{
  "altLabels": [
    "Document Corpus",
    "Document Collection"
  ],
  "artifactKind": "Dataset",
  "definition": "A collection of documents, passages, web pages, items, or other retrievable units used for search, retrieval, training, or evaluation.",
  "derivedRelations": [
    {
      "target": "browsecomp-plus",
      "type": "related"
    }
  ],
  "distinctions": [
    {
      "reason": "A corpus is a collection of retrievable items; BEIR is a benchmark suite aggregating multiple evaluation datasets.",
      "statement": "Corpus is not BEIR.",
      "target": "beir",
      "targetLabel": "BEIR",
      "targetUri": "https://id.searchplex.net/beir/"
    },
    {
      "reason": "A corpus contains retrievable items; qrels contain relevance judgments for query-item pairs.",
      "statement": "Corpus is not Qrels.",
      "target": "qrels",
      "targetLabel": "Qrels",
      "targetUri": "https://id.searchplex.net/qrels/"
    },
    {
      "reason": "A corpus is the searchable collection; a test collection also includes queries or topics and relevance judgments.",
      "statement": "Corpus is not Test Collection.",
      "target": "test-collection",
      "targetLabel": "Test Collection",
      "targetUri": "https://id.searchplex.net/test-collection/"
    }
  ],
  "id": "corpus",
  "kind": "Artifact",
  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
  "links": [
    {
      "label": "An example information retrieval problem",
      "type": "canonicalSurvey",
      "url": "https://nlp.stanford.edu/IR-book/html/htmledition/an-example-information-retrieval-problem-1.html"
    },
    {
      "label": "ir_datasets catalog",
      "type": "officialHomepage",
      "url": "https://ir-datasets.com/"
    }
  ],
  "modifiedAt": "2026-09-14T06:43:46Z",
  "prefLabel": "Corpus",
  "publisher": {
    "name": "Searchplex",
    "url": "https://searchplex.net/"
  },
  "relations": [
    {
      "note": "A corpus is a collection of retrievable items; BEIR is a benchmark suite aggregating multiple evaluation datasets.",
      "target": "beir",
      "type": "notEquivalentTo"
    },
    {
      "note": "A corpus contains retrievable items; qrels contain relevance judgments for query-item pairs.",
      "target": "qrels",
      "type": "notEquivalentTo"
    },
    {
      "note": "A corpus is the searchable collection; a test collection also includes queries or topics and relevance judgments.",
      "target": "test-collection",
      "type": "notEquivalentTo"
    },
    {
      "target": "test-collection",
      "type": "partOf"
    },
    {
      "target": "document-retrieval",
      "type": "related"
    },
    {
      "target": "ir-datasets",
      "type": "related"
    },
    {
      "target": "passage-retrieval",
      "type": "related"
    },
    {
      "target": "qrels",
      "type": "related"
    }
  ],
  "representations": {
    "html": "https://id.searchplex.net/corpus/",
    "json": "https://id.searchplex.net/corpus.json",
    "jsonld": "https://id.searchplex.net/corpus.jsonld"
  },
  "scheme": "https://id.searchplex.net/scheme/",
  "scopeNote": "In IR evaluation, the corpus is the searchable collection component of a test collection. The bare term collection is ambiguous: it may mean a corpus or searchable document collection, while test collection usually means the full evaluation package with corpus, topics or queries, and relevance judgments.",
  "status": "published",
  "terms": [
    {
      "community": "academic",
      "label": "Collection",
      "usage": "nearSynonym"
    },
    {
      "community": "academic",
      "label": "Search Collection",
      "usage": "nearSynonym"
    }
  ],
  "uri": "https://id.searchplex.net/corpus/"
}