<?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-00627811</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="2026-05-06T21:00:49+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Syntax tree fingerprinting: a foundation for source code similarity detection</title>
            <author role="aut">
              <persName>
                <forename type="first">Michel</forename>
                <surname>Chilowicz</surname>
              </persName>
              <idno type="halauthorid">552828-0</idno>
              <affiliation ref="#struct-3210"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Étienne</forename>
                <surname>Duris</surname>
              </persName>
              <idno type="halauthorid">581977-0</idno>
              <affiliation ref="#struct-3210"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gilles</forename>
                <surname>Roussel</surname>
              </persName>
              <email type="md5">94af8ed1eafb378a3f2f0a8d165c0045</email>
              <email type="domain">univ-eiffel.fr</email>
              <idno type="idhal" notation="string">gilles-roussel</idno>
              <idno type="idhal" notation="numeric">182892</idno>
              <idno type="halauthorid" notation="string">2261-182892</idno>
              <affiliation ref="#struct-3210"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Etienne</forename>
                <surname>Duris</surname>
              </persName>
              <email type="md5">debf2f268d2e28ed9900219ea07c8d9d</email>
              <email type="domain">univ-paris-est.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2011-09-29 16:07:23</date>
              <date type="whenWritten">2009</date>
              <date type="whenModified">2026-04-02 11:58:01</date>
              <date type="whenReleased">2011-09-29 16:09:52</date>
              <date type="whenProduced">2009</date>
              <date type="whenEndEmbargoed">2011-09-29</date>
              <ref type="file" target="https://hal.science/hal-00627811v1/document">
                <date notBefore="2011-09-29"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-00627811v1/file/HAL.pdf" id="file-627811-282652">
                <date notBefore="2011-09-29"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="171534">
                <persName>
                  <forename>Etienne</forename>
                  <surname>Duris</surname>
                </persName>
                <email type="md5">debf2f268d2e28ed9900219ea07c8d9d</email>
                <email type="domain">univ-paris-est.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00627811</idno>
            <idno type="halUri">https://hal.science/hal-00627811</idno>
            <idno type="halBibtex">chilowicz:hal-00627811</idno>
            <idno type="halRefHtml">2009</idno>
            <idno type="halRef">2009</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-627811-282652"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="ENPC" corresp="PARISTECH">École nationale des ponts et chaussées </idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-MLV">Université de Marne la Vallée</idno>
            <idno type="stamp" n="LIGM_ALGO" corresp="LIGM">Algorithmics</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="ENPC-LIGM" corresp="ENPC">Laboratoire d'informatique Gaspard-Monge</idno>
            <idno type="stamp" n="LIGM" corresp="ENPC">Laboratoire d'informatique Gaspard-Monge</idno>
            <idno type="stamp" n="CV_LIGM" corresp="CV_UNIV-MLV">CV des membres du LIGM</idno>
            <idno type="stamp" n="LIGM_LRT" corresp="LIGM">Software, Networks and Real-Time Systems</idno>
            <idno type="stamp" n="LARA">LARA</idno>
            <idno type="stamp" n="ESIEE-PARIS">ESIEE Paris</idno>
            <idno type="stamp" n="UNIV-EIFFEL">Université Gustave Eiffel</idno>
            <idno type="stamp" n="UPEM-UNIVEIFFEL">Université Paris-Est Marne-la-Vallée</idno>
            <idno type="stamp" n="ESIEE-UNIVEIFFEL">ESIEE Paris</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="1">Not set</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Syntax tree fingerprinting: a foundation for source code similarity detection</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Michel</forename>
                    <surname>Chilowicz</surname>
                  </persName>
                  <idno type="halauthorid">552828-0</idno>
                  <affiliation ref="#struct-3210"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Étienne</forename>
                    <surname>Duris</surname>
                  </persName>
                  <idno type="halauthorid">581977-0</idno>
                  <affiliation ref="#struct-3210"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gilles</forename>
                    <surname>Roussel</surname>
                  </persName>
                  <email type="md5">94af8ed1eafb378a3f2f0a8d165c0045</email>
                  <email type="domain">univ-eiffel.fr</email>
                  <idno type="idhal" notation="string">gilles-roussel</idno>
                  <idno type="idhal" notation="numeric">182892</idno>
                  <idno type="halauthorid" notation="string">2261-182892</idno>
                  <affiliation ref="#struct-3210"/>
                </author>
              </analytic>
              <monogr>
                <imprint>
                  <pubPlace>L.I.G.M., Université de Marne-la-Vallée</pubPlace>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ds">Computer Science [cs]/Data Structures and Algorithms [cs.DS]</classCode>
              <classCode scheme="halTypology" n="REPORT">Reports</classCode>
              <classCode scheme="halOldTypology" n="REPORT">Reports</classCode>
              <classCode scheme="halTreeTypology" n="REPORT">Reports</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Plagiarism detection and clone refactoring in software depend on one common concern: nding similar source chunks across large repositories. However, since code duplication in software is often the result of copy-paste behaviors, only minor modi cations are expected between shared codes. On the contrary, in a plagiarism detection context, edits are more extensive and exact matching strategies show their limits. Among the three main representations used by source code similarity detection tools, namely the linear token sequences, the Abstract Syntax Tree (AST) and the Program Depen- dency Graph (PDG), we believe that the AST could e ciently support the program analysis and transformations required for the advanced similarity detection process. In this paper we present a simple and scalable architecture based on syntax tree nger- printing. Thanks to a study of several hashing strategies reducing false-positive collisions, we propose a framework that e ciently indexes AST representations in a database, that quickly detects exact (w.r.t source code abstraction) clone clusters and that easily retrieves their corresponding ASTs. Our aim is to allow further processing of neighboring exact matches in order to identify the larger approximate matches, dealing with the common modi cation patterns seen in the intra-project copy-pastes and in the plagiarism cases.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-3210" status="OLD">
          <idno type="IdRef">142877891</idno>
          <idno type="ISNI">0000000091039111</idno>
          <idno type="RNSR">200212717U</idno>
          <idno type="ROR">https://ror.org/04t50yk91</idno>
          <orgName>Laboratoire d'Informatique Gaspard-Monge</orgName>
          <orgName type="acronym">LIGM</orgName>
          <date type="start">1992-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Université de Paris-Est Marne-la-Vallée, Cité Descartes, Bâtiment Copernic, 5 bd Descartes, 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ligm.u-pem.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301243" type="direct"/>
            <relation active="#struct-301545" type="direct"/>
            <relation active="#struct-302035" type="direct"/>
            <relation active="#struct-302085" type="direct"/>
            <relation name="FRA3522 / FR3522" active="#struct-441569" type="direct"/>
            <relation name="UMR8049" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301243" status="OLD">
          <idno type="IdRef">030820499</idno>
          <idno type="ISNI">0000000115124813</idno>
          <idno type="ROR">https://ror.org/02aqt9c37</idno>
          <orgName>Université Paris-Est Marne-la-Vallée</orgName>
          <orgName type="acronym">UPEM</orgName>
          <date type="start">1991-07-22</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>5 boulevard Descartes - Champs-sur-Marne - 77454 Marne-la-Vallée Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-pem.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301545" status="OLD">
          <idno type="ROR">https://ror.org/02nwvxz07</idno>
          <orgName>École nationale des ponts et chaussées</orgName>
          <orgName type="acronym">ENPC</orgName>
          <date type="start">1747-02-14</date>
          <date type="end">2024-12-31</date>
          <desc>
            <address>
              <addrLine>École nationale des ponts et chaussées, 6-8 avenue Blaise-Pascal, Cité Descartes, Champs-sur-Marne, 77455 Marne-la-Vallée cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://ecoledesponts.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302035" status="VALID">
          <idno type="RNSR">199814079S</idno>
          <orgName>ESIEE Paris</orgName>
          <date type="start">2016-11-25</date>
          <desc>
            <address>
              <addrLine>2 boulevard Blaise PascalCité DescartesBP 9993162 Noisy-le-Grand Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.esiee.fr</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-302085" status="VALID">
          <idno type="RNSR">201220485U</idno>
          <orgName>Fédération de Recherche Bézout</orgName>
          <orgName type="acronym">BEZOUT</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>5, bd Descartes, Champs-sur-Marne77455 Marne-la-Vallée Cedex 2 – France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://labex-bezout.fr/bezout-federation/</ref>
          </desc>
          <listRelation>
            <relation name="FRA3522 / FR3522" active="#struct-441569" type="direct"/>
          </listRelation>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>