{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:41:10Z","timestamp":1789000870879,"version":"build-2803163510"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100009550","name":"Universiteit Hasselt","doi-asserted-by":"publisher","award":["BOF20ZAP02"],"award-info":[{"award-number":["BOF20ZAP02"]}],"id":[{"id":"10.13039\/501100009550","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek Vlaanderen","doi-asserted-by":"crossref","award":["G055219N"],"award-info":[{"award-number":["G055219N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100019618","name":"Vlaams Supercomputer Centrum","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019618","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":[[2026,6]]},"DOI":"10.1007\/s10796-024-10504-y","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T04:02:22Z","timestamp":1720152142000},"page":"877-899","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Data Ingestion Validation Through Stable Conditional Metrics with Ranking and Filtering"],"prefix":"10.1007","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7360-8162","authenticated-orcid":false,"given":"Niels","family":"Bylois","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7143-1903","authenticated-orcid":false,"given":"Frank","family":"Neven","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7793-9049","authenticated-orcid":false,"given":"Stijn","family":"Vansummeren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,5]]},"reference":[{"key":"10504_CR1","doi-asserted-by":"publisher","unstructured":"Abedjan, Z., Chu, X., Deng, D., Fernandez, R.C., Ilyas, I.F., Ouzzani, M., Papotti, P., Stonebraker, M., Tang, N. (2016) Detecting data errors: Where are we and what needs to be done? Proc. VLDB Endow, 9(12), 993\u20131004. https:\/\/doi.org\/10.14778\/2994509.2994518. http:\/\/www.vldb.org\/pvldb\/vol9\/p993-abedjan.pdf","DOI":"10.14778\/2994509.2994518"},{"key":"10504_CR2","doi-asserted-by":"publisher","unstructured":"Abedjan, Z., Golab, L., & Naumann, F. (2015). Profiling relational data: A survey. VLDB J., 24(4), 557\u2013581. https:\/\/doi.org\/10.1007\/s00778-015-0389-y","DOI":"10.1007\/s00778-015-0389-y"},{"key":"10504_CR3","doi-asserted-by":"publisher","DOI":"10.2200\/S00878ED1V01Y201810DTM052","volume-title":"Data Profiling","author":"Z Abedjan","year":"2018","unstructured":"Abedjan, Z., Golab, L., Naumann, F., & Papenbrock, T. (2018). Data Profiling. Synthesis Lectures on Data Management: Morgan & Claypool Publishers. https:\/\/doi.org\/10.2200\/S00878ED1V01Y201810DTM052"},{"key":"10504_CR4","unstructured":"Abiteboul, S., Hull, R., Vianu, V. (1995) Foundations of databases, vol.\u00a08. Addison-Wesley Reading"},{"key":"10504_CR5","unstructured":"Ataccama (2024) Unified data management platform. https:\/\/www.ataccama.com\/"},{"key":"10504_CR6","doi-asserted-by":"publisher","unstructured":"Baylor, D., Breck, E., Cheng, H.T., Fiedel, N., Foo, C.Y., Haque, Z., Haykal, S., Ispir, M., Jain, V., Koc, L., Koo, C.Y., Lew, L., ewald, C., Modi, A.N., Polyzotis, N., Ramesh, S., Roy, S., Whang, S.E., Wicke, M., Wilkiewicz, J., Zhang, X., Zinkevich, M. (2017) Tfx: A tensorflow-based production-scale machine learning platform. In: Proceedings of the 23rd ACM SIGKDD international conference on Knowledge Discovery and Data mining, KDD \u201917, pp. 1387\u20131395. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/3097983.3098021","DOI":"10.1145\/3097983.3098021"},{"key":"10504_CR7","doi-asserted-by":"publisher","unstructured":"Boese, J., Flunkert, V., Gasthaus, J., Januschowski, T., Lange, D., Salinas, D., Schelter, S., Seeger, M.W., Wang, B. (2017) Probabilistic demand forecasting at scale. Proc. VLDB Endow, 10(12), 1694\u20131705. https:\/\/doi.org\/10.14778\/3137765.3137775. http:\/\/www.vldb.org\/pvldb\/vol10\/p1694-schelter.pdf","DOI":"10.14778\/3137765.3137775"},{"key":"10504_CR8","unstructured":"Breck, E., Polyzotis, N., Roy, S., Whang, S., Zinkevich, M.: Data validation for machine learning. In: A.\u00a0Talwalkar, V.\u00a0Smith, M.\u00a0Zaharia (eds.) Proceedings of Machine Learning and Systems 2019, MLSys 2019, Stanford, CA, USA, March 31 - April 2, 2019. mlsys.org (2019). https:\/\/proceedings.mlsys.org\/book\/267.pdf"},{"issue":"1\u20137","key":"10504_CR9","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/S0169-7552(98)00110-X","volume":"30","author":"S Brin","year":"1998","unstructured":"Brin, S., & Page, L. (1998). The anatomy of a large-scale hypertextual web search engine. Comput. Networks, 30(1\u20137), 107\u2013117. https:\/\/doi.org\/10.1016\/S0169-7552(98)00110-X","journal-title":"Comput. Networks"},{"key":"10504_CR10","doi-asserted-by":"crossref","unstructured":"Bylois, N., Neven, F., Vansummeren, S. (2023) CM-Explorer: Dissecting data ingestion problems. Demo accepted for VLDB 2023","DOI":"10.14778\/3611540.3611595"},{"key":"10504_CR11","doi-asserted-by":"crossref","unstructured":"Bylois, N., Neven, F., Vansummeren, S. (2023) Data ingestion validation through stable conditional metrics with ranking and filtering. To appear in the proceedings of the 27th European Conference on Advances in Databases and Information Systems (ADBIS 2023)","DOI":"10.2139\/ssrn.4552561"},{"key":"10504_CR12","doi-asserted-by":"publisher","unstructured":"Caveness, E., C., P.S.G., Peng, Z., Polyzotis, N., Roy, S., Zinkevich, M. (2020) Tensorflow data validation: Data analysis and validation in continuous ML pipelines. In: D.\u00a0Maier, R.\u00a0Pottinger, A.\u00a0Doan, W.\u00a0Tan, A.\u00a0Alawini, H.Q. Ngo (eds.) Proceedings of the 2020 international conference on management of data, SIGMOD conference 2020, online conference [Portland, OR, USA], June 14-19, 2020, pp. 2793\u20132796. ACM. https:\/\/doi.org\/10.1145\/3318464.3384707","DOI":"10.1145\/3318464.3384707"},{"key":"10504_CR13","doi-asserted-by":"publisher","unstructured":"Chandola, V., Banerjee, A., Kumar, V. (2009) Anomaly detection: A survey. ACM Comput Surv, 41(3). https:\/\/doi.org\/10.1145\/1541880.1541882","DOI":"10.1145\/1541880.1541882"},{"key":"10504_CR14","doi-asserted-by":"publisher","unstructured":"Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21\u201327. https:\/\/doi.org\/10.1109\/TIT.1967.1053964","DOI":"10.1109\/TIT.1967.1053964"},{"key":"10504_CR15","doi-asserted-by":"publisher","unstructured":"Fan, W., Geerts, F., Jia, X., Kementsietsidis, A. (2008) Conditional functional dependencies for capturing data inconsistencies. ACM Trans Database Syst, 33(2), 6:1\u20136:48. https:\/\/doi.org\/10.1145\/1366102.1366103","DOI":"10.1145\/1366102.1366103"},{"issue":"1","key":"10504_CR16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.2307\/3033543","volume":"40","author":"LC Freeman","year":"1977","unstructured":"Freeman, L. C. (1977). A set of measures of centrality based on betweenness. Sociometry, 40(1), 35\u201341.","journal-title":"Sociometry"},{"issue":"3","key":"10504_CR17","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/0378-8733(78)90021-7","volume":"1","author":"LC Freeman","year":"1979","unstructured":"Freeman, L. C. (1979). Centrality in networks conceptual clarification. Social Networks, 1(3), 215\u2013239.","journal-title":"Social Networks"},{"key":"10504_CR18","doi-asserted-by":"publisher","unstructured":"Heidari, A., McGrath, J., Ilyas, I.F., Rekatsinas, T. (2019) Holodetect: Few-shot learning for error detection. In: P.A. Boncz, S.\u00a0Manegold, A.\u00a0Ailamaki, A.\u00a0Deshpande, T.\u00a0Kraska (eds.) Proceedings of the 2019 international conference on management of data, SIGMOD Conference 2019, Amsterdam, The Netherlands, June 30 - July 5, 2019, pp. 829\u2013846. ACM. https:\/\/doi.org\/10.1145\/3299869.3319888","DOI":"10.1145\/3299869.3319888"},{"key":"10504_CR19","doi-asserted-by":"publisher","unstructured":"Ilyas, I. F., & Chu, X. (2019). Data Cleaning. ACM. https:\/\/doi.org\/10.1145\/3310205","DOI":"10.1145\/3310205"},{"key":"10504_CR20","unstructured":"Informatica (2024) Home. https:\/\/docs.informatica.com\/"},{"issue":"5","key":"10504_CR21","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1145\/324133.324140","volume":"46","author":"JM Kleinberg","year":"1999","unstructured":"Kleinberg, J. M. (1999). Authoritative sources in a hyperlinked environment. J. ACM, 46(5), 604\u2013632. https:\/\/doi.org\/10.1145\/324133.324140","journal-title":"J. ACM"},{"key":"10504_CR22","doi-asserted-by":"publisher","unstructured":"Li, Z., Zhao, Y., Hu, X., Botta, N., Ionescu, C., & Chen, G. H. (2023). ECOD: Unsupervised outlier detection using empirical cumulative distribution functions. IEEE Trans. Knowl. Data Eng., 35(12), 12181\u201312193. https:\/\/doi.org\/10.1109\/TKDE.2022.3159580","DOI":"10.1109\/TKDE.2022.3159580"},{"key":"10504_CR23","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., Zhou, Z.H. (2008) Isolation forest. In: Proceedings of the 2008 eighth IEEE international conference on data mining, IEEE, pp. 413\u2013422.","DOI":"10.1109\/ICDM.2008.17"},{"key":"10504_CR24","doi-asserted-by":"publisher","unstructured":"Liu, Z., Zhou, Z., & Rekatsinas, T. (2022). Picket: Guarding against corrupted data in tabular data during learning and inference. VLDB J., 31(5), 927\u2013955. https:\/\/doi.org\/10.1007\/s00778-021-00699-w","DOI":"10.1007\/s00778-021-00699-w"},{"key":"10504_CR25","doi-asserted-by":"publisher","unstructured":"Mahdavi, M., Abedjan, Z., Fernandez, R.C., Madden, S., Ouzzani, M., Stonebraker, M., Tang, N. (2019) Raha: A configuration-free error detection system. In: P.A. Boncz, S.\u00a0Manegold, A.\u00a0Ailamaki, A.\u00a0Deshpande, T.\u00a0Kraska (eds.) Proceedings of the 2019 international conference on management of data, SIGMOD Conference 2019, Amsterdam, The Netherlands, June 30 - July 5, 2019, pp. 865\u2013882. ACM. https:\/\/doi.org\/10.1145\/3299869.3324956","DOI":"10.1145\/3299869.3324956"},{"key":"10504_CR26","doi-asserted-by":"publisher","unstructured":"Pastor, E., de\u00a0Alfaro, L., Baralis, E. (2021) Looking for trouble: Analyzing classifier behavior via pattern divergence. In: G.\u00a0Li, Z.\u00a0Li, S.\u00a0Idreos, D.\u00a0Srivastava (eds.) SIGMOD \u201921: International conference on management of data, virtual event, China, June 20-25, 2021, pp. 1400\u20131412. ACM. https:\/\/doi.org\/10.1145\/3448016.3457284","DOI":"10.1145\/3448016.3457284"},{"key":"10504_CR27","unstructured":"Polyzotis, N., Whang, S., Kraska, T.K., Chung, Y. (2019) Slice finder: Automated data slicing for model validation. In: Proceedings of the IEEE Int\u2019 Conf. on Data Engineering (ICDE), 2019. https:\/\/arxiv.org\/pdf\/1807.06068.pdf"},{"key":"10504_CR28","doi-asserted-by":"publisher","unstructured":"Redyuk, S., Kaoudi, Z., Markl, V., Schelter, S. (2021) Automating data quality validation for dynamic data ingestion. In: Y.\u00a0Velegrakis, D.\u00a0Zeinalipour-Yazti, P.K. Chrysanthis, F.\u00a0Guerra (eds.) Proceedings of the 24th international conference on extending database technology, EDBT 2021, Nicosia, Cyprus, March 23 - 26, 2021, pp. 61\u201372. OpenProceedings.org. https:\/\/doi.org\/10.5441\/002\/edbt.2021.07","DOI":"10.5441\/002\/edbt.2021.07"},{"key":"10504_CR29","doi-asserted-by":"publisher","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., R\u00e9, C. (2017) Holoclean: Holistic data repairs with probabilistic inference. Proc. VLDB Endow. 10(11), 1190\u20131201. https:\/\/doi.org\/10.14778\/3137628.3137631. http:\/\/www.vldb.org\/pvldb\/vol10\/p1190-rekatsinas.pdf","DOI":"10.14778\/3137628.3137631"},{"key":"10504_CR30","doi-asserted-by":"publisher","unstructured":"Sa, C.D., Ilyas, I.F., Kimelfeld, B., R\u00e9, C., Rekatsinas, T. (2019) A formal framework for probabilistic unclean databases. In: P.\u00a0Barcel\u00f3, M.\u00a0Calautti (eds.) 22nd international conference on database theory, ICDT 2019, March 26-28, 2019, Lisbon, Portugal, LIPIcs, 127, pp. 6:1\u20136:18. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik. https:\/\/doi.org\/10.4230\/LIPIcs.ICDT.2019.6","DOI":"10.4230\/LIPIcs.ICDT.2019.6"},{"key":"10504_CR31","doi-asserted-by":"publisher","unstructured":"Sagadeeva, S., Boehm, M. (2021) Sliceline: Fast, linear-algebra-based slice finding for ML model debugging. In: G.\u00a0Li, Z.\u00a0Li, S.\u00a0Idreos, D.\u00a0Srivastava (eds.) SIGMOD \u201921: International Conference on Management of Data, Virtual Event, China, June 20-25, 2021, pp. 2290\u20132299. ACM. https:\/\/doi.org\/10.1145\/3448016.3457323","DOI":"10.1145\/3448016.3457323"},{"key":"10504_CR32","doi-asserted-by":"publisher","unstructured":"Schelter, S., Bie\u00dfmann, F., Lange, D., Rukat, T., Schmidt, P., Seufert, S., Brunelle, P., Taptunov, A. (2019) Unit testing data with deequ. In: P.A. Boncz, S.\u00a0Manegold, A.\u00a0Ailamaki, A.\u00a0Deshpande, T.\u00a0Kraska (eds.) Proceedings of the 2019 international conference on management of data, SIGMOD Conference 2019, Amsterdam, The Netherlands, June 30 - July 5, 2019, pp. 1993\u20131996. ACM. https:\/\/doi.org\/10.1145\/3299869.3320210","DOI":"10.1145\/3299869.3320210"},{"key":"10504_CR33","doi-asserted-by":"crossref","unstructured":"Schelter, S., Lange, D., Schmidt, P., Celikel, M., Biessmann, F. (2018) Automating large-scale data quality verification. In: VLDB 2018. https:\/\/www.amazon.science\/publications\/automating-large-scale-data-quality-verification","DOI":"10.14778\/3229863.3229867"},{"key":"10504_CR34","doi-asserted-by":"publisher","unstructured":"Schelter, S., Lange, D., Schmidt, P., Celikel, M., Bie\u00dfmann, F., Grafberger, A. (2018) Automating large-scale data quality verification. Proc. VLDB Endow, 11(12), 1781\u20131794. https:\/\/doi.org\/10.14778\/3229863.3229867. http:\/\/www.vldb.org\/pvldb\/vol11\/p1781-schelter.pdf","DOI":"10.14778\/3229863.3229867"},{"key":"10504_CR35","doi-asserted-by":"crossref","unstructured":"Sebastian-Coleman, L. (2012). Measuring data quality for ongoing improvement: A data quality assessment framework (1st ed.). San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.","DOI":"10.1016\/B978-0-12-397033-6.00020-1"},{"key":"10504_CR36","unstructured":"Software, A. (2024) Welcome to astera data stack documentation\u2014version 10\u2014astera data stack. https:\/\/documentation.astera.com\/"},{"issue":"5","key":"10504_CR37","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.3233\/IDA-150764","volume":"19","author":"G Tang","year":"2015","unstructured":"Tang, G., Pei, J., Bailey, J., & Dong, G. (2015). Mining multidimensional contextual outliers from categorical relational data. Intell. Data Anal., 19(5), 1171\u20131192. https:\/\/doi.org\/10.3233\/IDA-150764","journal-title":"Intell. Data Anal."},{"key":"10504_CR38","doi-asserted-by":"publisher","unstructured":"Wang, R.Y., Strong, D.M. (1996) Beyond accuracy: What data quality means to data consumers. J Manage Inf Syst, 12(4), 5\u201333. https:\/\/doi.org\/10.1080\/07421222.1996.11518099","DOI":"10.1080\/07421222.1996.11518099"},{"key":"10504_CR39","doi-asserted-by":"crossref","unstructured":"Wei, L., Qian, W., Zhou, A., Jin, W., & Yu, J. X. (2003). Hot: Hypergraph-based outlier test for categorical data. In: K. Y. Whang, J. Jeon, K. Shim, & J. Srivastava (Eds.), Advances in knowledge discovery and data mining (pp. 399\u2013410). Berlin Heidelberg, Berlin, Heidelberg: Springer.","DOI":"10.1007\/3-540-36175-8_40"},{"key":"10504_CR40","doi-asserted-by":"publisher","unstructured":"Zaharia, M., Xin, R.S., Wendell, P., Das, T., Armbrust, M., Dave, A., Meng, X., Rosen, J., Venkataraman, S., Franklin, M.J., Ghodsi, A., Gonzalez, J., Shenker, S., Stoica, I. (2016) Apache spark: A unified engine for big data processing. Commun ACM, 59(11), 56\u201365. https:\/\/doi.org\/10.1145\/2934664","DOI":"10.1145\/2934664"}],"container-title":["Information Systems Frontiers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10796-024-10504-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10796-024-10504-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10796-024-10504-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T08:57:48Z","timestamp":1784883468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10796-024-10504-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,5]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10504"],"URL":"https:\/\/doi.org\/10.1007\/s10796-024-10504-y","relation":{},"ISSN":["1387-3326","1572-9419"],"issn-type":[{"value":"1387-3326","type":"print"},{"value":"1572-9419","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,5]]},"assertion":[{"value":"10 June 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"There are no ethical issues involved in this work.","order":1,"name":"Ethics","label":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors give their consent for publication.","order":2,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":3,"name":"Ethics","label":"Conflict of Interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}