Conference paper Open Access

Big Data Bags: A Scalable Packaging Format for Science

D'Arcy, Mike; Chard, Kyle; Foster, Ian; Kesselman, Carl; Madduri, Ravi; Saint, Nickolaus; Wagner, Rick


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: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.3338725">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Text"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3338725</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3338725"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>D'Arcy, Mike</foaf:name>
        <foaf:givenName>Mike</foaf:givenName>
        <foaf:familyName>D'Arcy</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Southern California</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>Chard, Kyle</foaf:name>
        <foaf:givenName>Kyle</foaf:givenName>
        <foaf:familyName>Chard</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Chicago</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>Foster, Ian</foaf:name>
        <foaf:givenName>Ian</foaf:givenName>
        <foaf:familyName>Foster</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Chicago</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>Kesselman, Carl</foaf:name>
        <foaf:givenName>Carl</foaf:givenName>
        <foaf:familyName>Kesselman</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Southern California</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>Madduri, Ravi</foaf:name>
        <foaf:givenName>Ravi</foaf:givenName>
        <foaf:familyName>Madduri</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Chicago</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>Saint, Nickolaus</foaf:name>
        <foaf:givenName>Nickolaus</foaf:givenName>
        <foaf:familyName>Saint</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Chicago</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>Wagner, Rick</foaf:name>
        <foaf:givenName>Rick</foaf:givenName>
        <foaf:familyName>Wagner</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Chicago</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Big Data Bags: A Scalable Packaging Format for Science</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">2019-07-17</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3338725"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3338725</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3338724"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/ro"/>
    <dct:description>&lt;p&gt;The need to describe and exchange large and complex data underlies the vast majority of science conducted today. Such needs arise when downloading data from a repository, moving data between remote locations, exchanging data between collaborators, and even publishing data as part of the publication process. While such examples are common, it is surprisingly difficult to describe and exchange data, and it is even more difficult when datasets are large and span multiple storage locations. To address some of these challenges we proposed the Big Data Bag (BDBag)&amp;nbsp;as a data packaging format for representing and describing complex, distributed, and large datasets. In this presentation, we outline the BDBag model and describe three scenarios in which it is currently being used&lt;/p&gt;</dct:description>
    <dct:description>Preprint submitted to RO2019 workshop at IEEE eScience Conference 2019</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:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3338725"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.3338725</dcat:accessURL>
        <dcat:byteSize>123755</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/3338725/files/bdbag.pdf</dcat:downloadURL>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
101
144
views
downloads
All versions This version
Views 101101
Downloads 144144
Data volume 17.8 MB17.8 MB
Unique views 8787
Unique downloads 132132

Share

Cite as