{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:10:31Z","timestamp":1777871431117,"version":"3.51.4"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003005","name":"Eindhoven University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003005","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115800","type":"journal-article","created":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:17:01Z","timestamp":1774052221000},"page":"115800","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["LLM-based harmonized data ingestion for dataspace: a novel system for automating data ingestion across heterogeneous data sources"],"prefix":"10.1016","volume":"342","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4106-111X","authenticated-orcid":false,"given":"Parwinder","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3640-9134","authenticated-orcid":false,"given":"Michele","family":"Gaspari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8379-770X","authenticated-orcid":false,"given":"Nirvana","family":"Meratnia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7357-2796","authenticated-orcid":false,"given":"Mirko","family":"Presser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115800_bib0001","article-title":"Enabling edge-driven dataspace integration through convergence of distributed technologies","volume":"25","author":"Singh","year":"2024","journal-title":"IoT"},{"key":"10.1016\/j.knosys.2026.115800_bib0002","series-title":"2023 IEEE Conference on Standards for Communications and Networking (CSCN)","first-page":"130","article-title":"Meta standard requirements for harmonizing dataspace integration at the edge","author":"Singh","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0003","series-title":"INTERNET 2024: The Sixteenth International Conference on Evolving Internet, ISBN: 978-1-68558-133-6","article-title":"Data-driven IoT ecosystem for cross business growth: an inspiration future internet model with dataspace at the edge","author":"Singh","year":"2024"},{"key":"10.1016\/j.knosys.2026.115800_bib0004","series-title":"International Symposium on Leveraging Applications of Formal Methods","first-page":"366","article-title":"Evolving data space technologies: lessons learned from an IDS connector reference implementation","author":"Pampus","year":"2022"},{"key":"10.1016\/j.knosys.2026.115800_bib0005","series-title":"Proceedings of the 1st International Workshop on Data Economy","first-page":"42","article-title":"Enabling data spaces: existing developments and challenges","author":"Solmaz","year":"2022"},{"key":"10.1016\/j.knosys.2026.115800_bib0006","unstructured":"B. Otto, GAIX-X and IDS. Position Paper, Version 1.0 01(2021)."},{"key":"10.1016\/j.knosys.2026.115800_bib0007","series-title":"International Conference on Advanced Information Systems Engineering","first-page":"549","article-title":"Data sovereignty and the internet of production","author":"Jarke","year":"2020"},{"key":"10.1016\/j.knosys.2026.115800_bib0008","unstructured":"International data spaces reference architecture model (IDS-RAM), 2024, (Conceptual Framework). Version 4.2."},{"issue":"5","key":"10.1016\/j.knosys.2026.115800_bib0009","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.3390\/s21051559","article-title":"Iotcrawler: challenges and solutions for searching the Internet of Things","volume":"21","author":"Iggena","year":"2021","journal-title":"Sensors"},{"key":"10.1016\/j.knosys.2026.115800_bib0010","unstructured":"OpenAI, et al., GPT-4 Technical Report, 2024."},{"key":"10.1016\/j.knosys.2026.115800_bib0011","series-title":"Gemini: A Family of Highly Capable Multimodal Models","author":"Team","year":"2025"},{"key":"10.1016\/j.knosys.2026.115800_bib0012","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3633453","article-title":"Measuring GitHub copilot\u2019s impact on productivity","volume":"67","author":"Ziegler","year":"2024","journal-title":"Commun. ACM"},{"key":"10.1016\/j.knosys.2026.115800_bib0013","series-title":"Proceedings of the 20th ACM Asia Conference on Computer and Communications Security","first-page":"425","article-title":"SoK: the privacy paradox of large language models: advancements, privacy risks, and mitigation","author":"Shanmugarasa","year":"2025"},{"key":"10.1016\/j.knosys.2026.115800_bib0014","series-title":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","first-page":"1","article-title":"From words to Watts: benchmarking the energy costs of large language model inference","author":"Samsi","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0015","series-title":"NeurIPS 2024 Competition Track","article-title":"Edge-LLMs: edge-device large language model competition","author":"Liu","year":"2024"},{"key":"10.1016\/j.knosys.2026.115800_bib0016","series-title":"Proceedings of the Fifth Workshop on Data Management for End-To-End Machine Learning","first-page":"1","article-title":"Semantic enrichment of data for AI applications","author":"\u00d6zcan","year":"2021"},{"issue":"11","key":"10.1016\/j.knosys.2026.115800_bib0017","doi-asserted-by":"crossref","first-page":"5110","DOI":"10.3390\/app11115110","article-title":"Semantic web and knowledge graphs for industry 4.0","volume":"11","author":"Yahya","year":"2021","journal-title":"Appl. Sci."},{"issue":"4","key":"10.1016\/j.knosys.2026.115800_bib0018","first-page":"689","article-title":"Survey on complex ontology matching","volume":"11","author":"Thi\u00e9blin","year":"2020","journal-title":"Semant. Web"},{"key":"10.1016\/j.knosys.2026.115800_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.datak.2024.102325","article-title":"Explanation, semantics, and ontology","volume":"153","author":"Guizzardi","year":"2024","journal-title":"Data Knowl. Eng."},{"key":"10.1016\/j.knosys.2026.115800_bib0020","doi-asserted-by":"crossref","DOI":"10.23919\/JCN.2023.000006","article-title":"Towards 6G hyper-connectivity: vision, challenges, and key enabling technologies","author":"Lee","year":"2023","journal-title":"J. Commun. Netw."},{"issue":"1","key":"10.1016\/j.knosys.2026.115800_bib0021","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1038\/s41597-024-02956-3","article-title":"A general primer for data harmonization","volume":"11","author":"Cheng","year":"2024","journal-title":"Sci. data"},{"key":"10.1016\/j.knosys.2026.115800_bib0022","series-title":"Clinical Applications of Artificial Intelligence in Real-World Data","first-page":"51","article-title":"Data integration and harmonisation","author":"Moinat","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0023","series-title":"World Conference on Information Systems for Business Management","first-page":"491","article-title":"Survey of recent approaches in ontology matching","author":"Sawant","year":"2024"},{"issue":"1","key":"10.1016\/j.knosys.2026.115800_bib0024","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/S0098-3004(01)00018-8","article-title":"Domain ontologies for data sharing\u2013an example from environmental monitoring using field GIS","volume":"28","author":"Pundt","year":"2002","journal-title":"Comput. Geosci."},{"key":"10.1016\/j.knosys.2026.115800_bib0025","series-title":"Handbook of Model-Based Systems Engineering","first-page":"15","article-title":"Semantics, metamodels, and ontologies","author":"Sievers","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0026","series-title":"The Semantic Web-ISWC 2015: 14th International Semantic Web Conference, Bethlehem, PA, USA, October 11-15, 2015, Proceedings, Part I 14","first-page":"533","article-title":"General terminology induction in OWL","author":"Sazonau","year":"2015"},{"issue":"3","key":"10.1016\/j.knosys.2026.115800_bib0027","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s10817-014-9305-1","article-title":"HermiT: an OWL 2 reasoner","volume":"53","author":"Glimm","year":"2014","journal-title":"J. Automat. Reason."},{"key":"10.1016\/j.knosys.2026.115800_bib0028","series-title":"Proceedings of the 8th International Conference on the Internet of Things","article-title":"Ontology-based virtual IoT devices for edge computing","author":"Sahlmann","year":"2018"},{"key":"10.1016\/j.knosys.2026.115800_bib0029","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1007\/978-3-030-50436-6_23","article-title":"Ontology-driven edge computing","volume":"12143","author":"Ryabinin","year":"2020","journal-title":"Comput. Sci. \u2013 ICCS 2020"},{"key":"10.1016\/j.knosys.2026.115800_bib0030","series-title":"Raising the Role of Vocabulary Hubs for Semantic Data Interoperability in Dataspaces","author":"Davida","year":"2024"},{"key":"10.1016\/j.knosys.2026.115800_bib0031","series-title":"International Conference on Practical Applications of Agents and Multi-Agent Systems","first-page":"71","article-title":"Towards semantic modelling of the edge-cloud continuum","author":"Bernab\u00e9","year":"2022"},{"key":"10.1016\/j.knosys.2026.115800_bib0032","doi-asserted-by":"crossref","first-page":"2","DOI":"10.23919\/ETR.2021.9904675","article-title":"Data ingestion architecture for telecom applications","volume":"2021","author":"R\u00f6nnberg","year":"2021","journal-title":"Ericss. Technol. Rev."},{"key":"10.1016\/j.knosys.2026.115800_bib0033","series-title":"2023 IEEE International Conference on Big Data (BigData)","first-page":"4712","article-title":"Enabling dataspaces using foundation models: technical, legal and ethical considerations and future trends","author":"Timilsina","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0034","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.knosys.2026.115800_bib0035","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.knosys.2026.115800_bib0036","series-title":"2018 4th International Conference on Big Data Innovations and Applications (Innovate-Data)","first-page":"1","article-title":"Semantic data ingestion for intelligent, value-driven big data analytics","author":"Debattista","year":"2018"},{"key":"10.1016\/j.knosys.2026.115800_bib0037","series-title":"Companion Proceedings of the ACM Web Conference 2023","first-page":"1462","article-title":"Enhancing data space semantic interoperability through machine learning: a visionary perspective","author":"Boukhers","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0038","series-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","first-page":"1500","article-title":"Sherlock: a deep learning approach to semantic data type detection","author":"Hulsebos","year":"2019"},{"key":"10.1016\/j.knosys.2026.115800_bib0039","unstructured":"T. Mikolov, Efficient estimation of word representations in vector space, (2013). arXiv: 1301.3781."},{"key":"10.1016\/j.knosys.2026.115800_bib0040","series-title":"2018 IEEE 34th International Conference on Data Engineering (ICDE)","first-page":"989","article-title":"Seeping semantics: linking datasets using word embeddings for data discovery","author":"Fernandez","year":"2018"},{"issue":"1","key":"10.1016\/j.knosys.2026.115800_bib0041","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Transact. Neural Netw."},{"key":"10.1016\/j.knosys.2026.115800_bib0042","series-title":"Comprehending Semantic Types in JSON Data with Graph Neural Networks","author":"Wei","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0043","series-title":"2023 IEEE International Conference on Big Data (BigData)","first-page":"4997","article-title":"Knowledge graphs, clinical trials, dataspace, and AI: uniting for progressive healthcare innovation","author":"Timilsina","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0044","series-title":"2025 IEEE 8th International Conference on Industrial Cyber-Physical Systems (ICPS)","first-page":"1","article-title":"Towards a toolkit for semantic interoperability in data spaces","author":"Lam","year":"2025"},{"key":"10.1016\/j.knosys.2026.115800_bib0045","series-title":"2024 IEEE\/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)","first-page":"206","article-title":"TabLinkLLM: an LLM-based approach for entity linking in tabular data","author":"Jayawardene","year":"2024"},{"issue":"4","key":"10.1016\/j.knosys.2026.115800_bib0046","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1145\/27633.27634","article-title":"A comparative analysis of methodologies for database schema integration","volume":"18","author":"Batini","year":"1986","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"10.1016\/j.knosys.2026.115800_bib0047","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.254","article-title":"An approach for semantic integration of heterogeneous data sources","volume":"6","author":"Fusco","year":"2020","journal-title":"PeerJ Comput. Sci."},{"key":"10.1016\/j.knosys.2026.115800_bib0048","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","first-page":"1","article-title":"Human-in-the-loop schema induction","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.115800_bib0049","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1109\/JBHI.2022.3153259","article-title":"A comparison of wearable tonometry, photoplethysmography, and electrocardiography for cuffless measurement of blood pressure in an ambulatory setting","volume":"26","author":"Mieloszyk","year":"2022","journal-title":"IEEE J. Biomed. Health Informat."},{"key":"10.1016\/j.knosys.2026.115800_bib0050","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"10.1016\/j.knosys.2026.115800_bib0051","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.knosys.2026.115800_bib0052","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s41597-022-01411-5","article-title":"VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients","volume":"9","author":"Lee","year":"2022","journal-title":"Sci. Data"},{"key":"10.1016\/j.knosys.2026.115800_bib0053","series-title":"Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP","first-page":"250","article-title":"The lookahead limitation: why multi-operand addition is hard for LLMs","author":"Baeumel","year":"2025"},{"issue":"3","key":"10.1016\/j.knosys.2026.115800_bib0054","first-page":"1743","article-title":"Design of a data storage and retrieval ontology for the efficient integration of information in artificial intelligence systems","volume":"16","author":"Aman","year":"2024","journal-title":"Int. J. Inform. Technol."},{"key":"10.1016\/j.knosys.2026.115800_bib0055","unstructured":"G. Team, et al., Gemma 3 Technical Report, 2025."},{"key":"10.1016\/j.knosys.2026.115800_bib0056","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"1107","article-title":"A survey on in-context learning","author":"Dong","year":"2024"},{"key":"10.1016\/j.knosys.2026.115800_bib0057","doi-asserted-by":"crossref","DOI":"10.1145\/3490390","article-title":"MOTION - a framework for mixed-protocol multi-party computation","volume":"25","author":"Braun","year":"2022","journal-title":"ACM Trans. Priv. Secur."},{"key":"10.1016\/j.knosys.2026.115800_bib0058","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TBDATA.2024.3362191","article-title":"Decentralized federated learning: a survey on security and privacy","volume":"10","author":"Hallaji","year":"2024","journal-title":"IEEE Transact. Big Data"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005265?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005265?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:16:16Z","timestamp":1777569376000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126005265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":58,"alternative-id":["S0950705126005265"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115800","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LLM-based harmonized data ingestion for dataspace: a novel system for automating data ingestion across heterogeneous data sources","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115800","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"115800"}}