<?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-05338260v1</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="2026-05-16T03:10:23+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Dynamics of discovery and the Heaps-Zipf relationship</title>
            <author role="aut">
              <persName>
                <forename type="first">Célestin</forename>
                <surname>Zimmerlin</surname>
              </persName>
              <idno type="halauthorid">3856681-0</idno>
              <affiliation ref="#struct-1005044"/>
              <affiliation ref="#struct-1320473"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Thomas</forename>
                <surname>Louail</surname>
              </persName>
              <email type="md5">176e65103fcd164a690ca2658943303a</email>
              <email type="domain">cnrs.fr</email>
              <idno type="idhal" notation="string">tlouail</idno>
              <idno type="idhal" notation="numeric">19980</idno>
              <idno type="halauthorid" notation="string">4714-19980</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8563-6881</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=pZAtLJMAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/151492859</idno>
              <idno type="VIAF">https://viaf.org/viaf/199104570</idno>
              <idno type="ISNI">http://isni.org/isni/0000000357723667</idno>
              <affiliation ref="#struct-1005044"/>
              <affiliation ref="#struct-1320473"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Manuel</forename>
                <surname>Moussallam</surname>
              </persName>
              <idno type="halauthorid">634437-0</idno>
              <affiliation ref="#struct-1040468"/>
              <affiliation ref="#struct-1320473"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Barthelemy</surname>
              </persName>
              <idno type="halauthorid">116972-0</idno>
              <affiliation ref="#struct-53952"/>
              <affiliation ref="#struct-1318"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Thomas</forename>
                <surname>Louail</surname>
              </persName>
              <email type="md5">176e65103fcd164a690ca2658943303a</email>
              <email type="domain">cnrs.fr</email>
            </editor>
            <funder ref="#projanr-185534"/>
            <funder>Programme PRIME80 de la Mission pour l'Interdisciplinarité et les Initiatives Transverses (MITI) du CNRS</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-10-30 09:49:58</date>
              <date type="whenWritten">2026-04-22</date>
              <date type="whenModified">2026-05-16 03:09:34</date>
              <date type="whenReleased">2025-10-30 09:52:25</date>
              <date type="whenProduced">2026-05-11</date>
              <date type="whenEndEmbargoed">2025-10-30</date>
              <ref type="file" target="https://hal.science/hal-05338260v1/document">
                <date notBefore="2025-10-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05338260v1/file/2510.21481v1.pdf" id="file-5338260-4570090">
                <date notBefore="2025-10-30"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2510.21481"/>
            </edition>
            <edition n="v2">
              <date type="whenSubmitted">2026-05-12 11:04:34</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="403703">
                <persName>
                  <forename>Thomas</forename>
                  <surname>Louail</surname>
                </persName>
                <email type="md5">176e65103fcd164a690ca2658943303a</email>
                <email type="domain">cnrs.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05338260</idno>
            <idno type="halUri">https://hal.science/hal-05338260</idno>
            <idno type="halBibtex">zimmerlin:hal-05338260</idno>
            <idno type="halRefHtml">&lt;i&gt;Physical Review E &lt;/i&gt;, 2026, 113, pp.054304. &lt;a target="_blank" href="https://dx.doi.org/10.1103/543d-frbq"&gt;&amp;#x27E8;10.1103/543d-frbq&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Physical Review E , 2026, 113, pp.054304. &amp;#x27E8;10.1103/543d-frbq&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-5338260-4570090"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Dynamics of discovery and the Heaps-Zipf relationship</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Célestin</forename>
                    <surname>Zimmerlin</surname>
                  </persName>
                  <idno type="halauthorid">3856681-0</idno>
                  <affiliation ref="#struct-1005044"/>
                  <affiliation ref="#struct-1320473"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Thomas</forename>
                    <surname>Louail</surname>
                  </persName>
                  <email type="md5">176e65103fcd164a690ca2658943303a</email>
                  <email type="domain">cnrs.fr</email>
                  <idno type="idhal" notation="string">tlouail</idno>
                  <idno type="idhal" notation="numeric">19980</idno>
                  <idno type="halauthorid" notation="string">4714-19980</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8563-6881</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=pZAtLJMAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/151492859</idno>
                  <idno type="VIAF">https://viaf.org/viaf/199104570</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000357723667</idno>
                  <affiliation ref="#struct-1005044"/>
                  <affiliation ref="#struct-1320473"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Manuel</forename>
                    <surname>Moussallam</surname>
                  </persName>
                  <idno type="halauthorid">634437-0</idno>
                  <affiliation ref="#struct-1040468"/>
                  <affiliation ref="#struct-1320473"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Barthelemy</surname>
                  </persName>
                  <idno type="halauthorid">116972-0</idno>
                  <affiliation ref="#struct-53952"/>
                  <affiliation ref="#struct-1318"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">106753</idno>
                <idno type="issn">2470-0045</idno>
                <idno type="eissn">2470-0053</idno>
                <title level="j">Physical Review E </title>
                <imprint>
                  <publisher>American Physical Society (APS)</publisher>
                  <biblScope unit="volume">113</biblScope>
                  <biblScope unit="pp">054304</biblScope>
                  <date type="datePub">2026-05-11</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2510.21481</idno>
              <idno type="doi">10.1103/543d-frbq</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Music listening behavior</term>
                <term xml:lang="en">Discovery processes</term>
                <term xml:lang="en">Type-token plot</term>
                <term xml:lang="en">Zipf's Law</term>
                <term xml:lang="en">Heaps' Law</term>
              </keywords>
              <classCode scheme="halDomain" n="phys.phys.phys-soc-ph">Physics [physics]/Physics [physics]/Physics and Society [physics.soc-ph]</classCode>
              <classCode scheme="halDomain" n="shs.stat">Humanities and Social Sciences/Methods and statistics</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>When following a sequence — such as reading a text or tracking a user’s activity — one can measure how the ‘dictionary’ of distinct elements (types) grows with the number of observations (tokens). When this growth follows a power law, it is referred to as Heaps’ law, a regularity often associated with Zipf’s law and frequently used to characterize human discovery processes. While random sampling from a Zipf-like distribution can reproduce Heaps’ law, this connection relies on the assumption of temporal independence — an assumption often violated in real-world systems although frequently found in the literature. Here, we investigate how temporal correlations in token sequences affect the type–token curve. In human behaviors like music listening and web browsing, domain-specific correlations in token ordering lead to systematic deviations from the Zipf–Heaps framework, effectively decoupling the type–token plot from the rank–frequency distribution. Using a minimal one-parameter model, we reproduce a wide variety of type–token trajectories, including the extremal cases that bound all possible behaviors compatible with a given frequency distribution. Our results demonstrate that type–token growth reflects not only the empirical distribution of type frequencies, but also the domain-specific, temporal structure of the sequence — a factor often overlooked in empirical applications of scaling laws to characterize human behavior.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1005044" status="VALID">
          <idno type="IdRef">087876566</idno>
          <idno type="ISNI">0000000406236436</idno>
          <idno type="RNSR">199812840V</idno>
          <idno type="ROR">05yqfzf35</idno>
          <orgName>Géographie-cités</orgName>
          <orgName type="acronym">GC (UMR_8504)</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Campus CondorcetBâtiment de recherches sud5, cours des Humanités93322 Aubervilliers cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.parisgeo.cnrs.fr</ref>
          </desc>
          <listRelation>
            <relation name="UMR8504" active="#struct-7550" type="direct"/>
            <relation active="#struct-99539" type="direct"/>
            <relation name="UMR8504" active="#struct-441569" type="direct"/>
            <relation name="UMR_8504" active="#struct-557826" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1320473" status="INCOMING">
          <orgName>MIXTAPES (données et méthodes MIXTes pour l'Analyse des Pratiques d'Ecoute en Streaming)</orgName>
          <orgName type="acronym">MIXTAPES</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-7550" type="direct"/>
            <relation active="#struct-84039" type="direct"/>
            <relation active="#struct-99539" type="direct"/>
            <relation active="#struct-557826" type="direct"/>
            <relation active="#struct-1040468" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1040468" status="VALID">
          <orgName>Deezer Research</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://research.deezer.com/projects/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-53952" status="VALID">
          <idno type="IdRef">152768483</idno>
          <idno type="RNSR">201522372G</idno>
          <idno type="ROR">https://ror.org/058rvd314</idno>
          <idno type="Wikidata">Q19945099</idno>
          <orgName>Institut de Physique Théorique - UMR CNRS 3681</orgName>
          <orgName type="acronym">IPHT</orgName>
          <date type="start">2008-01-01</date>
          <desc>
            <address>
              <addrLine>Institut de Physique ThéoriqueOrme des Merisiers batiment 774 Point courrier 136 CEA/DSM/IPhTCEA/Saclay F-91191 Gif-sur-Yvette Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ipht.cea.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419361" type="direct"/>
            <relation name="UMR3681" active="#struct-441569" type="direct"/>
            <relation active="#struct-465913" type="direct"/>
            <relation active="#struct-300016" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1318" status="VALID">
          <idno type="RNSR">199812885U</idno>
          <idno type="ROR">00vb8fc53</idno>
          <orgName>Centre d'Analyse et de Mathématique sociales</orgName>
          <orgName type="acronym">CAMS</orgName>
          <date type="start">1998-01-01</date>
          <desc>
            <address>
              <addrLine>54 boulevard Raspail 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cams.ehess.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-99539" type="direct"/>
            <relation name="UMR8557" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-7550" status="VALID">
          <idno type="IdRef">027361802</idno>
          <idno type="ISNI">000000012173743X</idno>
          <idno type="ROR">https://ror.org/002t25c44</idno>
          <orgName>Université Paris 1 Panthéon-Sorbonne</orgName>
          <orgName type="acronym">UP1</orgName>
          <desc>
            <address>
              <addrLine>12 place du Panthéon, 75231 Paris Cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.pantheonsorbonne.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-99539" status="VALID">
          <idno type="IdRef">026374889</idno>
          <idno type="ROR">https://ror.org/02d9dg697</idno>
          <orgName>École des hautes études en sciences sociales</orgName>
          <orgName type="acronym">EHESS</orgName>
          <date type="start">1975-01-01</date>
          <desc>
            <address>
              <addrLine>54, boulevard Raspail 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ehess.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="institution" xml:id="struct-557826" status="VALID">
          <idno type="IdRef">236453505</idno>
          <idno type="ISNI">0000 0004 7885 7602</idno>
          <idno type="ROR">https://ror.org/05f82e368</idno>
          <orgName>Université Paris Cité</orgName>
          <orgName type="acronym">UPCité</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>85 boulevard Saint-Germain75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://u-paris.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-84039" status="VALID">
          <idno type="IdRef">146608992</idno>
          <idno type="ISNI">0000000403871477</idno>
          <idno type="ROR">https://ror.org/04b0z7q78</idno>
          <orgName>Institut des Sciences Humaines et Sociales - CNRS Sciences humaines et sociales</orgName>
          <orgName type="acronym">INSHS-CNRS</orgName>
          <date type="start">2009-11-01</date>
          <desc>
            <address>
              <addrLine>CNRS 3 rue Michel-Ange 75794 PARIS CEDEX 16</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cnrs.fr/inshs</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-465913" status="VALID">
          <idno type="IdRef">251118436</idno>
          <idno type="RNSR">201622496M</idno>
          <idno type="ROR">https://ror.org/01yvj5k91</idno>
          <idno type="Wikidata">Q52604525</idno>
          <orgName>Direction de Recherche Fondamentale (CEA)</orgName>
          <orgName type="acronym">DRF (CEA)</orgName>
          <date type="start">2016-01-01</date>
          <desc>
            <address>
              <addrLine>Direction de Recherche FondamentaleFundamental Research DivisionCEA Saclay91191 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://ceasciences.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300016" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300016" status="VALID">
          <idno type="IdRef">026372061</idno>
          <idno type="ISNI">0000000122998025</idno>
          <idno type="ROR">https://ror.org/00jjx8s55</idno>
          <idno type="Wikidata">Q868550</idno>
          <orgName>Commissariat à l'énergie atomique et aux énergies alternatives</orgName>
          <orgName type="acronym">CEA</orgName>
          <desc>
            <address>
              <addrLine>Centre de SaclayCentre de GrenobleCentre de Cadaracheetc</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cea.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-185534" status="VALID">
          <idno type="anr">ANR-24-LCV1-0003</idno>
          <orgName>MIXTAPES</orgName>
          <desc>méthodes et données MIXTes pour l'Analyse des Pratiques d'Ecoute en Streaming</desc>
          <date type="start">2024</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>