Dataset Open Access

The Clarity Software Documentation Dataset

Anonymous Authors


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Software Documentation</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Android</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Screenshots</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Captions</subfield>
  </datafield>
  <controlfield tag="005">20220106014851.0</controlfield>
  <controlfield tag="001">5822884</controlfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">12328146854</subfield>
    <subfield code="z">md5:b0017a0ed1495c5942c33835889172fa</subfield>
    <subfield code="u">https://zenodo.org/record/5822884/files/Clarity-Data.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1493</subfield>
    <subfield code="z">md5:34d826f7f0a64d475eb88d4e6736294a</subfield>
    <subfield code="u">https://zenodo.org/record/5822884/files/README.md</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-01-05</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:5822884</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Anonymous</subfield>
    <subfield code="a">Anonymous Authors</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">The Clarity Software Documentation Dataset</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;This repository holds the Clarity Dataset which is a companion to the SANER&amp;#39;22 entitled &amp;quot;An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation&amp;quot;. The dataset consists of 45,998 captions&amp;nbsp;10,204 GUI screenshots and xml metadata files (akin to the &amp;quot;html&amp;quot; for stipulating GUIs)&amp;nbsp;of Android applications.&amp;nbsp;The NL captions were obtained from human labelers, underwent several quality control mechanisms, and contain both high- (screen-level) and low-(component)&amp;nbsp;level descriptions of screen functionality. This dataset is meant as a new source of data to augment techniques for software documentation that can take advantage of the rich pixel-based information contained within screenshots.&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.5821839</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.5822884</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
81
18
views
downloads
All versions This version
Views 8170
Downloads 1815
Data volume 123.3 GB86.3 GB
Unique views 6759
Unique downloads 1411

Share

Cite as