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


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <controlfield tag="005">20200124192512.0</controlfield>
  <controlfield tag="001">3403078</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="g">ASE</subfield>
    <subfield code="a">International Conference on Automated Software Engineering</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Carnegie Mellon University</subfield>
    <subfield code="a">Yin, Pengcheng</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Carnegie Mellon University Software Engineering Institute</subfield>
    <subfield code="a">Schwartz, Edward J.</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Microsoft Research</subfield>
    <subfield code="a">Allamanis, Miltiadis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Carnegie Mellon University</subfield>
    <subfield code="a">Le Goues, Claire</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Carnegie Mellon University</subfield>
    <subfield code="a">Neubig, Graham</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Carnegie Mellon University</subfield>
    <subfield code="a">Vasilescu, Bogdan</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">151230337</subfield>
    <subfield code="z">md5:f6f50e591e0b87286adf4037db5c5326</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/0-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">250808987</subfield>
    <subfield code="z">md5:b2b9e5b6d9804ee0dd5e512e2fb1b886</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/0-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">151843136</subfield>
    <subfield code="z">md5:22725b6a13a581fd11939d9f0d9755d2</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/1-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">251823084</subfield>
    <subfield code="z">md5:2b8ae5d693fad500f0fd0b59b50d8d81</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/1-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">156967905</subfield>
    <subfield code="z">md5:90d57fe8d1e0e7c5c965e29cce752388</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/2-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">259715957</subfield>
    <subfield code="z">md5:c80d48c918a1c7e8b60789691cda21cd</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/2-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">166775905</subfield>
    <subfield code="z">md5:d86ae421c9628b5fc6bdfe0b60bc8997</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/3-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">276902594</subfield>
    <subfield code="z">md5:03326d0d4300579efbd6e233be3b99bd</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/3-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">163880520</subfield>
    <subfield code="z">md5:e1448edff59ad43e81ca572ed5b9321c</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/4-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">271029988</subfield>
    <subfield code="z">md5:98cb8057b336d6cb8beea88de84fbac1</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/4-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">152969118</subfield>
    <subfield code="z">md5:236626301caa357b21806acc319b02e6</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/5-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">253704126</subfield>
    <subfield code="z">md5:9b4f94607335772b044c62d647aba6cf</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/5-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">264222818</subfield>
    <subfield code="z">md5:504a7bae05a79a1e9b417cdb24644ea7</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/6-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">150681017</subfield>
    <subfield code="z">md5:dbaed7f3096ed4a5ef90c5facf48be75</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/7-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">249912588</subfield>
    <subfield code="z">md5:b7347771c5ffd40d33857e66114d68ff</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/7-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">156188339</subfield>
    <subfield code="z">md5:bc480a2bee0bd3212937d512dd992c34</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/8-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">258967964</subfield>
    <subfield code="z">md5:c7672cc3575db9760da635f58d6e441d</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/8-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">157659741</subfield>
    <subfield code="z">md5:7e8c1d75838252154d76eec139e2e4d7</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/9-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">260969987</subfield>
    <subfield code="z">md5:ff8f29e381078c77bd3164138302ad0a</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/9-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">154214127</subfield>
    <subfield code="z">md5:8140925c954a99f925049633fb7a5a64</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/a-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">255339718</subfield>
    <subfield code="z">md5:d3b65c7aea71a146f0631c52f7424f05</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/a-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">155353559</subfield>
    <subfield code="z">md5:e6c3e05f761d996c2032a76169a018b6</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/b-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">257559022</subfield>
    <subfield code="z">md5:9d74988a8e928a9122166deb4a21e90c</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/b-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">163501721</subfield>
    <subfield code="z">md5:307a08acef47c35e5a489d5afab0ddcd</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/c-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">271945668</subfield>
    <subfield code="z">md5:05dc395dbf51303e1ef38e71f5249ca9</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/c-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">162543223</subfield>
    <subfield code="z">md5:f7ad3caabad2b0a2ec8e204ebde2e609</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/d-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">269678426</subfield>
    <subfield code="z">md5:1c666f3b20ba0403d5d0ec261ebc03b7</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/d-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">155956013</subfield>
    <subfield code="z">md5:89ab0e0fe48f283ec642e69ddddc8e35</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/e-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">257935192</subfield>
    <subfield code="z">md5:7b57706ec9a2948cc2ae3b45353090aa</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/e-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">150117126</subfield>
    <subfield code="z">md5:681666c06d9e43093fa4c50dbbfecb4a</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/f-trees.tar.bz2</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">249195409</subfield>
    <subfield code="z">md5:ae0ecd96ef96cccc0e2340f757d8bdcf</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/f-trees.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">935</subfield>
    <subfield code="z">md5:ce1c12d7b5072c540e1ffea48bd78e0b</subfield>
    <subfield code="u">https://zenodo.org/record/3403078/files/README</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-09-09</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:3403078</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Carnegie Mellon University</subfield>
    <subfield code="0">(orcid)0000-0003-0653-5738</subfield>
    <subfield code="a">Lacomis, Jeremy</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">DIRE: A Neural Approach to Decompiled Identifier Naming</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://opensource.org/licenses/MIT</subfield>
    <subfield code="a">MIT License</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;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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3403077</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3403078</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
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