{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T08:05:26Z","timestamp":1761552326774,"version":"build-2065373602"},"reference-count":44,"publisher":"Ubiquity Press, Ltd.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,1]]},"DOI":"10.5334\/dsj-2023-005","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:55:55Z","timestamp":1677660955000},"source":"Crossref","is-referenced-by-count":2,"title":["Scaling Identifiers and their Metadata to Gigascale: An Architecture to Tackle the Challenges of Volume and Variety"],"prefix":"10.5334","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5911-6022","authenticated-orcid":false,"given":"Jens","family":"Klump","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2257-9127","authenticated-orcid":false,"given":"Doug","family":"Fils","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0870-3192","authenticated-orcid":false,"given":"Anusuriya","family":"Devaraju","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1135-5942","authenticated-orcid":false,"given":"Sarah","family":"Ramdeen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4553-9697","authenticated-orcid":false,"given":"Jess","family":"Robertson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5976-4943","authenticated-orcid":false,"given":"Lesley","family":"Wyborn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7036-1977","authenticated-orcid":false,"given":"Kerstin","family":"Lehnert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3285","reference":[{"key":"key20230301085551_B1","unstructured":"Albertoni, R, Browning, D, Cox, SJD, Gonzalez-Beltran, A, Perego, A and Winstanley, P. 2021. Data Catalog Vocabulary (DCAT) - Version 3 (W3C Proposed Recommendation). Cambridge, MA: World Wide Web Consortium (W3C). Available at https:\/\/www.w3.org\/TR\/vocab-dcat-3\/."},{"key":"key20230301085551_B2","first-page":"45","article-title":"When is it sensible not to use XML?","volume":"4","year":"2010","journal-title":"Earth Science Informatics"},{"key":"key20230301085551_B3","unstructured":"Berners-Lee, T. 2009. Linked Data. W3C Design Issues. Available at https:\/\/www.w3.org\/DesignIssues\/LinkedData.html [Last accessed 29 October 2021]."},{"journal-title":"DataCite Blog","article-title":"Partnership between IGSN and DataCite","year":"2021","key":"key20230301085551_B4"},{"issue":"1","key":"key20230301085551_B5","first-page":"1","article-title":"Connected research: The potential of the PID graph","volume":"2","year":"2021","journal-title":"Patterns"},{"issue":"1","key":"key20230301085551_B6","doi-asserted-by":"crossref","first-page":"11","DOI":"10.5334\/dsj-2021-011","article-title":"Sample identifiers and metadata to support data management and reuse in multidisciplinary ecosystem sciences","volume":"20","year":"2021","journal-title":"Data Science Journal"},{"issue":"giab028","key":"key20230301085551_B7","article-title":"Internet of samples (iSamples): Toward an interdisciplinary cyberinfrastructure for material samples","volume":"10","year":"2021","journal-title":"GigaScience"},{"issue":"2","key":"key20230301085551_B8","doi-asserted-by":"crossref","first-page":"21","DOI":"10.3390\/publications8020021","article-title":"FAIR digital objects for science: From data pieces to actionable knowledge units","volume":"8","year":"2020","journal-title":"Publications"},{"issue":"11","key":"key20230301085551_B9","doi-asserted-by":"crossref","first-page":"100370","DOI":"10.1016\/j.patter.2021.100370","article-title":"An automated solution for measuring the progress toward FAIR research data","volume":"2","year":"2021","journal-title":"Patterns"},{"issue":"5","key":"key20230301085551_B10","article-title":"iTools: A framework for classification, categorization and integration of computational biology resources","volume":"3","year":"2008","journal-title":"PLoS ONE"},{"edition":"2nd ed.","volume-title":"The search for the perfect language","year":"1997","key":"key20230301085551_B11"},{"key":"key20230301085551_B12","unstructured":"Fils, D. 2021. gleanerio\/gleaner-compose. Available at https:\/\/github.com\/gleanerio\/gleaner-compose [Last accessed 25 June 2021]."},{"year":"2020","key":"key20230301085551_B13","article-title":"Connecting data to the physical world: IGSN 2040 sprint outcomes and recommendations (Technical Report)"},{"issue":"6","key":"key20230301085551_B14","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1127\/metz\/2020\/1042","article-title":"A short guide to increase FAIRness of atmospheric model data","volume":"29","year":"2020","journal-title":"Meteorologische Zeitschrift"},{"issue":"16","key":"key20230301085551_B15","article-title":"Building a disciplinary, world-wide data infrastructure","volume":"16","year":"2017","journal-title":"Data Science Journal"},{"key":"key20230301085551_B16","unstructured":"Guha, R. 2011. Official Google blog: Introducing schema.org: Search engines come together for a richer Web. Google Blog. Available at https:\/\/googleblog.blogspot.com\/2011\/06\/introducing-schemaorg-search-engines.html [Last accessed 3 July 2020]."},{"issue":"1","key":"key20230301085551_B17","first-page":"9","article-title":"The modular SSN ontology: A joint W3C and OGC standard specifying the semantics of sensors, observations, sampling, and actuation","volume":"10","year":"2019","journal-title":"Semantic Web"},{"key":"key20230301085551_B18","article-title":"A choice of persistent identifier schemes for the Distributed System of Scientific Collections (DiSSCo)","volume":"7","year":"2021","journal-title":"Research Ideas and Outcomes"},{"year":"2021","key":"key20230301085551_B19","article-title":"Science-on-Schema.org v1.2.0"},{"issue":"9","key":"key20230301085551_B20","first-page":"1","article-title":"20 years of persistent identifiers \u2013 Which systems are here to stay?","volume":"16","year":"2017","journal-title":"Data Science Journal"},{"issue":"33","key":"key20230301085551_B21","first-page":"1","article-title":"Towards globally unique identification of physical samples: Governance and technical implementation of the IGSN global sample number","volume":"20","year":"2021","journal-title":"Data Science Journal"},{"year":"2020","key":"key20230301085551_B22"},{"key":"key20230301085551_B23","unstructured":"Laney, D. 2001. 3D Data Management (No. 949). Stamford, CT: META Group. Available at https:\/\/web.archive.org\/web\/20120806062002\/http:\/\/blogs.gartner.com\/doug-laney\/files\/2012\/01\/ad949-3D-Data-Management-Controlling-Data-Volume-Velocity-and-Variety.pdf."},{"issue":"1\u20132","key":"key20230301085551_B24","first-page":"122","article-title":"FAIR data and services in biodiversity science and geoscience","volume":"2","year":"2019","journal-title":"Data Intelligence"},{"first-page":"SF32A","article-title":"SESAR: Addressing the need for unique sample identification in the Solid Earth Sciences","year":"2004","key":"key20230301085551_B25"},{"journal-title":"Zenodo","article-title":"IGSN 2040 Summary Report: Defining the Future of the IGSN as a Global Persistent Identifier for Material Samples","year":"2021","key":"key20230301085551_B26"},{"key":"key20230301085551_B27","unstructured":"Lidwell, W, Holden, K and Butler, J. 2010. Universal Principles of Design, Revised and Updated. 2nd ed. Beverley, MA: Rockport Publishers. Available at https:\/\/learning.oreilly.com\/library\/view\/universal-principles-of\/9781592535873\/."},{"first-page":"IN31B","article-title":"Project 418: A Funded Project of the EarthCube Science Support Office","year":"2018","key":"key20230301085551_B28"},{"key":"key20230301085551_B29","article-title":"Bioschemas & Schema.org: a Lightweight Semantic Layer for Life Sciences Websites","volume":"2","author":"The Bioschemas Community","year":"2018","journal-title":"Biodiversity Information Science and Standards"},{"issue":"10","key":"key20230301085551_B30","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1007\/s10822-014-9776-5","article-title":"DataCite and DOI names for research data","volume":"28","year":"2014","journal-title":"Journal of Computer-Aided Molecular Design"},{"key":"key20230301085551_B31","unstructured":"Noy, N and Brickley, D. 2017. Facilitating the discovery of public datasets. Google AI Blog. Available at http:\/\/ai.googleblog.com\/2017\/01\/facilitating-discovery-of-public.html [Last accessed 3 March 2020]."},{"key":"key20230301085551_B32","doi-asserted-by":"crossref","first-page":"101400","DOI":"10.1016\/j.gsf.2022.101400","article-title":"The evolution of a geoscience standard: An instructive tale of science keyword development and adoption","year":"2022","journal-title":"Geoscience Frontiers"},{"issue":"46","key":"key20230301085551_B33","first-page":"8","article-title":"Going digital: Persistent identifiers for research samples, resources and instruments","volume":"19","year":"2020","journal-title":"Data Science Journal"},{"key":"key20230301085551_B34","unstructured":"Robertson, JC, Fils, D, Devaraju, A, Song, L, Ramdeen, S and Klump, J. 2020. IGSN\/igsn-json: Test schema repo for IGSN 2040 Architecture sprint. Available at https:\/\/github.com\/IGSN\/igsn-json [Last accessed 10 November 2022]."},{"year":"2020","key":"key20230301085551_B35","article-title":"FAIMS 3.0: Electronic Field Notebooks"},{"key":"key20230301085551_B36","unstructured":"Schindler, U and Devaraju, A. 2020. MARUM DIS IGSN landing page mockup implementation. Available at https:\/\/github.com\/pangaea-data-publisher\/marum-dis-igsn [Last accessed 10 November 2022]."},{"year":"2021","key":"key20230301085551_B37"},{"first-page":"IN31B","article-title":"Facilitating data discovery on the internet using sitemaps.org and schema.org dataset metadata through the Environmental Data Initiative Data Portal","year":"2018","key":"key20230301085551_B38"},{"key":"key20230301085551_B39","unstructured":"sitemaps.org. 2006. What are Sitemaps? Available at https:\/\/www.sitemaps.org\/ [Last accessed 12 July 2021]."},{"key":"key20230301085551_B40","first-page":"1","article-title":"Bird\u2019s eye view on \u201cbig data management.\u201d","volume-title":"2014 Conference on IT in Business, Industry and Government (CSIBIG)","year":"2014"},{"key":"key20230301085551_B41","article-title":"20 GB in 10 minutes: A case for linking major biodiversity databases using an open socio-technical infrastructure and a pragmatic, cross-institutional collaboration","volume":"4","year":"2018","journal-title":"PeerJ Computer Science"},{"issue":"1","key":"key20230301085551_B42","doi-asserted-by":"crossref","first-page":"54","DOI":"10.5334\/dsj-2019-054","article-title":"Proper attribution for curation and maintenance of research collections: Metadata recommendations of the RDA\/TDWG Working Group","volume":"18","year":"2019","journal-title":"Data Science Journal"},{"issue":"12","key":"key20230301085551_B43","first-page":"18","article-title":"Resource harvesting within the OAI-PMH framework","volume":"10","year":"2004","journal-title":"D-Lib Magazine"},{"key":"key20230301085551_B44","doi-asserted-by":"crossref","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR Guiding Principles for scientific data management and stewardship","volume":"3","year":"2016","journal-title":"Scientific Data"}],"container-title":["Data Science Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/storage.googleapis.com\/jnl-up-j-dsj-files\/journals\/1\/articles\/1490\/submission\/proof\/1490-1-11228-1-10-20230301.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T07:56:00Z","timestamp":1761551760000},"score":1,"resource":{"primary":{"URL":"http:\/\/datascience.codata.org\/articles\/10.5334\/dsj-2023-005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"alternative-id":["10.5334\/dsj-2023-005"],"URL":"https:\/\/doi.org\/10.5334\/dsj-2023-005","relation":{},"ISSN":["1683-1470"],"issn-type":[{"type":"electronic","value":"1683-1470"}],"subject":[],"published":{"date-parts":[[2023]]},"article-number":"5"}}