<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>10064</id>
    <completedYear/>
    <publishedYear>2026</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2025-07-22</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Mapping the Web of Science, a large-scale graph and text-based dataset with LLM embeddings</title>
    <abstract language="eng">Large text data sets, such as publications, websites, and other text-based media, inherit two distinct types of features: (1) the text itself, its information conveyed through semantics, and (2) its relationship to other texts through links, references, or shared attributes. While the latter can be described as a graph structure and can be handled by a range of established algorithms for classification and prediction, the former has recently gained new potential through the use of LLM embedding models.&#13;
Demonstrating these possibilities and their practicability, we investigate the Web of Science dataset, containing ~56 million scientific publications through the lens of our proposed embedding method, revealing a self-structured landscape of texts.</abstract>
    <parentTitle language="deu">Operations Research Proceedings 2025. OR 2025</parentTitle>
    <identifier type="issn">1438-0064</identifier>
    <identifier type="doi">10.12752/10064</identifier>
    <identifier type="urn">urn:nbn:de:0297-zib-100646</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="SubmissionStatus">accepted for publication</enrichment>
    <enrichment key="PeerReviewed">yes</enrichment>
    <enrichment key="Series">Lecture Notes in Operations Research</enrichment>
    <enrichment key="AcceptedDate">2026-01-18</enrichment>
    <author>Tim Kunt</author>
    <submitter>Tim Kunt</submitter>
    <author>Annika Buchholz</author>
    <author>Imene Khebouri</author>
    <author>Thorsten Koch</author>
    <author>Ida Litzel</author>
    <author>Thi Huong Vu</author>
    <series>
      <title>ZIB-Report</title>
      <number>25-11</number>
    </series>
    <collection role="institutes" number="sis">Digital Data and Information for Society, Science, and Culture</collection>
    <collection role="persons" number="koch">Koch, Thorsten</collection>
    <collection role="institutes" number="aim">Applied Algorithmic Intelligence Methods</collection>
    <collection role="persons" number="kunt">Kunt, Tim</collection>
    <collection role="persons" number="buchholz">Buchholz, Annika</collection>
    <collection role="persons" number="huong.vu">Vu, Thi Huong</collection>
    <collection role="projects" number="FAN">FAN</collection>
    <collection role="persons" number="khebouri">Khebouri, Imene</collection>
    <collection role="institutes" number="aopt">Applied Optimization</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/10064/ZIB_Report_v4.pdf</file>
  </doc>
</export-example>
