There is a newer version of this record available.

Dataset Open Access

Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks

Saier, Tarek; Färber, Michael


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.2609187">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.2609187</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.2609187"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Saier, Tarek</foaf:name>
        <foaf:givenName>Tarek</foaf:givenName>
        <foaf:familyName>Saier</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Freiburg</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-5458-8645">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-5458-8645</dct:identifier>
        <foaf:name>Färber, Michael</foaf:name>
        <foaf:givenName>Michael</foaf:givenName>
        <foaf:familyName>Färber</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Freiburg</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2019</dct:issued>
    <dcat:keyword>scholarly data</dcat:keyword>
    <dcat:keyword>citations</dcat:keyword>
    <dcat:keyword>papers</dcat:keyword>
    <dcat:keyword>arXiv.org</dcat:keyword>
    <dcat:keyword>digital libraries</dcat:keyword>
    <dcat:keyword>dataset</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-02-01</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/2609187"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/2609187</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <foaf:page rdf:resource="http://ceur-ws.org/Vol-2345/paper2.pdf"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.2553522"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/bibliometrics"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/natural-language-processing"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/scholarly-data"/>
    <dct:description>&lt;p&gt;We propose a new data set based on &lt;strong&gt;all publications from all scientific fields available on arXiv.org&lt;/strong&gt;. Apart from providing the &lt;strong&gt;papers&amp;#39; plain text&lt;/strong&gt;, &lt;strong&gt;in-text citations&lt;/strong&gt; were annotated via global identifiers. As far as possible, cited publications were linked to the &lt;strong&gt;Microsoft Academic Graph&lt;/strong&gt;. Our data set consists of &lt;strong&gt;over one million documents&lt;/strong&gt; and &lt;strong&gt;29.2 million citation contexts&lt;/strong&gt;. The data set, which is made freely available for research purposes, not only can enhance the future evaluation of researchpaper-based and citation context-based approaches but also serve as a basis for novel ideas to analyze papers.&lt;/p&gt; &lt;p&gt;More information can be found in our paper &lt;a href="http://ceur-ws.org/Vol-2345/paper2.pdf"&gt;Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;See &lt;a href="https://github.com/IllDepence/unarXive"&gt;https://github.com/IllDepence/unarXive&lt;/a&gt; for the source code which has been used for creating the data set.&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.2609187"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.2609187"/>
        <dcat:byteSize>22891008306</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/2609187/files/arxiv_v2.1.tar.gz"/>
        <dcat:mediaType>application/x-tar</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
2,566
23,990
views
downloads
All versions This version
Views 2,566450
Downloads 23,99011,628
Data volume 490.4 TB266.2 TB
Unique views 2,059397
Unique downloads 2,897889

Share

Cite as