<?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-05063560</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="2026-05-03T11:41:52+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Linux Kernel Configurations at Scale: A Dataset for Performance and Evolution Analysis</title>
            <author role="aut">
              <persName>
                <forename type="first">Heraldo</forename>
                <surname>Borges</surname>
              </persName>
              <email type="md5">65b0dbab92520e04ccdd6e1574818281</email>
              <email type="domain">irisa.fr</email>
              <idno type="idhal" notation="string">1118315</idno>
              <idno type="idhal" notation="numeric">1540172</idno>
              <idno type="halauthorid" notation="string">1417594-1540172</idno>
              <affiliation ref="#struct-491189"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Juliana</forename>
                <forename type="middle">Alves</forename>
                <surname>Pereira</surname>
              </persName>
              <email type="md5">e8bddf237bd940e8fcf94baa3addea75</email>
              <email type="domain">inf.puc-rio.br</email>
              <idno type="idhal" notation="numeric">1540183</idno>
              <idno type="halauthorid" notation="string">1652120-1540183</idno>
              <affiliation ref="#struct-362752"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Djamel</forename>
                <forename type="middle">Eddine</forename>
                <surname>Khelladi</surname>
              </persName>
              <email type="md5">11fc77c8bea9911a5daef38dc673efdd</email>
              <email type="domain">irisa.fr</email>
              <idno type="idhal" notation="string">dkhelladi</idno>
              <idno type="idhal" notation="numeric">176712</idno>
              <idno type="halauthorid" notation="string">54492-176712</idno>
              <affiliation ref="#struct-491189"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mathieu</forename>
                <surname>Acher</surname>
              </persName>
              <email type="md5">c89693c867272ce417824153dd5442c0</email>
              <email type="domain">irisa.fr</email>
              <idno type="idhal" notation="string">mathieu-acher</idno>
              <idno type="idhal" notation="numeric">2007</idno>
              <idno type="halauthorid" notation="string">15358-2007</idno>
              <idno type="IDREF">https://www.idref.fr/158563913</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1483-3858</idno>
              <affiliation ref="#struct-491189"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Heraldo</forename>
                <surname>Pimenta Borges Filho</surname>
              </persName>
              <email type="md5">65b0dbab92520e04ccdd6e1574818281</email>
              <email type="domain">irisa.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-05-12 11:04:31</date>
              <date type="whenModified">2026-01-23 09:12:07</date>
              <date type="whenReleased">2025-05-12 11:19:04</date>
              <date type="whenProduced">2025-06-17</date>
              <date type="whenEndEmbargoed">2025-05-12</date>
              <ref type="file" target="https://hal.science/hal-05063560v1/document">
                <date notBefore="2025-05-12"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05063560v1/file/EASE2025_LinuxKernelDatapaper.pdf" id="file-5063560-4381281">
                <date notBefore="2025-05-12"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1673640">
                <persName>
                  <forename>Heraldo</forename>
                  <surname>Pimenta Borges Filho</surname>
                </persName>
                <email type="md5">65b0dbab92520e04ccdd6e1574818281</email>
                <email type="domain">irisa.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05063560</idno>
            <idno type="halUri">https://hal.science/hal-05063560</idno>
            <idno type="halBibtex">borges:hal-05063560</idno>
            <idno type="halRefHtml">&lt;i&gt;EASE 2025 - Evaluation and Assessment in Software Engineering&lt;/i&gt;, Jun 2025, Istambul, Turkey. pp.1-10</idno>
            <idno type="halRef">EASE 2025 - Evaluation and Assessment in Software Engineering, Jun 2025, Istambul, Turkey. pp.1-10</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5063560-4381281"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-RENNES1">Université de Rennes 1</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="UNIV-UBS">Université de Bretagne Sud</idno>
            <idno type="stamp" n="INSA-RENNES">Institut National des Sciences Appliquées de Rennes</idno>
            <idno type="stamp" n="INRIA-RENNES">INRIA Rennes - Bretagne Atlantique</idno>
            <idno type="stamp" n="IRISA">Irisa</idno>
            <idno type="stamp" n="IRISA_SET">IRISA_SET</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="IRISA-INSA-R" corresp="IRISA">Institut de Recherche en Informatique et Systèmes Aléatoires - Composante INSA Rennes</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="UR1-HAL">Publications labos UR1 dans HAL-Rennes 1</idno>
            <idno type="stamp" n="UR1-MATH-STIC">UR1 - publications Maths-STIC</idno>
            <idno type="stamp" n="UR1-UFR-ISTIC">UFR ISTIC Informatique et électronique</idno>
            <idno type="stamp" n="TEST-UR-CSS">TEST Université de Rennes CSS</idno>
            <idno type="stamp" n="UNIV-RENNES">Université de Rennes</idno>
            <idno type="stamp" n="INRIA-RENGRE">INRIA-RENGRE</idno>
            <idno type="stamp" n="UR1-MATH-NUM">Pôle UnivRennes - Mathématiques - Numérique </idno>
            <idno type="stamp" n="CYBERSCHOOL">CyberSchool - Ecole universitaire de recherche en Cybersécurité</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Linux Kernel Configurations at Scale: A Dataset for Performance and Evolution Analysis</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Heraldo</forename>
                    <surname>Borges</surname>
                  </persName>
                  <email type="md5">65b0dbab92520e04ccdd6e1574818281</email>
                  <email type="domain">irisa.fr</email>
                  <idno type="idhal" notation="string">1118315</idno>
                  <idno type="idhal" notation="numeric">1540172</idno>
                  <idno type="halauthorid" notation="string">1417594-1540172</idno>
                  <affiliation ref="#struct-491189"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Juliana</forename>
                    <forename type="middle">Alves</forename>
                    <surname>Pereira</surname>
                  </persName>
                  <email type="md5">e8bddf237bd940e8fcf94baa3addea75</email>
                  <email type="domain">inf.puc-rio.br</email>
                  <idno type="idhal" notation="numeric">1540183</idno>
                  <idno type="halauthorid" notation="string">1652120-1540183</idno>
                  <affiliation ref="#struct-362752"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Djamel</forename>
                    <forename type="middle">Eddine</forename>
                    <surname>Khelladi</surname>
                  </persName>
                  <email type="md5">11fc77c8bea9911a5daef38dc673efdd</email>
                  <email type="domain">irisa.fr</email>
                  <idno type="idhal" notation="string">dkhelladi</idno>
                  <idno type="idhal" notation="numeric">176712</idno>
                  <idno type="halauthorid" notation="string">54492-176712</idno>
                  <affiliation ref="#struct-491189"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mathieu</forename>
                    <surname>Acher</surname>
                  </persName>
                  <email type="md5">c89693c867272ce417824153dd5442c0</email>
                  <email type="domain">irisa.fr</email>
                  <idno type="idhal" notation="string">mathieu-acher</idno>
                  <idno type="idhal" notation="numeric">2007</idno>
                  <idno type="halauthorid" notation="string">15358-2007</idno>
                  <idno type="IDREF">https://www.idref.fr/158563913</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1483-3858</idno>
                  <affiliation ref="#struct-491189"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>EASE 2025 - Evaluation and Assessment in Software Engineering</title>
                  <date type="start">2025-06-17</date>
                  <date type="end">2025-06-20</date>
                  <settlement>Istambul</settlement>
                  <country key="TR">Turkey</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">1-10</biblScope>
                  <date type="datePub">2025</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Configurable Systems</term>
                <term xml:lang="en">Linux Kernel</term>
                <term xml:lang="en">Kernel Configuration</term>
                <term xml:lang="en">Tabular Data</term>
                <term xml:lang="en">Software Evolution</term>
                <term xml:lang="en">Dataset</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halDomain" n="info.info-lg">Computer Science [cs]/Machine Learning [cs.LG]</classCode>
              <classCode scheme="halDomain" n="info.info-se">Computer Science [cs]/Software Engineering [cs.SE]</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>Configuring the Linux kernel to meet specific requirements, such as binary size, is highly challenging due to its immense complexity—with over 15,000 interdependent options evolving rapidly across different versions. Although several studies have explored sampling strategies and machine learning methods to understand and predict the impact of configuration options, the literature still lacks a comprehensive and large-scale dataset encompassing multiple kernel versions along with detailed quantitative measurements. To bridge this gap, we introduce TuxKConfig, an accessible collection of kernel configurations spanning several kernel releases, specifically from versions 4.13 to 5.8. This dataset, gathered through automated tools and build processes, comprises over 240,000 kernel configurations systematically labeled with compilation outcomes and binary sizes. By providing detailed records of configuration evolution and capturing the intricate interplay among kernel options, our dataset enables innovative research in feature subset selection, prediction models based on machine learning, and transfer learning across kernel versions. Throughout this paper, we describe how the dataset has been made easily accessible via OpenML and illustrate how it can be leveraged using only a few lines of Python code to evaluate AI-based techniques, such as supervised machine learning. We anticipate that this dataset will significantly enhance reproducibility and foster new insights into configuration-space analysis at a scale that presents unique opportunities and inherent challenges, thereby advancing our understanding of the Linux kernel’s configurability and evolution.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-491189" status="VALID">
          <idno type="RNSR">201422126U</idno>
          <idno type="ROR">https://ror.org/0194hft57</idno>
          <orgName>Diversity-centric Software Engineering</orgName>
          <orgName type="acronym">DiverSe</orgName>
          <date type="start">2014-07-01</date>
          <date type="end">2026-06-30</date>
          <desc>
            <address>
              <addrLine>Campus de Beaulieu, 35042 Rennes cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/diverse</ref>
          </desc>
          <listRelation>
            <relation active="#struct-419153" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-491188" type="direct"/>
            <relation active="#struct-490899" type="indirect"/>
            <relation active="#struct-105160" type="indirect"/>
            <relation active="#struct-117606" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="indirect"/>
            <relation active="#struct-247362" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR6074" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-362752" status="VALID">
          <idno type="IdRef">02641841X</idno>
          <idno type="ISNI">0000000121570844</idno>
          <idno type="ROR">https://ror.org/01dg47b60</idno>
          <idno type="Wikidata">Q1857293</idno>
          <orgName>Pontifícia Universidade Católica do Rio de Janeiro [Brasil] = Pontifical Catholic University of Rio de Janeiro [Brazil] = Université catholique pontificale de Rio de Janeiro [Brésil]</orgName>
          <orgName type="acronym">PUC-Rio</orgName>
          <desc>
            <address>
              <addrLine>R. Marquês de São Vicente, 225 - Gávea, Rio de Janeiro - RJ, 22451-900, Brésil</addrLine>
              <country key="BR"/>
            </address>
            <ref type="url">https://www.puc-rio.br/index.html</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-419153" status="VALID">
          <idno type="RNSR">198018249C</idno>
          <idno type="ROR">https://ror.org/04040yw90</idno>
          <orgName>Centre Inria de l'Université de Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de beaulieu35042 Rennes cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/rennes</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </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="department" xml:id="struct-491188" status="VALID">
          <orgName>LANGAGE ET GÉNIE LOGICIEL</orgName>
          <orgName type="acronym">IRISA-D4</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-490899" type="direct"/>
            <relation active="#struct-105160" type="indirect"/>
            <relation active="#struct-117606" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="indirect"/>
            <relation active="#struct-247362" type="indirect"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation name="UMR6074" active="#struct-441569" type="indirect"/>
            <relation active="#struct-481355" type="indirect"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-490899" status="VALID">
          <idno type="IdRef">026386909</idno>
          <idno type="ISNI">0000 0001 2298 7270</idno>
          <idno type="RNSR">200012163A</idno>
          <idno type="ROR">https://ror.org/00myn0z94</idno>
          <orgName>Institut de Recherche en Informatique et Systèmes Aléatoires</orgName>
          <orgName type="acronym">IRISA</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Avenue du général LeclercCampus de Beaulieu 35042 RENNES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.irisa.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-105160" type="direct"/>
            <relation active="#struct-117606" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-172265" type="direct"/>
            <relation active="#struct-247362" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation name="UMR6074" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-105160" status="VALID">
          <idno type="IdRef">26693823X</idno>
          <idno type="ROR">https://ror.org/015m7wh34</idno>
          <orgName>Université de Rennes</orgName>
          <orgName type="acronym">UR</orgName>
          <desc>
            <address>
              <addrLine>Campus de Beaulieu, 263 avenue Général Leclerc, CS 74205, 35042 RENNES CEDEX</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-rennes.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-117606" status="VALID">
          <idno type="ROR">https://ror.org/04xaa4j22</idno>
          <orgName>Institut National des Sciences Appliquées - Rennes</orgName>
          <orgName type="acronym">INSA Rennes</orgName>
          <desc>
            <address>
              <addrLine>20, avenue des Buttes de Coësmes - CS 70839 - 35708 Rennes cedex 7</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-rennes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-172265" status="VALID">
          <idno type="IdRef">05017746X</idno>
          <idno type="ISNI">0000000121680285</idno>
          <idno type="ROR">https://ror.org/04ed7fw48</idno>
          <orgName>Université de Bretagne Sud</orgName>
          <orgName type="acronym">UBS</orgName>
          <date type="start">1995-02-07</date>
          <desc>
            <address>
              <addrLine>BP 92116 - 56321 Lorient cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-ubs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-247362" status="VALID">
          <idno type="ROR">https://ror.org/03rxtdc22</idno>
          <orgName>École normale supérieure - Rennes</orgName>
          <orgName type="acronym">ENS Rennes</orgName>
          <desc>
            <address>
              <addrLine>Campus de Ker Lann - avenue Robert Schuman - 35170 Bruz</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ens-rennes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.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-481355" status="VALID">
          <idno type="IdRef">202743233</idno>
          <idno type="ROR">https://ror.org/030hj3061</idno>
          <orgName>IMT Atlantique</orgName>
          <orgName type="acronym">IMT Atlantique</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Brest : Technopôle Brest-Iroise CS 8381829238 BREST Cedex 3 -Campus Nantes : 4, rue Alfred Kastler- La chantrerie 44300 NANTES -Campus Rennes :  2 Rue de la Châtaigneraie, 35510 CESSON SEVIGNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt-atlantique.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </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>
      </listOrg>
    </back>
  </text>
</TEI>