January 5, 2022 Dataset Open Access

Anonymous Authors

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.5822884</identifier>
  <creators>
    <creator>
      <creatorName>Anonymous Authors</creatorName>
      <affiliation>Anonymous</affiliation>
    </creator>
  </creators>
  <titles>
    <title>The Clarity Software Documentation Dataset</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2022</publicationYear>
  <subjects>
    <subject>Software Documentation</subject>
    <subject>Android</subject>
    <subject>Screenshots</subject>
    <subject>Captions</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2022-01-05</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/5822884</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.5821839</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
  </descriptions>
</resource>