Dataset Open Access

DIRE: A Neural Approach to Decompiled Identifier Naming

Lacomis, Jeremy; Yin, Pengcheng; Schwartz, Edward J.; Allamanis, Miltiadis; Le Goues, Claire; Neubig, Graham; Vasilescu, Bogdan


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:cnt="http://www.w3.org/2011/content#" 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.3403078">
    <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.3403078</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3403078"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-0653-5738">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Lacomis, Jeremy</foaf:name>
        <foaf:givenName>Jeremy</foaf:givenName>
        <foaf:familyName>Lacomis</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carnegie Mellon University</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>Yin, Pengcheng</foaf:name>
        <foaf:givenName>Pengcheng</foaf:givenName>
        <foaf:familyName>Yin</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carnegie Mellon University</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>Schwartz, Edward J.</foaf:name>
        <foaf:givenName>Edward J.</foaf:givenName>
        <foaf:familyName>Schwartz</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carnegie Mellon University Software Engineering Institute</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>Allamanis, Miltiadis</foaf:name>
        <foaf:givenName>Miltiadis</foaf:givenName>
        <foaf:familyName>Allamanis</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Microsoft Research</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>Le Goues, Claire</foaf:name>
        <foaf:givenName>Claire</foaf:givenName>
        <foaf:familyName>Le Goues</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carnegie Mellon University</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>Neubig, Graham</foaf:name>
        <foaf:givenName>Graham</foaf:givenName>
        <foaf:familyName>Neubig</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carnegie Mellon University</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>Vasilescu, Bogdan</foaf:name>
        <foaf:givenName>Bogdan</foaf:givenName>
        <foaf:familyName>Vasilescu</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carnegie Mellon University</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>DIRE: A Neural Approach to Decompiled Identifier Naming</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>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-09-09</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3403078"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3403078</skos:notation>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3403077"/>
    <dct:description>&lt;p&gt;This dataset is released as a companion to the paper &amp;quot;DIRE: A Neural Approach to Decompiled Identifier Naming&amp;quot;, appearing in the proceedings of the&amp;nbsp;34th IEEE/ACM International Conference on Automated Software Engineering (ASE 2019).&lt;/p&gt; &lt;p&gt;It contains information generated by decompiling 3,195,962 functions found in 164,632 unique binaries generated from C code scraped from GitHub. For practicality, the dataset is partitioned into 16 archives by the first hexadecimal digit of the SHA-256 hash of the binary used to generate it. Each of the 16 archives contains approximately 10,000&amp;nbsp;JSONL files, named according to a binary&amp;#39;s hash. Each JSONL file consists of a single JSON object per-line corresponding to a single function in the decompiled binary.&lt;/p&gt; &lt;p&gt;Archives are provided in both GZIP and BZIP2 format.&lt;/p&gt; &lt;p&gt;See the README file for more information.&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:rights>
          <dct:RightsStatement rdf:about="https://opensource.org/licenses/MIT">
            <rdfs:label>MIT License</rdfs:label>
          </dct:RightsStatement>
        </dct:rights>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3403078"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
546
5,059
views
downloads
All versions This version
Views 546546
Downloads 5,0595,059
Data volume 846.1 GB846.1 GB
Unique views 482482
Unique downloads 347347

Share

Cite as