{
  "access": {
    "embargo": {
      "active": false,
      "reason": null
    },
    "files": "public",
    "record": "public",
    "status": "open"
  },
  "created": "2025-04-28T12:50:18.286004+00:00",
  "custom_fields": {},
  "deletion_status": {
    "is_deleted": false,
    "status": "P"
  },
  "files": {
    "count": 1,
    "enabled": true,
    "entries": {
      "wikipedia-20250401.xml.bz2": {
        "access": {
          "hidden": false
        },
        "checksum": "md5:5a5a3f8caa469dcf72034c81679fa294",
        "ext": "bz2",
        "id": "4abd3178-a496-4e8c-8b86-a13e9d52e05b",
        "key": "wikipedia-20250401.xml.bz2",
        "links": {
          "content": "https://zenodo.org/api/records/15296728/files/wikipedia-20250401.xml.bz2/content",
          "self": "https://zenodo.org/api/records/15296728/files/wikipedia-20250401.xml.bz2"
        },
        "metadata": {},
        "mimetype": "application/x-bzip2",
        "size": 2804664490,
        "storage_class": "L"
      }
    },
    "order": [],
    "total_bytes": 2804664490
  },
  "id": "15296728",
  "is_draft": false,
  "is_published": true,
  "links": {
    "access": "https://zenodo.org/api/records/15296728/access",
    "access_grants": "https://zenodo.org/api/records/15296728/access/grants",
    "access_links": "https://zenodo.org/api/records/15296728/access/links",
    "access_request": "https://zenodo.org/api/records/15296728/access/request",
    "access_users": "https://zenodo.org/api/records/15296728/access/users",
    "archive": "https://zenodo.org/api/records/15296728/files-archive",
    "archive_media": "https://zenodo.org/api/records/15296728/media-files-archive",
    "communities": "https://zenodo.org/api/records/15296728/communities",
    "communities-suggestions": "https://zenodo.org/api/records/15296728/communities-suggestions",
    "doi": "https://doi.org/10.5281/zenodo.15296728",
    "draft": "https://zenodo.org/api/records/15296728/draft",
    "file_modification": "https://zenodo.org/api/records/15296728/file-modification",
    "files": "https://zenodo.org/api/records/15296728/files",
    "latest": "https://zenodo.org/api/records/15296728/versions/latest",
    "latest_html": "https://zenodo.org/records/15296728/latest",
    "media_files": "https://zenodo.org/api/records/15296728/media-files",
    "parent": "https://zenodo.org/api/records/7568490",
    "parent_doi": "https://doi.org/10.5281/zenodo.7568490",
    "parent_doi_html": "https://zenodo.org/doi/10.5281/zenodo.7568490",
    "parent_html": "https://zenodo.org/records/7568490",
    "preview_html": "https://zenodo.org/records/15296728?preview=1",
    "quota_increase": "https://zenodo.org/api/records/15296728/quota-increase",
    "request_deletion": "https://zenodo.org/api/records/15296728/request-deletion",
    "requests": "https://zenodo.org/api/records/15296728/requests",
    "reserve_doi": "https://zenodo.org/api/records/15296728/draft/pids/doi",
    "self": "https://zenodo.org/api/records/15296728",
    "self_doi": "https://doi.org/10.5281/zenodo.15296728",
    "self_doi_html": "https://zenodo.org/doi/10.5281/zenodo.15296728",
    "self_html": "https://zenodo.org/records/15296728",
    "self_iiif_manifest": "https://zenodo.org/api/iiif/record:15296728/manifest",
    "self_iiif_sequence": "https://zenodo.org/api/iiif/record:15296728/sequence/default",
    "versions": "https://zenodo.org/api/records/15296728/versions"
  },
  "media_files": {
    "count": 0,
    "enabled": false,
    "entries": {},
    "order": [],
    "total_bytes": 0
  },
  "metadata": {
    "creators": [
      {
        "affiliations": [
          {
            "name": "BBAW"
          }
        ],
        "person_or_org": {
          "family_name": "Nolda",
          "given_name": "Andreas",
          "identifiers": [
            {
              "identifier": "0000-0003-4532-8256",
              "scheme": "orcid"
            }
          ],
          "name": "Nolda, Andreas",
          "type": "personal"
        }
      }
    ],
    "description": "<p>Das <a href=\"https://www.dwds.de/d/korpora/wikipedia\">Wikipedia-Korpus</a> auf <a href=\"http://www.dwds.de\">dwds.de</a> enth&auml;lt Volltexte aus den Artikeln aus der <a href=\"https://de.wikipedia.org/wiki/Deutschsprachige_Wikipedia\">deutschsprachigen Wikipedia</a> auf der Basis des <a href=\"https://dumps.wikimedia.org/dewiki/20250401/\">Datenbank-Abzugs vom 1.4.\u202f2025</a>. Texte aus anderen Seitenarten (Diskussionen etc.) wurden nicht aufgenommen.</p>\n<p>Das Korpus wurde so konzipiert, dass es sich insbesondere f&uuml;r die Recherche nach (fach)sprachlichen lexikographischen Belegen eignet. Deshalb wurden bei der automatischen Korpuskuration die Artikeltexte so weit wie m&ouml;glich um Textteile bereinigt, die nicht satzf&ouml;rmig oder nicht deutschsprachig sind. Dies betrifft unter anderem &Uuml;berschriften, Tabellen, Literaturangaben und fremdsprachliche Zitate, soweit diese in den Wikipedia-Quellen als solche ausgezeichnet sind.</p>\n<p>Verf&uuml;gbar sind hier die Quellen des Wikipedia-Korpus auf <a href=\"http://www.dwds.de\">dwds.de</a> im XML/TEI-Format als teiCorpus-Datei. Wie die originalen Wikipedia-Artikel stehen sie unter der Lizenz <a href=\"https://creativecommons.org/licenses/by-sa/4.0/\">\"Creative Commons Attribution/Share Alike\"</a>.</p>",
    "languages": [
      {
        "id": "deu",
        "title": {
          "en": "German"
        }
      }
    ],
    "publication_date": "2025-04-28",
    "publisher": "Zenodo",
    "related_identifiers": [
      {
        "identifier": "10.5281/zenodo.7568518",
        "relation_type": {
          "id": "isreferencedby",
          "title": {
            "de": "Wird referenziert von",
            "en": "Is referenced by"
          }
        },
        "resource_type": {
          "id": "dataset",
          "title": {
            "de": "Datensatz",
            "en": "Dataset"
          }
        },
        "scheme": "doi"
      }
    ],
    "resource_type": {
      "id": "dataset",
      "title": {
        "de": "Datensatz",
        "en": "Dataset"
      }
    },
    "rights": [
      {
        "description": {
          "en": "Permits almost any use subject to providing credit and license notice. Frequently used for media assets and educational materials. The most common license for Open Access scientific publications. Not recommended for software."
        },
        "icon": "cc-by-sa-icon",
        "id": "cc-by-sa-4.0",
        "props": {
          "scheme": "spdx",
          "url": "https://creativecommons.org/licenses/by-sa/4.0/legalcode"
        },
        "title": {
          "en": "Creative Commons Attribution Share Alike 4.0 International"
        }
      }
    ],
    "subjects": [
      {
        "subject": "Wikipedia"
      },
      {
        "subject": "Corpus"
      },
      {
        "subject": "German"
      },
      {
        "subject": "XML"
      },
      {
        "subject": "TEI"
      },
      {
        "subject": "DWDS"
      },
      {
        "subject": "ZDL"
      },
      {
        "subject": "BBAW"
      }
    ],
    "title": "Wikipedia-Korpus: Korpusquellen der deutschsprachigen Wikipedia im TEI-Format",
    "version": "20250401"
  },
  "parent": {
    "access": {
      "owned_by": {
        "user": "487234"
      },
      "settings": {
        "accept_conditions_text": null,
        "allow_guest_requests": false,
        "allow_user_requests": false,
        "secret_link_expiration": 0
      }
    },
    "communities": {
      "default": "df4621d3-554e-49e1-ac37-93eafff41304",
      "entries": [
        {
          "access": {
            "member_policy": "open",
            "members_visibility": "public",
            "record_submission_policy": "open",
            "review_policy": "closed",
            "visibility": "public"
          },
          "children": {
            "allow": false
          },
          "created": "2023-11-30T09:23:19.870688+00:00",
          "custom_fields": {},
          "deletion_status": {
            "is_deleted": false,
            "status": "P"
          },
          "id": "df4621d3-554e-49e1-ac37-93eafff41304",
          "links": {},
          "metadata": {
            "title": "Zentrum f\u00fcr digitale Lexikographie der deutschen Sprache",
            "type": {
              "id": "organization"
            },
            "website": "https://www.zdl.org/"
          },
          "revision_id": 4,
          "slug": "zdl",
          "updated": "2023-11-30T09:28:27.587256+00:00"
        }
      ],
      "ids": [
        "df4621d3-554e-49e1-ac37-93eafff41304"
      ]
    },
    "id": "7568490",
    "pids": {
      "doi": {
        "client": "datacite",
        "identifier": "10.5281/zenodo.7568490",
        "provider": "datacite"
      }
    }
  },
  "pids": {
    "doi": {
      "client": "datacite",
      "identifier": "10.5281/zenodo.15296728",
      "provider": "datacite"
    },
    "oai": {
      "identifier": "oai:zenodo.org:15296728",
      "provider": "oai"
    }
  },
  "revision_id": 4,
  "stats": {
    "all_versions": {
      "data_volume": 1808106970055.0,
      "downloads": 674,
      "unique_downloads": 647,
      "unique_views": 1990,
      "views": 2099
    },
    "this_version": {
      "data_volume": 162670540420.0,
      "downloads": 58,
      "unique_downloads": 47,
      "unique_views": 63,
      "views": 63
    }
  },
  "status": "published",
  "swh": {},
  "updated": "2025-04-28T12:50:18.542466+00:00",
  "versions": {
    "index": 11,
    "is_latest": false
  }
}