<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01093188</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-19T08:09:46+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">LiveRank: How to Refresh Old Crawls</title>
            <author role="aut">
              <persName>
                <forename type="first">The Dang</forename>
                <surname>Huynh</surname>
              </persName>
              <idno type="halauthorid">631994-0</idno>
              <affiliation ref="#struct-160294"/>
              <affiliation ref="#struct-104763"/>
              <affiliation ref="#struct-34120"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Fabien</forename>
                <surname>Mathieu</surname>
              </persName>
              <email type="md5">216b51218f7e2d57be3828f43e6f6391</email>
              <email type="domain">normalesup.org</email>
              <ptr type="url" target="https://balouf.github.io/"/>
              <idno type="idhal" notation="string">fabien-mathieu</idno>
              <idno type="idhal" notation="numeric">446</idno>
              <idno type="halauthorid" notation="string">21677-446</idno>
              <idno type="IDREF">https://www.idref.fr/088099849</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1362-0359</idno>
              <affiliation ref="#struct-160294"/>
              <affiliation ref="#struct-104763"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Laurent</forename>
                <surname>Viennot</surname>
              </persName>
              <email type="md5">6bc2ca7e27f9b949929655afb8df6627</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">laurentviennot</idno>
              <idno type="idhal" notation="numeric">1841</idno>
              <idno type="halauthorid" notation="string">16606-1841</idno>
              <idno type="IDREF">https://www.idref.fr/034781072</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3657-6979</idno>
              <affiliation ref="#struct-160294"/>
              <affiliation ref="#struct-34120"/>
              <affiliation ref="#struct-1033"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Laurent</forename>
                <surname>Viennot</surname>
              </persName>
              <email type="md5">6bc2ca7e27f9b949929655afb8df6627</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2014-12-10 12:08:39</date>
              <date type="whenModified">2026-01-19 16:46:18</date>
              <date type="whenReleased">2014-12-15 14:06:12</date>
              <date type="whenProduced">2014-12-17</date>
              <date type="whenEndEmbargoed">2014-12-15</date>
              <ref type="file" target="https://inria.hal.science/hal-01093188v1/document">
                <date notBefore="2014-12-15"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01093188v1/file/liverank2014waw.pdf" id="file-1093188-1175751">
                <date notBefore="2014-12-15"/>
              </ref>
              <ref type="externalLink" target="https://hal.inria.fr/hal-01093188/file/liverank2014waw.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="102589">
                <persName>
                  <forename>Laurent</forename>
                  <surname>Viennot</surname>
                </persName>
                <email type="md5">6bc2ca7e27f9b949929655afb8df6627</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01093188</idno>
            <idno type="halUri">https://inria.hal.science/hal-01093188</idno>
            <idno type="halBibtex">huynh:hal-01093188</idno>
            <idno type="halRefHtml">&lt;i&gt;Algorithms and Models for the Web Graph - 11th International Workshop (WAW 2014)&lt;/i&gt;, Dec 2014, Beijing, China. pp.148 - 160, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-319-13123-8_12"&gt;&amp;#x27E8;10.1007/978-3-319-13123-8_12&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Algorithms and Models for the Web Graph - 11th International Workshop (WAW 2014), Dec 2014, Beijing, China. pp.148 - 160, &amp;#x27E8;10.1007/978-3-319-13123-8_12&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1093188-1175751"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS7" corresp="UNIV-PARIS">Université Denis Diderot - Paris VII</idno>
            <idno type="stamp" n="UPMC" corresp="SORBONNE-UNIVERSITE">Université Pierre et Marie Curie</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="SU-SCI" corresp="SORBONNE-UNIVERSITE">Sciences - Sorbonne Université</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">LiveRank: How to Refresh Old Crawls</title>
                <author role="aut">
                  <persName>
                    <forename type="first">The Dang</forename>
                    <surname>Huynh</surname>
                  </persName>
                  <idno type="halauthorid">631994-0</idno>
                  <affiliation ref="#struct-160294"/>
                  <affiliation ref="#struct-104763"/>
                  <affiliation ref="#struct-34120"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Fabien</forename>
                    <surname>Mathieu</surname>
                  </persName>
                  <email type="md5">216b51218f7e2d57be3828f43e6f6391</email>
                  <email type="domain">normalesup.org</email>
                  <ptr type="url" target="https://balouf.github.io/"/>
                  <idno type="idhal" notation="string">fabien-mathieu</idno>
                  <idno type="idhal" notation="numeric">446</idno>
                  <idno type="halauthorid" notation="string">21677-446</idno>
                  <idno type="IDREF">https://www.idref.fr/088099849</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1362-0359</idno>
                  <affiliation ref="#struct-160294"/>
                  <affiliation ref="#struct-104763"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Laurent</forename>
                    <surname>Viennot</surname>
                  </persName>
                  <email type="md5">6bc2ca7e27f9b949929655afb8df6627</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">laurentviennot</idno>
                  <idno type="idhal" notation="numeric">1841</idno>
                  <idno type="halauthorid" notation="string">16606-1841</idno>
                  <idno type="IDREF">https://www.idref.fr/034781072</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3657-6979</idno>
                  <affiliation ref="#struct-160294"/>
                  <affiliation ref="#struct-34120"/>
                  <affiliation ref="#struct-1033"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Algorithms and Models for the Web Graph - 11th International Workshop (WAW 2014)</title>
                  <date type="start">2014-12-17</date>
                  <settlement>Beijing</settlement>
                  <country key="CN">China</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">148 - 160</biblScope>
                  <date type="datePub">2014</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-319-13123-8_12</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">crawl</term>
                <term xml:lang="en">LiveRank</term>
                <term xml:lang="en">Pagerank</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ni">Computer Science [cs]/Networking and Internet Architecture [cs.NI]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This paper considers the problem of refreshing a crawl. More precisely, given a collection of Web pages (with hyperlinks) gathered at some time, we want to identify a significant fraction of these pages that still exist at present time. The liveness of an old page can be tested through an online query at present time. We call LiveRank a ranking of the old pages so that active nodes are more likely to appear first. The quality of a LiveRank is measured by the number of queries necessary to identify a given fraction of the alive pages when using the LiveRank order. We study different scenarios from a static setting where the LiveRank is computed before any query is made, to dynamic settings where the LiveRank can be updated as queries are processed. Our results show that building on the PageRank can lead to efficient LiveRanks for Web graphs.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-160294" status="OLD">
          <orgName>Laboratory of Information, Network and Communication Sciences</orgName>
          <orgName type="acronym">LINCS</orgName>
          <desc>
            <address>
              <addrLine>23 avenue d'Italie 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lincs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93591" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-104763" status="VALID">
          <orgName>Alcatel-Lucent Bell Labs France [Nozay]</orgName>
          <desc>
            <address>
              <addrLine>Centre de Villarceaux, Route de Villejust, 91620, NOZAY, FRANCE</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-368392" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-34120" status="OLD">
          <idno type="RNSR">200718314F</idno>
          <orgName>Networks, Graphs and Algorithms</orgName>
          <orgName type="acronym">GANG</orgName>
          <date type="start">2007-07-01</date>
          <date type="end">2015-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/gang</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1033" type="direct"/>
            <relation active="#struct-300301" type="indirect"/>
            <relation name="UMR7089" active="#struct-441569" type="indirect"/>
            <relation active="#struct-86790" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1033" status="OLD">
          <orgName>Laboratoire d'informatique Algorithmique : Fondements et Applications</orgName>
          <orgName type="acronym">LIAFA</orgName>
          <date type="start">1997-01-01</date>
          <date type="end">2015-12-31</date>
          <desc>
            <address>
              <addrLine>Université Paris Diderot, Bât. Sophie Germain, case postale 7014, 75205 Paris cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.liafa.jussieu.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300301" type="direct"/>
            <relation name="UMR7089" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-93591" status="OLD">
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Pierre et Marie Curie - Paris 6</orgName>
          <orgName type="acronym">UPMC</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 place Jussieu - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmc.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-368392" status="INCOMING">
          <orgName>Alcatel-Lucent Bell Labs France</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300301" status="OLD">
          <idno type="IdRef">027542084</idno>
          <idno type="ISNI">0000000121514068</idno>
          <idno type="ROR">https://ror.org/02n7qrg46</idno>
          <orgName>Université Paris Diderot - Paris 7</orgName>
          <orgName type="acronym">UPD7</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>5 rue Thomas-Mann - 75205 Paris cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris-diderot.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-86790" status="OLD">
          <orgName>Inria Paris-Rocquencourt</orgName>
          <date type="end">2016-03-30</date>
          <desc>
            <address>
              <addrLine>INRIA Rocquencourt : Domaine de Voluceau, Rocquencourt B.P. 105 78153 le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris-rocquencourt</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>