<?xml version='1.0' encoding='utf-8'?>
<?xml-stylesheet type="text/xsl" href="/v2/static/oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" 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">
  <responseDate>2026-10-10T22:21:25Z</responseDate>
  <request identifier="oai:figshare.com:article/33974170" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/33974170</identifier>
        <datestamp>2026-09-24T01:55:53Z</datestamp>
        <setSpec>category_28822</setSpec>
        <setSpec>item_type_3</setSpec>
        <setSpec>month_year_09_2026</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>network compression</dc:title>
          <dc:creator>Lai Wei (25098484)</dc:creator>
          <dc:subject>Applied computing not elsewhere classified</dc:subject>
          <dc:subject>Graph clustering</dc:subject>
          <dc:subject>community detection analysis</dc:subject>
          <dc:subject>data compression algorithm</dc:subject>
          <dc:description>&lt;p dir="ltr"&gt;BIB (https://www.kaggle.com/datasets/oswinrh/bible} is a long-form literary corpus with strong lexical and discourse repetition; ENR (https://www.cs.cmu.edu/~enron) is a semi-structured email collection with headers and user-specific writing styles; SUB (https://object.pouta.csc.fi/OPUS-OpenSubtitles/v2018/mono/en.txt.gz} consists of short conversational sentences with frequent phrase repetition; and LOG (\url{https://zenodo.org/records/3227177/files/Thunderbird.tar.gz}) contains machine-generated records with recurring templates and variable fields. BRV (https://www.kaggle.com/datasets/mohamedbakhet/amazon-books-reviews}, AIT (https://www.kaggle.com/datasets/shanegerami/ai-vs-human-text), MOV (https://www.kaggle.com/datasets/jrobischon/wikipedia-movie-plots), and HS (https://www.kaggle.com/datasets/thuynyle/redfin-housing-market-data) provide additional heterogeneous sources, including book reviews, AI and human texts, movie plots, and housing records.&lt;/p&gt;</dc:description>
          <dc:date>2026-09-24T01:55:53Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.6084/m9.figshare.33974170.v1</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/network_compression/33974170</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
