<?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>2026-10-14T08:39:26Z</responseDate>
  <request identifier="oai:figshare.com:article/33952177" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/33952177</identifier>
        <datestamp>2026-09-21T11:59:03Z</datestamp>
        <setSpec>category_28942</setSpec>
        <setSpec>category_28951</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>Processed datos.gob.es Collection for Tabular Dataset Retrieval Benchmarking</dc:title>
          <dc:creator>José Melgarejo Hernández (25083115)</dc:creator>
          <dc:subject>Database systems</dc:subject>
          <dc:subject>Information retrieval and web search</dc:subject>
          <dc:subject>datos.gob.es</dc:subject>
          <dc:subject>open data</dc:subject>
          <dc:subject>tabular data</dc:subject>
          <dc:subject>public sector information</dc:subject>
          <dc:description>&lt;p dir="ltr"&gt;This dataset contains the processed datos.gob.es collection used for tabular dataset retrieval experiments in the paper “LLM-Assisted Benchmark Construction in Tabular Dataset Retrieval”.  &lt;/p&gt;&lt;p dir="ltr"&gt;The collection is derived from a datos.gob.es crawl snapshot dated 2026-04-15. After filtering, deduplication, resource validation, and tabular-content reduction, the processed collection contains 56,983 searchable datasets. For each retained dataset, the collection includes the normalized metadata record and the selected tabular resource used by the retrieval backend. &lt;/p&gt;&lt;p dir="ltr"&gt;The complete raw portal crawl is not distributed. This release provides the processed collection used by the benchmark retrieval pipeline, enabling reconstruction of the local retrieval indexes and candidate pools described in the accompanying artifact.&lt;/p&gt;</dc:description>
          <dc:date>2026-09-21T11:59:03Z</dc:date>
          <dc:type>Dataset</dc:type>
          <dc:type>Dataset</dc:type>
          <dc:identifier>10.6084/m9.figshare.33952177.v1</dc:identifier>
          <dc:relation>https://figshare.com/articles/dataset/Processed_datos_gob_es_Collection_for_Tabular_Dataset_Retrieval_Benchmarking/33952177</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
