Technical note Open Access

A Dataset for GitHub Repository Deduplication: Extended Description

Spinellis, Diomidis; Kotti, Zoe; Mockus, Audris


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">deduplication</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">fork</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">project clone</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">GitHub</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
  <controlfield tag="005">20200421101104.0</controlfield>
  <controlfield tag="001">3740595</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Athens University of Economics and Business</subfield>
    <subfield code="0">(orcid)0000-0003-3816-9162</subfield>
    <subfield code="a">Kotti, Zoe</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Tennessee</subfield>
    <subfield code="a">Mockus, Audris</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1836423</subfield>
    <subfield code="z">md5:c3791f1707a97d5e3a25fe8bd662c165</subfield>
    <subfield code="u">https://zenodo.org/record/3740595/files/forkproj-extended.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-04-21</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:3740595</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Athens University of Economics and Business</subfield>
    <subfield code="0">(orcid)0000-0003-4231-1897</subfield>
    <subfield code="a">Spinellis, Diomidis</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">A Dataset for GitHub Repository Deduplication: Extended Description</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">825328</subfield>
    <subfield code="a">Fine-Grained Analysis of Software Ecosystems as Networks</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isSupplementTo</subfield>
    <subfield code="a">10.1145/3379597.3387496</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isCitedBy</subfield>
    <subfield code="a">10.1145/3379597.3387496</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">documents</subfield>
    <subfield code="a">10.5281/zenodo.3653924</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">documents</subfield>
    <subfield code="a">10.5281/zenodo.3653920</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3740594</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3740595</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">technicalnote</subfield>
  </datafield>
</record>
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