<?xml version="1.0" encoding="UTF-8"?>
<resource xmlns="http://datacite.org/schema/kernel-4" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.5/metadata.xsd">
  <identifier identifierType="Handle">21.15109/ARP/VWQFD2</identifier>
  <creators>
    <creator>
      <creatorName nameType="Personal">Micsik, András</creatorName>
      <givenName>András</givenName>
      <familyName>Micsik</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org">https://orcid.org/0000-0001-9859-9186</nameIdentifier>
      <affiliation>HUN-REN SZTAKI</affiliation>
    </creator>
    <creator>
      <creatorName nameType="Personal">Tanácsi, Roland</creatorName>
      <givenName>Roland</givenName>
      <familyName>Tanácsi</familyName>
      <affiliation>HUN-REN SZTAKI</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Subject categorisation experiments with AI in MTMT</title>
  </titles>
  <publisher>ARP</publisher>
  <publicationYear>2026</publicationYear>
  <subjects>
    <subject>Computer and Information Science</subject>
    <subject>subject classification</subject>
    <subject>scientific categorization</subject>
    <subject>transformer models</subject>
    <subject>Support Vector Classifier</subject>
    <subject>data cleaning</subject>
    <subject>large language models</subject>
    <subject schemeURI="http://data.europa.eu/8mn/euroscivoc/4c8f4b46-6f5c-41d9-9079-7de85c16431d" subjectScheme="EuroSciVoc">artificial intelligence</subject>
  </subjects>
  <contributors>
    <contributor contributorType="ContactPerson">
      <contributorName nameType="Personal">Micsik, András</contributorName>
      <givenName>András</givenName>
      <familyName>Micsik</familyName>
      <affiliation>HUN-REN SZTAKI</affiliation>
    </contributor>
  </contributors>
  <dates>
    <date dateType="Created">2025-11-15</date>
    <date dateType="Submitted">2026-02-03</date>
    <date dateType="Available">2026-05-08</date>
    <date dateType="Updated">2026-05-12</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <relatedIdentifiers>
    <relatedIdentifier relationType="IsSupplementTo" relatedIdentifierType="DOI">10.3390/BDCC10050151</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/OLMFQR</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/NF3M7P</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/TUU2A3</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/GQ2QTF</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/UMCK7O</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/RSDNVR</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/YSHVT5</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/WF4GHD</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/2NLZ4Q</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/SKUVFP</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/2Q93LH</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/W4KTNW</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/AKX2F6</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/S6CBTZ</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/WMCKQO</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/MV8MX6</relatedIdentifier>
    <relatedIdentifier relationType="HasPart" relatedIdentifierType="Handle">21.15109/ARP/VWQFD2/4BGUBA</relatedIdentifier>
  </relatedIdentifiers>
  <sizes>
    <size>6446</size>
    <size>2394</size>
    <size>4075</size>
    <size>59377</size>
    <size>12681</size>
    <size>99</size>
    <size>3258</size>
    <size>317</size>
    <size>15114</size>
    <size>5867</size>
    <size>3288</size>
    <size>2267</size>
    <size>4807</size>
    <size>4243584</size>
    <size>1818752</size>
    <size>25015</size>
    <size>2015902080</size>
    <size>182</size>
  </sizes>
  <formats>
    <format>text/x-python</format>
    <format>application/json</format>
    <format>text/csv</format>
    <format>text/csv</format>
    <format>text/csv</format>
    <format>text/plain</format>
    <format>text/csv</format>
    <format>text/plain</format>
    <format>text/csv</format>
    <format>text/csv</format>
    <format>text/csv</format>
    <format>text/csv</format>
    <format>text/x-python</format>
    <format>application/octet-stream</format>
    <format>application/octet-stream</format>
    <format>text/csv</format>
    <format>application/octet-stream</format>
    <format>text/plain</format>
  </formats>
  <version>2.0</version>
  <rightsList>
    <rights rightsURI="info:eu-repo/semantics/openAccess"/>
    <rights rightsURI="http://creativecommons.org/licenses/by-nc-nd/4.0" xml:lang="en">Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">Code, sample data and results for subject categorisation experiments with AI in MTMT</description>
    <description descriptionType="TechnicalInfo">Python, 3.10</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>NKFIH</funderName>
      <awardNumber>RRF-2.3.1-21-2022-00004</awardNumber>
    </fundingReference>
  </fundingReferences>
</resource>
