{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:00:37Z","timestamp":1775250037577,"version":"3.50.1"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union\u2019s Horizon Europe Program","award":["101057779 (Project: TwinAIR)"],"award-info":[{"award-number":["101057779 (Project: TwinAIR)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3676924","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:09:20Z","timestamp":1774296560000},"page":"48262-48276","source":"Crossref","is-referenced-by-count":0,"title":["A Survey on Platform-Level Data Quality: From Visibility to Controllability"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3824-3056","authenticated-orcid":false,"given":"Tony","family":"Rosset","sequence":"first","affiliation":[{"name":"Institute Industrial IT (inIT), Technische Hochschule OWL, Lemgo, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6537-4511","authenticated-orcid":false,"given":"Lukasz","family":"Wisniewski","sequence":"additional","affiliation":[{"name":"Institute Industrial IT (inIT), Technische Hochschule OWL, Lemgo, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7643-2342","authenticated-orcid":false,"given":"Stefano","family":"Scanzio","sequence":"additional","affiliation":[{"name":"CNR-IEIIT, Milan, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2596101"},{"key":"ref2","volume-title":"Data Quality Improvement Stats From ETL: 50+ Key Facts Every Data Professional Should Know","year":"2026"},{"key":"ref3","volume-title":"Data Quality Challenges: 2025 Planning Insights","year":"2025"},{"key":"ref4","volume-title":"The Cost of Poor Data Quality on Bus. Operations","year":"2023"},{"key":"ref5","volume-title":"The Annual State of Data Quality Survey","year":"2023"},{"key":"ref6","volume-title":"Millions Lost in 2023 Due to Poor Data Quality, Potential for Billions To Be Lost With AI Without Action","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.1996.11518099"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2523813"},{"key":"ref10","volume-title":"Datahub: A Generalized Metadata Search and Discovery Tool","author":"Lan","year":"2026"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2023.107268"},{"key":"ref12","volume-title":"ISO\/IEC 25012:2008-Software Engineering-Systems and Software Quality Requirements and Evaluation (SQuaRE)-Data Quality Model","year":"2008"},{"key":"ref13","volume-title":"Improving Data Warehouse and Business Information Quality","author":"English","year":"1999"},{"key":"ref14","volume-title":"Data Quality: The Field Guide","author":"Redman","year":"2001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415560"},{"key":"ref16","volume-title":"Apache Iceberg: An Open Table Format for Huge Analytic Datasets","year":"2024"},{"key":"ref17","volume-title":"Apache Hudi: The Data Lake Platform","year":"2021"},{"key":"ref18","volume-title":"Dapper, A Large-Scale Distributed Systems Tracing Infrastructure","author":"Sigelman","year":"2010"},{"key":"ref19","volume-title":"Site Reliability Engineering: How Google Runs Production Systems","author":"Beyer","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994518"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3377455"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2"},{"issue":"8","key":"ref23","first-page":"1","article-title":"A survey of data quality requirements that matter in machine learning development pipelines","volume":"56","author":"Priestley-Maria","year":"2023","journal-title":"ACM Comput. Surveys"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/AITest62860.2024.00023"},{"key":"ref25","article-title":"A survey of open-source data quality tools: Shedding light on the materialization of data quality dimensions in practice","author":"Papastergios","year":"2024","journal-title":"arXiv:2407.18649"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-017-0486-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054772"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2022.850611"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.03.008"},{"key":"ref30","first-page":"3","article-title":"A data quality framework for graph-based virtual data integration systems","volume-title":"Proc. 23rd Int. Conf. Web Inf. Syst. Eng. (WISE)","author":"Debruyne"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24106-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3636388"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3564139"},{"key":"ref34","volume-title":"DAMA-DMBOK: Data Management Body of Knowledge","year":"2017"},{"key":"ref35","volume-title":"ISO 8000-1:2022-data Quality\u2014Part 1: Overview","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jik.2024.100598"},{"key":"ref37","first-page":"35","article-title":"Data governance capabilities; empirical validation in case studies of large organisations","volume-title":"Proc. 36th Bled eConf.-Digital Economy Society, Balancing Act Digital Innov. Times Instability","author":"Merkus"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3417291"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3627855"},{"key":"ref40","volume-title":"The State of Data Quality 2022","year":"2022"},{"key":"ref41","volume-title":"Data Mesh: Delivering Data-Driven Value At Scale","author":"Dehghani","year":"2022"},{"key":"ref42","first-page":"272","article-title":"A morphology of the organisation of data governance","volume-title":"Proc. 19th Eur. Conf. Inf. Syst. (ECIS)","author":"Otto"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972771.42"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1515\/itit-2022-0077"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-92474-3_2","article-title":"Challenges in data quality management for IoT-enhanced event logs","volume-title":"Proc. 19th Int. Conf. Res. Challenges Inf. Sci.","author":"Bertrand"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2815400.2815415"},{"key":"ref47","volume-title":"The Rise of Data Downtime","author":"Moses","year":"2021"},{"key":"ref48","volume-title":"LakeFS: Data Version Control for Data Lakes","year":"2025"},{"key":"ref49","volume-title":"Ontology-Based Data Quality Management for Data Streams","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824076"},{"key":"ref51","volume-title":"Streaming Systems: The What, Where, When, and How of Large-Scale Data Processing","author":"Akidau","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.08.002"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/s21175834"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3456859.3456863"},{"key":"ref55","volume-title":"Designing Data-Intensive Applications","author":"Kleppmann","year":"2017"},{"key":"ref56","volume-title":"Context Information Management (CIM); NGSI-LD API","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/s20040953"},{"key":"ref58","volume-title":"PROV-DM: The PROV Data Model","author":"Moreau","year":"2026"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s44230-025-00106-5"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1561\/1900000068"},{"key":"ref61","volume-title":"OpenLineage: An Open Framework for Data Lineage Collection and Analysis","year":"2026"},{"key":"ref62","volume-title":"Marquez: Open Source Metadata Service for Data Ecosystem Observability","year":"2026"},{"key":"ref63","volume-title":"Open Sourcing DataHub: LinkedIn\u2019s Metadata Search and Discovery Platform","author":"Sahin","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2025.112584"},{"key":"ref65","volume-title":"2023 Data Catalogs in Review: Key Trends Shaping Data Management in 2024","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3568542"},{"key":"ref67","volume-title":"Data Validation for Machine Learning","author":"Polyzotis"},{"key":"ref68","first-page":"2503","article-title":"Hidden technical debt in machine learning systems","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"28","author":"Sculley"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00775-9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00041"},{"key":"ref72","volume-title":"Hopsworks Feature Store Documentation","year":"2026"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3571724"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3299887.3299891"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2876857"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3533381"},{"key":"ref77","volume-title":"Apache Avro Specification","year":"2026"},{"key":"ref78","volume-title":"Schema Registry for Confluent Platform","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-012-0302-x"},{"key":"ref80","article-title":"Lakehouse: A new generation of open platforms that unify data warehousing and advanced analytics","volume-title":"Proc. 11th Annu. Conf. Innov. Data Syst. Res. (CIDR)","author":"Zaharia"},{"key":"ref81","volume-title":"A Compounding Threat: The True Cost of Poor Data Quality","year":"2026"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3310205"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"ref84","volume-title":"Anonymizing Health Data: Case Studies and Methods to Get You Started","author":"El Emam","year":"2013"},{"key":"ref85","article-title":"Scalable private learning with PATE","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Papernot"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11454448.pdf?arnumber=11454448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:54:52Z","timestamp":1775246092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11454448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3676924","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}