Technical note Open Access

A Dataset for GitHub Repository Deduplication: Extended Description

Spinellis, Diomidis; Kotti, Zoe; Mockus, Audris


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.3740595">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Text"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3740595</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3740595"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-4231-1897">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-4231-1897</dct:identifier>
        <foaf:name>Spinellis, Diomidis</foaf:name>
        <foaf:givenName>Diomidis</foaf:givenName>
        <foaf:familyName>Spinellis</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Athens University of Economics and Business</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-3816-9162">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-3816-9162</dct:identifier>
        <foaf:name>Kotti, Zoe</foaf:name>
        <foaf:givenName>Zoe</foaf:givenName>
        <foaf:familyName>Kotti</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Athens University of Economics and Business</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Mockus, Audris</foaf:name>
        <foaf:givenName>Audris</foaf:givenName>
        <foaf:familyName>Mockus</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Tennessee</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>A Dataset for GitHub Repository Deduplication: Extended Description</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">2020</dct:issued>
    <dcat:keyword>deduplication</dcat:keyword>
    <dcat:keyword>fork</dcat:keyword>
    <dcat:keyword>project clone</dcat:keyword>
    <dcat:keyword>GitHub</dcat:keyword>
    <dcat:keyword>dataset</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/825328/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-04-21</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3740595"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3740595</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://doi.org/10.1145/3379597.3387496"/>
    <dct:relation rdf:resource="https://doi.org/10.1145/3379597.3387496"/>
    <dct:relation rdf:resource="https://doi.org/10.5281/zenodo.3653924"/>
    <dct:relation rdf:resource="https://doi.org/10.5281/zenodo.3653920"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3740594"/>
    <dct:description>&lt;p&gt;GitHub projects can be easily replicated through the site&amp;#39;s fork&lt;br&gt; process or through a Git clone-push sequence.&amp;nbsp; This is a problem for&lt;br&gt; empirical software engineering, because it can lead to skewed results&lt;br&gt; or mistrained machine learning models.&amp;nbsp; We provide a dataset of 10.6&lt;br&gt; million GitHub projects that are copies of others, and link each record&lt;br&gt; with the project&amp;#39;s ultimate parent.&amp;nbsp; The ultimate parents were derived&lt;br&gt; from a ranking along six metrics.&amp;nbsp; The related projects were calculated&lt;br&gt; as the connected components of an 18.2 million node and 12 million&lt;br&gt; edge denoised graph created by directing edges to ultimate parents.&lt;br&gt; The graph was created by filtering out more than 30 hand-picked and 2.3&lt;br&gt; million pattern-matched clumping projects.&amp;nbsp; Projects that introduced&lt;br&gt; unwanted clumping were identified by repeatedly visualizing shortest path&lt;br&gt; distances between unrelated important projects.&amp;nbsp; Our dataset identified&lt;br&gt; 30 thousand duplicate projects in an existing popular reference dataset&lt;br&gt; of 1.8 million projects.&amp;nbsp; An evaluation of our dataset against another&lt;br&gt; created independently with different methods found a significant overlap,&lt;br&gt; but also differences attributed to the operational definition of what&lt;br&gt; projects are considered as related.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&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>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3740595"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.3740595</dcat:accessURL>
        <dcat:byteSize>1836423</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/3740595/files/forkproj-extended.pdf</dcat:downloadURL>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/825328/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">825328</dct:identifier>
    <dct:title>Fine-Grained Analysis of Software Ecosystems as Networks</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
351
179
views
downloads
All versions This version
Views 351351
Downloads 179179
Data volume 328.7 MB328.7 MB
Unique views 318318
Unique downloads 164164

Share

Cite as