<?xml version="1.0" encoding="utf-8" standalone="no"?>
<?xml-stylesheet type='text/xsl' href='/oai-pmh/oai2.xsl'?>
<OAI-PMH xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd" xmlns="http://www.openarchives.org/OAI/2.0/">
  <responseDate>2026-10-06</responseDate>
  <request verb="GetRecord" identifier="oai:researchdata.se:2026-94/1" metadataPrefix="oai_dc">https://api.researchdata.se/oai-pmh</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:researchdata.se:2026-94/1</identifier>
        <datestamp>2026-03-26</datestamp>
        <setSpec>subject:ssif:60303</setSpec>
        <setSpec>subject:ssif:50805</setSpec>
        <setSpec>subject:ssif:10210</setSpec>
        <setSpec>subject:ssif:102</setSpec>
        <setSpec>subject:ssif:508</setSpec>
        <setSpec>subject:ssif:603</setSpec>
        <setSpec>subject:ssif:1</setSpec>
        <setSpec>subject:ssif:5</setSpec>
        <setSpec>subject:ssif:6</setSpec>
        <setSpec>principal:slug:linnaeus-university</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:type>info:eu-repo/semantics/other</dc:type>
          <dc:type>http://purl.org/dc/dcmitype/Dataset</dc:type>
          <dc:identifier>https://doi.org/10.5878/npy2-hk17</dc:identifier>
          <dc:title xml:lang="en">Multi-model Interreligious Roleplay Archive</dc:title>
          <dc:title xml:lang="sv">Multi-model Interreligious Roleplay Archive</dc:title>
          <dc:creator>https://orcid.org/0000-0002-1633-9178</dc:creator>
          <dc:creator>https://orcid.org/0000-0003-0785-4714</dc:creator>
          <dc:creator>https://orcid.org/0000-0002-2232-2292</dc:creator>
          <dc:creator>https://orcid.org/0000-0002-4425-0541</dc:creator>
          <dc:subject xml:lang="en">Media</dc:subject>
          <dc:subject xml:lang="sv">Media</dc:subject>
          <dc:subject xml:lang="en">Information society</dc:subject>
          <dc:subject xml:lang="sv">Informationssamhället</dc:subject>
          <dc:subject xml:lang="en">Information technology</dc:subject>
          <dc:subject xml:lang="sv">Informationsteknik</dc:subject>
          <dc:subject xml:lang="en">Cultural and national identity</dc:subject>
          <dc:subject xml:lang="sv">Kulturell och nationell identitet</dc:subject>
          <dc:subject xml:lang="en">Religion and values</dc:subject>
          <dc:subject xml:lang="sv">Religion och värderingar</dc:subject>
          <dc:subject xml:lang="en">Religious Studies</dc:subject>
          <dc:subject xml:lang="sv">Religionsvetenskap</dc:subject>
          <dc:subject xml:lang="en">Information Studies</dc:subject>
          <dc:subject xml:lang="sv">Biblioteks- och informationsvetenskap</dc:subject>
          <dc:subject xml:lang="en">Artificial Intelligence</dc:subject>
          <dc:subject xml:lang="sv">Artificiell intelligens</dc:subject>
          <dc:description xml:lang="en">The dataset consists of 960 outputs collected in 2025 from various large language models (LLMs). The LLMs were given a religious question to answer as one of 12 theological personas (6 Christian and 6 Muslim). Four (4) different models were queried: Claude Sonnet 4, Gemini 2.5 Flash, GPT4o,  and GPT5. Two (2) different channels were used for prompting and collecting outputs: API and web user-interface. Ten (10) outputs were collected for each combination of the preceding parameters. The data is available as a xlsx file. The prompt and personas are available as a PDF.</dc:description>
          <dc:description xml:lang="sv">Datamängden består av 960 svar som samlades in år 2025 från olika stora språkmodeller (LLM). Språkmodellerna fick en religiös fråga att besvara i rollen som en av 12 teologiska personligheter (6 kristna och 6 muslimska). Fyra (4) olika modeller tillfrågades: Claude Sonnet 4, Gemini 2.5 Flash, GPT4o och GPT5. Två (2) olika kanaler användes för att ställa frågor och samla in svar: API och webbgränssnitt. Tio (10) svar samlades in för varje kombination av de ovanstående parametrarna. Data finns tillgängliga som en xlsx-fil. Frågorna och rollfigurerna finns tillgängliga som en PDF-fil.</dc:description>
          <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
          <dc:rights>https://creativecommons.org/licenses/by/4.0/</dc:rights>
          <dc:publisher xml:lang="en">Linnaeus University</dc:publisher>
          <dc:publisher xml:lang="sv">Linnéuniversitetet</dc:publisher>
          <dc:date>2026-03-26T08:28:21.184781Z</dc:date>
          <dc:language>eng</dc:language>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>