<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04017152</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-21T15:14:14+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">TOWARDS A DATA QUALITY FRAMEWORK FOR EOSC Authorship Community</title>
            <author role="aut">
              <persName>
                <forename type="first">Carlo</forename>
                <surname>Lacagnina</surname>
              </persName>
              <idno type="halauthorid">2668599-0</idno>
              <affiliation ref="#struct-118313"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Romain</forename>
                <surname>David</surname>
              </persName>
              <email type="md5">2092020341e216e003ffca1cd4269c1a</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">romain-david</idno>
              <idno type="idhal" notation="numeric">11404</idno>
              <idno type="halauthorid" notation="string">45941-11404</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/ABH-8335-2020</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-4073-7456</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gI7BuJcAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/233679359</idno>
              <idno type="VIAF">https://viaf.org/viaf/1194155284793087060771</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/ABH-8335-2020</idno>
              <affiliation ref="#struct-1042333"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Anastasija</forename>
                <surname>Nikiforova</surname>
              </persName>
              <idno type="halauthorid">2523258-0</idno>
              <affiliation ref="#struct-545683"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mari-Elisa</forename>
                <surname>Kuusniemi</surname>
              </persName>
              <idno type="halauthorid">2747911-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Cinzia</forename>
                <surname>Cappiello</surname>
              </persName>
              <idno type="halauthorid">527923-0</idno>
              <affiliation ref="#struct-175236"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Oliver</forename>
                <surname>Biehlmaier</surname>
              </persName>
              <idno type="halauthorid">2747912-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Louise</forename>
                <surname>Wright</surname>
              </persName>
              <idno type="halauthorid">2747913-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Chris</forename>
                <surname>Schubert</surname>
              </persName>
              <idno type="halauthorid">2705825-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Andrea</forename>
                <surname>Bertino</surname>
              </persName>
              <idno type="halauthorid">41887-0</idno>
              <affiliation ref="#struct-203762"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hannes</forename>
                <surname>Thiemann</surname>
              </persName>
              <idno type="halauthorid">2747914-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Richard</forename>
                <surname>Dennis</surname>
              </persName>
              <idno type="halauthorid">2394236-0</idno>
              <affiliation ref="#struct-460939"/>
              <affiliation ref="#struct-556849"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Romain</forename>
                <surname>David</surname>
              </persName>
              <email type="md5">2092020341e216e003ffca1cd4269c1a</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projeurop-718358"/>
            <funder ref="#projeurop-713203"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-03-07 03:00:00</date>
              <date type="whenModified">2026-04-05 14:22:02</date>
              <date type="whenReleased">2023-03-30 10:56:44</date>
              <date type="whenProduced">2022-12-01</date>
              <date type="whenEndEmbargoed">2023-03-07</date>
              <ref type="file" target="https://hal.science/hal-04017152v1/document">
                <date notBefore="2023-03-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04017152v1/file/Towards_a_data_quality_framework_for_eosc_final%20%281%29.pdf" id="file-4017152-3498735">
                <date notBefore="2023-03-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="15685">
                <persName>
                  <forename>Romain</forename>
                  <surname>David</surname>
                </persName>
                <email type="md5">2092020341e216e003ffca1cd4269c1a</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04017152</idno>
            <idno type="halUri">https://hal.science/hal-04017152</idno>
            <idno type="halBibtex">lacagnina:hal-04017152</idno>
            <idno type="halRefHtml">EOSC Association. 2022</idno>
            <idno type="halRef">EOSC Association. 2022</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4017152-3498735"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNS">Conseil National du Sida</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="LARA">LARA</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">TOWARDS A DATA QUALITY FRAMEWORK FOR EOSC Authorship Community</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Carlo</forename>
                    <surname>Lacagnina</surname>
                  </persName>
                  <idno type="halauthorid">2668599-0</idno>
                  <affiliation ref="#struct-118313"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Romain</forename>
                    <surname>David</surname>
                  </persName>
                  <email type="md5">2092020341e216e003ffca1cd4269c1a</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">romain-david</idno>
                  <idno type="idhal" notation="numeric">11404</idno>
                  <idno type="halauthorid" notation="string">45941-11404</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/ABH-8335-2020</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-4073-7456</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=gI7BuJcAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/233679359</idno>
                  <idno type="VIAF">https://viaf.org/viaf/1194155284793087060771</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/ABH-8335-2020</idno>
                  <affiliation ref="#struct-1042333"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Anastasija</forename>
                    <surname>Nikiforova</surname>
                  </persName>
                  <idno type="halauthorid">2523258-0</idno>
                  <affiliation ref="#struct-545683"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mari-Elisa</forename>
                    <surname>Kuusniemi</surname>
                  </persName>
                  <idno type="halauthorid">2747911-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Cinzia</forename>
                    <surname>Cappiello</surname>
                  </persName>
                  <idno type="halauthorid">527923-0</idno>
                  <affiliation ref="#struct-175236"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Oliver</forename>
                    <surname>Biehlmaier</surname>
                  </persName>
                  <idno type="halauthorid">2747912-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Louise</forename>
                    <surname>Wright</surname>
                  </persName>
                  <idno type="halauthorid">2747913-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Chris</forename>
                    <surname>Schubert</surname>
                  </persName>
                  <idno type="halauthorid">2705825-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Andrea</forename>
                    <surname>Bertino</surname>
                  </persName>
                  <idno type="halauthorid">41887-0</idno>
                  <affiliation ref="#struct-203762"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hannes</forename>
                    <surname>Thiemann</surname>
                  </persName>
                  <idno type="halauthorid">2747914-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Richard</forename>
                    <surname>Dennis</surname>
                  </persName>
                  <idno type="halauthorid">2394236-0</idno>
                  <affiliation ref="#struct-460939"/>
                  <affiliation ref="#struct-556849"/>
                </author>
              </analytic>
              <monogr>
                <imprint>
                  <date type="datePub">2022-12-01</date>
                </imprint>
                <authority type="institution">EOSC Association</authority>
              </monogr>
              <idno type="doi">10.5281/zenodo.7515816</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">data quality assessment</term>
                <term xml:lang="en">quality dimension</term>
                <term xml:lang="en">EOSC Association</term>
                <term xml:lang="en">OpenScience</term>
                <term xml:lang="en">Advancing OpenScience in Europe</term>
                <term xml:lang="en">EOSC</term>
                <term xml:lang="en">HorizonEU</term>
                <term xml:lang="en">Standards</term>
                <term xml:lang="en">data quality</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="REPORT">Reports</classCode>
              <classCode scheme="halOldTypology" n="REPORT">Reports</classCode>
              <classCode scheme="halTreeTypology" n="REPORT">Reports</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The European Open Science Cloud (EOSC) Association leverages thirteen Task Forces (TFs), grouped into five Advisory Boards, to help steer the implementation of EOSC. This document is released by the Data Quality subgroup of the “FAIR Metrics and Data Quality” TF. Data quality is critical in ensuring the credibility, legitimacy, and actionability of resources within EOSC. Indeed, certification and conformity mechanisms must be established to assure researchers that the infrastructures they deposit and access data conform to clear rules and criteria. If researchers feel a loss of control and visibility or have concerns about how professionally their data will be managed, additional barriers to data sharing will emerge. Informed by the results of a systematic literature review and community consultation utilising surveys, presentations, and case studies, this TF identified key concepts and formulated recommendations. Let us start with a quick view of the critical concepts.Following the definition given by ISO 8000, with “data quality” we mean the degree to which a set of inherent characteristics of data fulfils requirements. Aligning actual data characteristics with the desired requirements implies that quality depends on context (both dataset application and lifecycle) and stakeholders, central elements in setting the requirements. Requirements must have a clear target aspect (e.g., privacy) and a level to reach (e.g., GDPR standard) and can be distinguished into functional (targeting the question “are you producing the right thing for its application?") and non-functional (targeting the question "are you producing it right?”). The goal of data quality management is to ensure that: (i) valuable information to understand the dataset is available, (ii) the dataset is reliable and ready to be used according to non-functional requirements (fit-for-use), and (iii) the dataset meets functional requirements (fit-for-purpose) when the purpose is known; if the purpose is unknown, data quality management ensures that the information necessary for users to make self-assessments of fitness-for-purpose is available. Note that in a FAIR ecosystem, where datasets could be reused far from the original purpose, information about the intended new purpose and associated functional requirements is limited.This document explains basic concepts to build a solid basis for a mutual understanding of data quality in a multidisciplinary environment. These range from the difference between quality control, assurance, and management to categories of quality dimensions, as well as typical approaches and workflows to curate and disseminate dataset quality information, minimum requirements, indicators, certification, and vocabulary. These concepts are explored considering the importance of evaluating resources carefully when deciding the sophistication of the quality assessments. Human resources, technology capabilities, and capacity-building plans constrain the design of sustainable solutions.We identified several benefits (or risks) of having good (or poor) quality and which are the stakeholders impacted. Despite these benefits, barriers and concerns prevent the provision of quality-assessed datasets, we identified these issues in detail.Distilling the knowledge accumulated in this Task Force, we extracted cross-domain commonalities, lessons learned, and challenges. The resulting main recommendations are:Data quality assessment needs standards to check data against; unfortunately, not all communities have agreed on standards, so EOSC should assist and push each community to agree on community standards to guarantee the FAIR exchange of research data. Although we extracted a few examples highlighting this gap, the current situation requires a more detailed and systematic evaluation in each community. Establishing a quality management function can help in this direction because the process can identify which standard already in use by some initiatives can be enforced as a general requirement for that community. We recommend that EOSC considers taking the opportunity to encourage communities to reach a consensus in using their standards.Data in EOSC need to be served with enough information for the user to understand how to read and correctly interpret the dataset, what restrictions are in place to use it, and what processes participate in its production. EOSC should ensure that the dataset is structured and documented in a way that can be (re)used and understood. Quality assessments in EOSC should not be concerned with checking the soundness of the data content. Aspects like uncertainty are also important to properly (re)use a dataset. Still, these aspects must be evaluated outside the EOSC ecosystem, which only checks that evidence about data content assessments is available. Following stakeholders’ expectations, we recommend that EOSC is equipped with essential data quality management, i.e., it should perform tasks like controlling the availability of basic metadata and documentation and performing basic metadata compliance checks. The EOSC quality management should not change data but point to deficiencies that the data provider or producer can address.Errors found by the curators or users need to be rectified by the data producer/provider. If not possible, errors need to be documented. Improving data quality as close to the source (i.e., producer or provider) as possible is highly recommended. Quality assessments conducted in EOSC should be shown first to the data provider to give a chance to improve the data and then to the users.User engagement is necessary to understand the user requirements (needs, expectations, etc.); it may or may not be part of a quality management function. Determining and evaluating stakeholder needs is not a one-time requirement but a continuous and collaborative part of the service delivery process.It is recommended to develop a proof-of-concept quality function performing basic quality assessments tailored to the EOSC needs (e.g., data reliability and usability). These assessments can also support rewarding research teams most committed to providing FAIR datasets. The proof-of-concept function cannot be a theoretical conceptualization of what is preferable in terms of quality. Still, it must be constrained by the reality of dealing with an enormous amount of data within a reasonable time and workforce.Data quality is a concern for all stakeholders, detailed further in this document. The quality assessments must be a multi-actor process between the data provider, EOSC, and users, potentially extended to other actors in the long run. The resulting content of quality assessments should be captured in structured, human- and machine-readable, and standard-based formats. Dataset information must be easily comparable across similar products, which calls for providing homogeneous quality information.A number of requirements valid for all datasets in EOSC (and beyond) and specific aspects of a maturity matrix gauging the maturity of a community when dealing with quality have been defined. Further refinement will be necessary for the future, and specific standards to follow will need to be identified.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-118313" status="VALID">
          <orgName>Barcelona Supercomputing Center - Centro Nacional de Supercomputacion</orgName>
          <orgName type="acronym">BSC-CNS</orgName>
          <desc>
            <address>
              <addrLine>Plaça d'Eusebi Güell, 1-3, Les Corts, 08034 Barcelona</addrLine>
              <country key="ES"/>
            </address>
            <ref type="url">http://www.bsc.es/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1042333" status="VALID">
          <orgName>European Research Infrastructure on Highly Pathogenic Agents</orgName>
          <orgName type="acronym">ERINHA-AISBL</orgName>
          <desc>
            <address>
              <addrLine>98, rue du Trône B-1050 Bruxelles</addrLine>
              <country key="BE"/>
            </address>
            <ref type="url">https://www.erinha.eu/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-545683" status="VALID">
          <orgName>Institute of Computer Science [University of Tartu, Estonie]</orgName>
          <desc>
            <address>
              <addrLine>Liivi 2, 50409, Tartu, Estonia</addrLine>
              <country key="EE"/>
            </address>
            <ref type="url">https://www.cs.ut.ee/en</ref>
          </desc>
          <listRelation>
            <relation active="#struct-164370" type="direct"/>
            <relation active="#struct-1186412" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-175236" status="VALID">
          <orgName>Dipartimento di Elettronica e Informazione</orgName>
          <orgName type="acronym">DEI</orgName>
          <desc>
            <address>
              <addrLine>Via Ponzio 34/5 20133 Milano</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">http://www.dei.polimi.it/index.php?&amp;idlang=eng</ref>
          </desc>
          <listRelation>
            <relation active="#struct-125443" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-203762" status="VALID">
          <orgName>Göttingen State and University Library</orgName>
          <orgName type="acronym">SUB Göttingen</orgName>
          <desc>
            <address>
              <addrLine>Platz der Göttinger Sieben 1 37073 Göttingen</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.sub.uni-goettingen.de</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1065644" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-460939" status="VALID">
          <idno type="IdRef">026458748</idno>
          <idno type="ROR">https://ror.org/035b05819</idno>
          <orgName>Københavns Universitet = University of Copenhagen = Université de Copenhague</orgName>
          <orgName type="acronym">UCPH</orgName>
          <date type="start">1479-01-01</date>
          <desc>
            <address>
              <addrLine>Nørregade 10, 1165 København, Danemark</addrLine>
              <country key="DK"/>
            </address>
            <ref type="url">http://www.ku.dk</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-556849" status="INCOMING">
          <orgName>Royal Danish Library</orgName>
          <desc>
            <address>
              <country key="DK"/>
            </address>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-164370" status="VALID">
          <orgName>Faculty of Science and Technology [University of Tartu]</orgName>
          <desc>
            <address>
              <addrLine>51014; Tartu</addrLine>
              <country key="EE"/>
            </address>
            <ref type="url">https://ut.ee/en/content/structure</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1186412" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1186412" status="VALID">
          <idno type="ISNI">0000000109437661</idno>
          <idno type="ROR">https://ror.org/03z77qz90</idno>
          <idno type="Wikidata">Q204181</idno>
          <orgName>Tartu Ülikool = University of Tartu [Estonie]</orgName>
          <desc>
            <address>
              <addrLine>Ülikooli tn 18, 50090 Tartu</addrLine>
              <country key="EE"/>
            </address>
            <ref type="url">https://ut.ee</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-125443" status="VALID">
          <idno type="ISNI">0000 0004 1937 0327</idno>
          <idno type="ROR">https://ror.org/01nffqt88</idno>
          <orgName>Politecnico di Milano [Milan]</orgName>
          <orgName type="acronym">POLIMI</orgName>
          <desc>
            <address>
              <addrLine>Piazza Leonardo da Vinci, 32 20133 Milano</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">https://www.polimi.it/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1065644" status="VALID">
          <idno type="ROR">https://ror.org/01y9bpm73</idno>
          <orgName>Georg-August-University of Goettingen = Georg-August-Universität Göttingen</orgName>
          <desc>
            <address>
              <addrLine>Wilhelmsplatz 1, 37073 Göttingen, Allemagne</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.uni-goettingen.de/en/1.html</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="europeanProject" xml:id="projeurop-718358" status="INCOMING">
          <orgName>EOSC Association</orgName>
          <desc>EOSC Association</desc>
        </org>
        <org type="europeanProject" xml:id="projeurop-713203" status="VALID">
          <idno type="number">824087</idno>
          <idno type="program">H2020-INFRAEOSC-2018-2020</idno>
          <idno type="call">H2020-INFRAEOSC-2018-2</idno>
          <orgName>EOSC-Life</orgName>
          <desc>Providing an open collaborative space for digital biology in Europe</desc>
          <date type="start">2019-03-01</date>
          <date type="end">2023-08-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>