managing your digital life. Communications of the ACM, 58(5), 32\u201335.","journal-title":"Communications of the ACM"},{"issue":"1","key":"10001_CR2","doi-asserted-by":"crossref","first-page":"1:1\u20131:39","DOI":"10.1145\/1322432.1322433","volume":"40","author":"R Angles","year":"2008","unstructured":"Angles, R., & Guti\u00e9rrez, C. (2008). Survey of graph database models. ACM Computing Surveys, 40(1), 1:1\u20131:39.","journal-title":"ACM Computing Surveys"},{"issue":"5","key":"10001_CR3","doi-asserted-by":"crossref","first-page":"68:1\u201368:40","DOI":"10.1145\/3104031","volume":"50","author":"R Angles","year":"2017","unstructured":"Angles, R., Arenas, M., Barcel\u00f3, P., Hogan, A., Reutter, J. L., & Vrgoc, D. (2017). Foundations of modern query languages for graph databases. ACM Computing Surveys, 50(5), 68:1\u201368:40.","journal-title":"ACM Computing Surveys"},{"key":"10001_CR4","unstructured":"Bean, R. (2016). Variety, not volume, is driving big data initiatives. URL https:\/\/sloanreview.mit.edu\/article\/variety-not-volume-is-driving-big-data-initiatives"},{"key":"10001_CR5","first-page":"57","volume-title":"CAiSE Forum","author":"B Bilalli","year":"2018","unstructured":"Bilalli, B., Abell\u00f3, A., Aluja-Banet, T., Munir, R. F., & Wrembel, R. (2018a). PRESISTANT: data pre-processing assistant. In CAiSE Forum (pp. 57\u201365)."},{"key":"10001_CR6","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.csi.2017.05.004","volume":"57","author":"B Bilalli","year":"2018","unstructured":"Bilalli, B., Abell\u00f3, A., Aluja-Banet, T., & Wrembel, R. (2018b). Intelligent assistance for data pre-processing. Computer Standards & Interfaces, 57, 101\u2013109.","journal-title":"Computer Standards & Interfaces"},{"key":"10001_CR7","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.datak.2019.101727","volume":"123","author":"B Bilalli","year":"2019","unstructured":"Bilalli, B., Abell\u00f3, A., Aluja-Banet, T., & Wrembel, R. (2019). PRESISTANT: Learning based assistant for data pre-processing. Data & Knowledge Engineering, 123, 100\u2013122.","journal-title":"Data & Knowledge Engineering"},{"issue":"3","key":"10001_CR8","doi-asserted-by":"crossref","first-page":"471","DOI":"10.3233\/SW-160217","volume":"8","author":"D Calvanese","year":"2017","unstructured":"Calvanese, D., Cogrel, B., Komla-Ebri, S., Kontchakov, R., Lanti, D., Rezk, M., Rodriguez-Muro, M., & Xiao, G. (2017). Ontop: Answering SPARQL queries over relational databases. Semantic Web, 8(3), 471\u2013487.","journal-title":"Semantic Web"},{"issue":"2","key":"10001_CR9","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/s13740-018-0086-2","volume":"7","author":"P Ceravolo","year":"2018","unstructured":"Ceravolo, P., Azzini, A., Angelini, M., Catarci, T., Cudr\u00e9-Mauroux, P., Damiani, E., Mazak, A., van Keulen, M., Jarrar, M., Santucci, G., Sattler, K., Scannapieco, M., Wimmer, M., Wrembel, R., & Zaraket, F. A. (2018). Big data semantics. J. Data Semantics, 7(2), 65\u201385.","journal-title":"J. Data Semantics"},{"issue":"12","key":"10001_CR10","first-page":"1802","volume":"5","author":"Y Chen","year":"2012","unstructured":"Chen, Y., Alspaugh, S., & Katz, R. H. (2012). Interactive analytical processing in big data systems: A cross-industry study of mapreduce workloads. PVLDB, 5(12), 1802\u20131813.","journal-title":"PVLDB"},{"key":"10001_CR11","first-page":"541","volume-title":"SIGMOD","author":"M Dallachiesa","year":"2013","unstructured":"Dallachiesa, M., Ebaid, A., Eldawy, A., Elmagarmid, A., Ilyas, I. F., Ouzzani, M., & Tang, N. (2013). Nadeef: A commodity data cleaning system. In SIGMOD (pp. 541\u2013552)."},{"key":"10001_CR12","volume-title":"CIDR","author":"D Deng","year":"2017","unstructured":"Deng, D., Fernandez, R. C., Abedjan, Z., Wang, S., Stonebraker, M., Elmagarmid, A. K., Ilyas, I. F., Madden, S., Ouzzani, M., & Tang, N. (2017). The data civilizer system. In CIDR."},{"key":"10001_CR13","unstructured":"Doan, A., Halevy, A. Y., & Ives, Z. G. (2012). Principles of Data Integration. Morgan Kaufmann."},{"issue":"2","key":"10001_CR14","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/2814710.2814713","volume":"44","author":"J Duggan","year":"2015","unstructured":"Duggan, J., Elmore, A. J., Stonebraker, M., Balazinska, M., Howe, B., Kepner, J., Madden, S., Maier, D., Mattson, T., & Zdonik, S. B. (2015). The BigDAWG Polystore System. SIGMOD Record, 44(2), 11\u201316.","journal-title":"SIGMOD Record"},{"key":"10001_CR15","first-page":"7:1\u20137:8","volume-title":"aiDM@SIGMOD","author":"RC Fernandez","year":"2019","unstructured":"Fernandez, R. C., & Madden, S. (2019). Termite: a system for tunneling through heterogeneous data. In aiDM@SIGMOD (p. 7:1\u20137:8)."},{"key":"10001_CR16","first-page":"150","volume-title":"SEBD","author":"GHL Fletcher","year":"2016","unstructured":"Fletcher, G. H. L., & Mandreoli, F. (2016). No users no dataspaces! query-driven dataspace orchestration? In SEBD (pp. 150\u2013157)."},{"issue":"4","key":"10001_CR17","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/1107499.1107502","volume":"34","author":"MJ Franklin","year":"2005","unstructured":"Franklin, M. J., Halevy, A. Y., & Maier, D. (2005). From databases to dataspaces: a new abstraction for information management. SIGMOD Record, 34(4), 27\u201333.","journal-title":"SIGMOD Record"},{"key":"10001_CR18","volume-title":"Navigational plans for data integration","author":"M Friedman","year":"1999","unstructured":"Friedman, M., Levy, A. Y., & Millstein, T. D. (1999). Navigational plans for data integration. IJCAI: In."},{"issue":"2","key":"10001_CR19","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1023\/A:1008683107812","volume":"8","author":"H Garcia-Molina","year":"1997","unstructured":"Garcia-Molina, H., Papakonstantinou, Y., Quass, D., Rajaraman, A., Sagiv, Y., Ullman, J. D., Vassalos, V., & Widom, J. (1997). The TSIMMIS approach to mediation: Data models and languages. Journal of Intelligent Information System, 8(2), 117\u2013132.","journal-title":"Journal of Intelligent Information System"},{"key":"10001_CR20","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1145\/3034786.3056124","volume-title":"Proceedings of the 36th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, PODS 2017","author":"B Golshan","year":"2017","unstructured":"Golshan, B., Halevy, A. Y., Mihaila, G. A., & Tan, W. (2017). Data integration: After the teenage years. In Proceedings of the 36th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, PODS 2017, Chicago, IL, USA, May 14-19, 2017 (pp. 101\u2013106)."},{"issue":"4","key":"10001_CR21","first-page":"713","volume":"27","author":"M Gorawski","year":"2017","unstructured":"Gorawski, M., & Lorek, M. (2017). Efficient storage, retrieval and analysis of poker hands: An adaptive data framework. Applied Mathematics and Computer Science, 27(4), 713\u2013726.","journal-title":"Applied Mathematics and Computer Science"},{"issue":"3","key":"10001_CR22","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1109\/MS.2014.51","volume":"32","author":"I Gorton","year":"2015","unstructured":"Gorton, I., & Klein, J. (2015). Distribution, data, deployment: Software architecture convergence in big data systems. IEEE Software, 32(3), 78\u201385.","journal-title":"IEEE Software"},{"key":"10001_CR23","first-page":"2097","volume-title":"SIGMOD","author":"R Hai","year":"2016","unstructured":"Hai, R., Geisler, S., & Quix, C. (2016). Constance: An intelligent data lake system. In SIGMOD (pp. 2097\u20132100)."},{"key":"10001_CR24","first-page":"9","volume-title":"Proceedings of the 32nd International Conference on Very Large Data Bases, Seoul, Korea, September 12-15, 2006","author":"AY Halevy","year":"2006","unstructured":"Halevy, A. Y., Rajaraman, A., & Ordille, J. J. (2006). Data integration: The teenage years. In Proceedings of the 32nd International Conference on Very Large Data Bases, Seoul, Korea, September 12-15, 2006 (pp. 9\u201316)."},{"issue":"3","key":"10001_CR25","first-page":"5","volume":"39","author":"AY Halevy","year":"2016","unstructured":"Halevy, A. Y., Korn, F., Noy, N. F., Olston, C., Polyzotis, N., Roy, S., & Whang, S. E. (2016). Managing google\u2019s data lake: an overview of the goods system. IEEE Data Eng. Bull., 39(3), 5\u201314.","journal-title":"IEEE Data Eng. Bull."},{"key":"10001_CR26","first-page":"463","volume-title":"ER","author":"M Hewasinghage","year":"2018","unstructured":"Hewasinghage, M., Varga, J., Abell\u00f3, A., & Zim\u00e1nyi, E. (2018). Managing polyglot systems metadata with hypergraphs. In ER (pp. 463\u2013478)."},{"key":"10001_CR27","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.is.2014.01.004","volume":"44","author":"P Jovanovic","year":"2014","unstructured":"Jovanovic, P., Romero, O., Simitsis, A., Abell\u00f3, A., & Mayorova, D. (2014a). A requirement-driven approach to the design and evolution of data warehouses. Information Systems, 44, 94\u2013119.","journal-title":"Information Systems"},{"key":"10001_CR28","first-page":"1060","volume-title":"ICDE","author":"P Jovanovic","year":"2014","unstructured":"Jovanovic, P., Simitsis, A., & Wilkinson, K. (2014b). Engine independence for logical analytic flows. In ICDE (pp. 1060\u20131071)."},{"issue":"5","key":"10001_CR29","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1109\/TKDE.2016.2515609","volume":"28","author":"P Jovanovic","year":"2016","unstructured":"Jovanovic, P., Romero, O., Simitsis, A., & Abell\u00f3, A. (2016). Incremental consolidation of data-intensive multi-flows. IEEE Transactions on Knowledge and Data Engineering, 28(5), 1203\u20131216.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10001_CR30","first-page":"1599","volume-title":"SIGMOD","author":"N Konstantinou","year":"2017","unstructured":"Konstantinou, N., Koehler, M., Abel, E., Civili, C., Neumayr, B., Sallinger, E., Fernandes, A. A. A., Gottlob, G., Keane, J. A., Libkin, L., & Paton, N. W. (2017). The VADA architecture for cost-effective data wrangling. In SIGMOD (pp. 1599\u20131602)."},{"key":"10001_CR31","first-page":"233","volume-title":"PODS","author":"M Lenzerini","year":"2002","unstructured":"Lenzerini, M. (2002). Data integration: A theoretical perspective. In PODS (pp. 233\u2013246)."},{"key":"10001_CR32","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1613\/jair.1145","volume":"18","author":"K Lerman","year":"2003","unstructured":"Lerman, K., Minton, S., & Knoblock, C. A. (2003). Wrapper maintenance: A machine learning approach. Journal of Artificial Intelligence Research, 18, 149\u2013181.","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"5","key":"10001_CR33","first-page":"30","volume":"46","author":"S Luj\u00e1n-Mora","year":"2006","unstructured":"Luj\u00e1n-Mora, S., & Trujillo, J. (2006). Applying the UML and the unified process to the design of data warehouses. JCIS, 46(5), 30\u201358.","journal-title":"JCIS"},{"issue":"2","key":"10001_CR34","doi-asserted-by":"crossref","first-page":"111","DOI":"10.3233\/FI-2018-1734","volume":"163","author":"RF Munir","year":"2018","unstructured":"Munir, R. F., Nadal, S., Romero, O., Abell\u00f3, A., Jovanovic, P., Thiele, M., & Lehner, W. (2018). Intermediate results materialization selection and format for data-intensive flows. Fundam. Inform., 163(2), 111\u2013138.","journal-title":"Fundam. Inform."},{"key":"10001_CR35","first-page":"185","volume-title":"ISWC","author":"S Nadal","year":"2019","unstructured":"Nadal, S., Rabbani, K., Romero, O., & Tadesse, S. (2019a). ODIN: A dataspace management system. In ISWC (pp. 185\u2013188)."},{"key":"10001_CR36","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.is.2018.01.006","volume":"79","author":"S Nadal","year":"2019","unstructured":"Nadal, S., Romero, O., Abell\u00f3, A., Vassiliadis, P., & Vansummeren, S. (2019b). An integration-oriented ontology to govern evolution in big data ecosystems. Information Systems, 79, 3\u201319.","journal-title":"Information Systems"},{"issue":"2","key":"10001_CR37","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1007\/s10796-016-9720-4","volume":"20","author":"A Popovic","year":"2018","unstructured":"Popovic, A., Hackney, R., Tassabehji, R., & Castelli, M. (2018). The impact of big data analytics on firms\u2019 high value business performance. Information Systems Frontiers, 20(2), 209\u2013222.","journal-title":"Information Systems Frontiers"},{"key":"10001_CR38","first-page":"479","volume-title":"WWW","author":"F Priyatna","year":"2014","unstructured":"Priyatna, F., Corcho, \u00d3., & Sequeda, J. F. (2014). Formalisation and experiences of r2rml-based SPARQL to SQL query translation using morph. In WWW (pp. 479\u2013490)."},{"key":"10001_CR39","volume-title":"Data lake","author":"C Quix","year":"2019","unstructured":"Quix, C., & Hai, R. (2019). Data lake. Encyclopedia of Big Data Technologies: In."},{"key":"10001_CR40","unstructured":"Rabbani, K. (2019). Supporting the Semi-Automatic Creation of the Target Schema in Data Integration Systems. Master\u2019s thesis, Technische Univesitat Berlin - Universitat Polit\u00e8cnica de Catalunya, BarcelonaTech."},{"issue":"4","key":"10001_CR41","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1145\/141356.141377","volume":"20","author":"F Saltor","year":"1991","unstructured":"Saltor, F., Castellanos, M., & Garc\u00eda-Solaco, M. (1991). Suitability of data models as canonical models for federated databases. SIGMOD Record, 20(4), 44\u201348.","journal-title":"SIGMOD Record"},{"key":"10001_CR42","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/978-3-642-16518-4_4","volume-title":"Schema Matching and Mapping","author":"AD Sarma","year":"2011","unstructured":"Sarma, A. D., Dong, X. L., & Halevy, A. Y. (2011). Uncertainty in data integration and dataspace support platforms. In Schema Matching and Mapping (pp. 75\u2013108)."},{"issue":"10","key":"10001_CR43","doi-asserted-by":"crossref","first-page":"1404","DOI":"10.1109\/TKDE.2005.169","volume":"17","author":"A Simitsis","year":"2005","unstructured":"Simitsis, A., Vassiliadis, P., & Sellis, T. K. (2005). State-space optimization of ETL workflows. IEEE Transactions on Knowledge and Data Engineering, 17(10), 1404\u20131419.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10001_CR44","first-page":"1174","volume-title":"ICDE","author":"A Simitsis","year":"2013","unstructured":"Simitsis, A., Wilkinson, K., Dayal, U., & Hsu, M. (2013). HFMS: managing the lifecycle and complexity of hybrid analytic data flows. In ICDE (pp. 1174\u20131185)."},{"issue":"4","key":"10001_CR45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/jswis.2007100101","volume":"3","author":"D Skoutas","year":"2007","unstructured":"Skoutas, D., & Simitsis, A. (2007). Ontology-based conceptual design of ETL processes for both structured and semi-structured data. Int. J. Semantic Web Inf. Syst., 3(4), 1\u201324.","journal-title":"Int. J. Semantic Web Inf. Syst."},{"key":"10001_CR46","unstructured":"Stonebraker, M. (2019). The Case for Polystores \u2013 ACM SIGMOD Blog. [Online; accessed 27. Jun. 2019]."},{"key":"10001_CR47","volume-title":"CIDR","author":"M Stonebraker","year":"2013","unstructured":"Stonebraker, M., Bruckner, D., Ilyas, I. F., Beskales, G., Cherniack, M., Zdonik, S. B., Pagan, A., & Xu, S. (2013). Data Curation at Scale: The Data Tamer System. In CIDR."},{"key":"10001_CR48","volume-title":"ARDI: Automatic Generation of RDFS Models from Heterogeneous Data Sources","author":"S Tadesse","year":"2019","unstructured":"Tadesse, S., G\u00f3mez, C., Romero, O., Hose, K., & Rabbani, K. (2019). ARDI: Automatic Generation of RDFS Models from Heterogeneous Data Sources. In: EDOC."},{"key":"10001_CR49","volume-title":"CIDR","author":"IG Terrizzano","year":"2015","unstructured":"Terrizzano, I. G., Schwarz, P. M., Roth, M., & Colino, J. E. (2015). Data wrangling: The challenging yourney from the wild to the lake. In CIDR."},{"key":"10001_CR50","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1145\/2811222.2811228","volume-title":"DOLAP","author":"R Touma","year":"2015","unstructured":"Touma, R., Romero, O., & Jovanovic, P. (2015). Supporting data integration tasks with semi-automatic ontology construction. In DOLAP (pp. 89\u201398)."},{"key":"10001_CR51","first-page":"89","volume-title":"DaWaK","author":"J Varga","year":"2014","unstructured":"Varga, J., Romero, O., Pedersen, T. B., & Thomsen, C. (2014). Towards next generation BI systems: The analytical metadata challenge. In DaWaK (pp. 89\u2013101)."},{"issue":"1","key":"10001_CR52","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10796-016-9732-0","volume":"20","author":"A Wojciechowski","year":"2018","unstructured":"Wojciechowski, A. (2018). ETL workflow reparation by means of case-based reasoning. Information Systems Frontiers, 20(1), 21\u201343.","journal-title":"Information Systems Frontiers"}],"container-title":["Information Systems Frontiers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10796-020-10001-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10796-020-10001-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10796-020-10001-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,18]],"date-time":"2021-04-18T00:08:36Z","timestamp":1618704516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10796-020-10001-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,18]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["10001"],"URL":"https:\/\/doi.org\/10.1007\/s10796-020-10001-y","relation":{},"ISSN":["1387-3326","1572-9419"],"issn-type":[{"value":"1387-3326","type":"print"},{"value":"1572-9419","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,18]]},"assertion":[{"value":"18 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}