<?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-04267976v2</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="2026-05-16T02:55:38+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Pro bono decontamination of the scientific literature: How sleuths track errors and fraud with the Problematic Paper Screener</title>
            <author role="aut">
              <persName>
                <forename type="first">Guillaume</forename>
                <surname>Cabanac</surname>
              </persName>
              <email type="md5">120b3d590ad9161386a346746011b13f</email>
              <email type="domain">univ-tlse3.fr</email>
              <idno type="idhal" notation="string">guillaume-cabanac</idno>
              <idno type="idhal" notation="numeric">11083</idno>
              <idno type="halauthorid" notation="string">7837-11083</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/C-5913-2011</idno>
              <idno type="IDREF">https://www.idref.fr/13735438X</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3060-6241</idno>
              <idno type="VIAF">https://viaf.org/viaf/215268985</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=4dp38PkAAAAJ&amp;hl=fr</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/C-5913-2011</idno>
              <affiliation ref="#struct-1612887"/>
              <affiliation ref="#struct-56663"/>
              <affiliation ref="#struct-1612993"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Guillaume</forename>
                <surname>Cabanac</surname>
              </persName>
              <email type="md5">120b3d590ad9161386a346746011b13f</email>
              <email type="domain">univ-tlse3.fr</email>
            </editor>
            <funder ref="#projeurop-714018"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1">
              <date type="whenSubmitted">2023-11-02 12:07:25</date>
            </edition>
            <edition n="v2" type="current">
              <date type="whenSubmitted">2025-04-08 11:55:00</date>
              <date type="whenModified">2026-03-24 03:01:02</date>
              <date type="whenReleased">2025-04-14 11:15:52</date>
              <date type="whenProduced">2025-04-07</date>
              <date type="whenEndEmbargoed">2025-04-08</date>
              <ref type="file" target="https://hal.science/hal-04267976v2/document">
                <date notBefore="2025-04-08"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04267976v2/file/20250331_FAIRS_Cabanac.pdf" id="file-5024932-4353183">
                <date notBefore="2025-04-08"/>
              </ref>
              <ref type="annex" n="0" target="https://hal.science/hal-04267976v2/file/20250331_FAIRS_Cababac.mp4" id="file-5024932-4353184">
                <date notBefore="2025-04-08"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="363679">
                <persName>
                  <forename>Guillaume</forename>
                  <surname>Cabanac</surname>
                </persName>
                <email type="md5">120b3d590ad9161386a346746011b13f</email>
                <email type="domain">univ-tlse3.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04267976</idno>
            <idno type="halUri">https://hal.science/hal-04267976</idno>
            <idno type="halBibtex">cabanac:hal-04267976</idno>
            <idno type="halRefHtml">Doctoral. Fostering Accountability for the Integrity of Research Studies (FAIRS), St John's College, Oxford, United Kingdom. 2025</idno>
            <idno type="halRef">Doctoral. Fostering Accountability for the Integrity of Research Studies (FAIRS), St John's College, Oxford, United Kingdom. 2025</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5024932-4353183"/><ref corresp="#file-5024932-4353184"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="IRIT">IRIT - Institut de Recherche en Informatique de Toulouse</idno>
            <idno type="stamp" n="IRIT-IRIS" corresp="IRIT">Recherche d’Information et Synthèse d’Information</idno>
            <idno type="stamp" n="IRIT-GD" corresp="IRIT">Gestion des Données</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</idno>
          </seriesStmt>
          <notesStmt>
            <note type="lecture" n="13">Doctoral</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Pro bono decontamination of the scientific literature: How sleuths track errors and fraud with the Problematic Paper Screener</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Guillaume</forename>
                    <surname>Cabanac</surname>
                  </persName>
                  <email type="md5">120b3d590ad9161386a346746011b13f</email>
                  <email type="domain">univ-tlse3.fr</email>
                  <idno type="idhal" notation="string">guillaume-cabanac</idno>
                  <idno type="idhal" notation="numeric">11083</idno>
                  <idno type="halauthorid" notation="string">7837-11083</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/C-5913-2011</idno>
                  <idno type="IDREF">https://www.idref.fr/13735438X</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3060-6241</idno>
                  <idno type="VIAF">https://viaf.org/viaf/215268985</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=4dp38PkAAAAJ&amp;hl=fr</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/C-5913-2011</idno>
                  <affiliation ref="#struct-1612887"/>
                  <affiliation ref="#struct-56663"/>
                  <affiliation ref="#struct-1612993"/>
                </author>
              </analytic>
              <monogr>
                <settlement>St John's College, Oxford</settlement>
                <country key="GB">United Kingdom</country>
                <imprint>
                  <date type="datePub">2025-04-07</date>
                </imprint>
                <authority type="institution">Oxford University</authority>
              </monogr>
              <series>
                <title>Fostering Accountability for the Integrity of Research Studies (FAIRS)</title>
              </series>
              <ref target="https://www.sjcfairsmeeting.com" type="seeAlso"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">research integrity</term>
                <term xml:lang="en">fraud</term>
                <term xml:lang="en">text mining</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-dl">Computer Science [cs]/Digital Libraries [cs.DL]</classCode>
              <classCode scheme="halTypology" n="LECTURE">Lectures</classCode>
              <classCode scheme="halOldTypology" n="LECTURE">Lectures</classCode>
              <classCode scheme="halTreeTypology" n="LECTURE">Lectures</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Imagine reading Fast Fourier Change, Innocent Bayes, and nucleic corrosive* in a scientific paper published in an established journal with Impact Factor from a haute couture publisher such as Elsevier, Wiley, Springer...  Well, we identified more than 11k such problematic papers featuring ‘tortured phrases’ produced by paraphrasing tools to deceive plagiarism detection.  In 2021, this issue affected 3 every 10k papers.  Scammers produce such unreliable papers in bulk to appear hyper productive; they organise citation rings to increase their H-index. This talk presents how sleuths strive to decontaminate the literature from this digital pollution.  A handful of professional scientists and hobbyists re-assess the suspect papers flagged by the ‘Problematic Paper Screener,’ contribute pro bono post-publication peer reviews on PubPeer, and eventually manage to get publishers retract hundreds of papers, mostly in engineering and biomedicine.*instead of Fast Fourier Transform, Naive Bayes, and nucleic acid.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1612887" status="VALID">
          <orgName>Recherche d’Information et Synthèse d’Information</orgName>
          <orgName type="acronym">IRIT-IRIS</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>IRIT118 Route de Narbonne 31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.irit.fr/departement/gestion-des-donnees/iris/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1612872" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="UMR5505" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
            <relation active="#struct-1574795" type="indirect"/>
            <relation active="#struct-1612865" type="indirect"/>
            <relation name="FED4171" active="#struct-1574795" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-56663" status="VALID">
          <idno type="IdRef">03442945X</idno>
          <idno type="ISNI">0000000119314817</idno>
          <idno type="ROR">https://ror.org/055khg266</idno>
          <idno type="Wikidata">Q1665127</idno>
          <orgName>Institut universitaire de France</orgName>
          <orgName type="acronym">IUF</orgName>
          <desc>
            <address>
              <addrLine>Maison des Universités 103 Boulevard Saint-Michel 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://iuf.amue.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301855" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1612993" status="VALID">
          <orgName>Institut Universitaire de Technologie - Paul Sabatier</orgName>
          <orgName type="acronym">IUT Toulouse Auch Castres</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>Université Toulouse III - 115C, route de Narbonne - 31077 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://iut.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1574795" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1612872" status="VALID">
          <idno type="IdRef">030947448</idno>
          <idno type="ISNI">0000000121927225</idno>
          <idno type="RNSR">199511949P</idno>
          <idno type="ROR">https://ror.org/01rx4qw44</idno>
          <orgName>Institut de recherche en informatique de Toulouse</orgName>
          <orgName type="acronym">IRIT</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 Route de Narbonne, F-31062 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irit.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="UMR5505" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
            <relation active="#struct-1574795" type="direct"/>
            <relation active="#struct-1612865" type="direct"/>
            <relation name="FED4171" active="#struct-1574795" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" 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>
        <org type="institution" xml:id="struct-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1574795" status="VALID">
          <orgName>Université de Toulouse</orgName>
          <orgName type="acronym">EPE UT</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 toute de Narbonne, 31062 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-1612865" status="VALID">
          <orgName>Toulouse Mind &amp; Brain Institut</orgName>
          <orgName type="acronym">TMBI</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>CHU Purpan, Pavillon Baudot, 31059 Toulouse cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.tmbi.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation name="FED4171" active="#struct-1574795" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301855" status="VALID">
          <orgName>Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche</orgName>
          <orgName type="acronym">M.E.N.E.S.R.</orgName>
          <desc>
            <address>
              <addrLine>1 rue Descartes - 75231 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="europeanProject" xml:id="projeurop-714018" status="VALID">
          <idno type="number">951393</idno>
          <idno type="program">ERC-2020-SyG</idno>
          <idno type="call">ERC-2020-SyG</idno>
          <orgName>NanoBubbles</orgName>
          <desc>Nano bubbles: how, when and why does science fail to correct itself?</desc>
          <date type="start">2021-06-01</date>
          <date type="end">2026-05-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>