{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2019-06-19T13:08:42.333197+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 2, "enabled": true, "entries": { "pan-plagiarism-corpus-2011.part1.rar": { "checksum": "md5:b2930f859497dd48ba5bb606d3f4a4f3", "ext": "rar", "id": "79ff581e-f273-45bc-8e1b-a9f8179465e0", "key": "pan-plagiarism-corpus-2011.part1.rar", "metadata": null, "mimetype": "application/octet-stream", "size": 1024000000 }, "pan-plagiarism-corpus-2011.part2.rar": { "checksum": "md5:b23d86c17a47d2bfbdc4c314ea5810df", "ext": "rar", "id": "49dc5d37-fc37-4768-bac8-78d46c8bbec8", "key": "pan-plagiarism-corpus-2011.part2.rar", "metadata": null, "mimetype": "application/octet-stream", "size": 703852907 } }, "order": [], "total_bytes": 1727852907 }, "id": "3250095", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/3250095/access", "access_links": "https://zenodo.org/api/records/3250095/access/links", "access_request": "https://zenodo.org/api/records/3250095/access/request", "access_users": "https://zenodo.org/api/records/3250095/access/users", "archive": "https://zenodo.org/api/records/3250095/files-archive", "archive_media": "https://zenodo.org/api/records/3250095/media-files-archive", "communities": "https://zenodo.org/api/records/3250095/communities", "communities-suggestions": "https://zenodo.org/api/records/3250095/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.3250095", "draft": "https://zenodo.org/api/records/3250095/draft", "files": "https://zenodo.org/api/records/3250095/files", "latest": "https://zenodo.org/api/records/3250095/versions/latest", "latest_html": "https://zenodo.org/records/3250095/latest", "media_files": "https://zenodo.org/api/records/3250095/media-files", "parent": "https://zenodo.org/api/records/3250094", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.3250094", "parent_html": "https://zenodo.org/records/3250094", "requests": "https://zenodo.org/api/records/3250095/requests", "reserve_doi": "https://zenodo.org/api/records/3250095/draft/pids/doi", "self": "https://zenodo.org/api/records/3250095", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.3250095", "self_html": "https://zenodo.org/records/3250095", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:3250095/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:3250095/sequence/default", "versions": "https://zenodo.org/api/records/3250095/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Bauhaus-Universit\u00e4t Weimar" } ], "person_or_org": { "family_name": "Potthast", "given_name": "Martin", "identifiers": [ { "identifier": "0000-0003-2451-0665", "scheme": "orcid" } ], "name": "Potthast, Martin", "type": "personal" } }, { "affiliations": [ { "name": "Bauhaus-Universit\u00e4t Weimar" } ], "person_or_org": { "family_name": "Stein", "given_name": "Benno", "identifiers": [ { "identifier": "0000-0001-9033-2217", "scheme": "orcid" } ], "name": "Stein, Benno", "type": "personal" } }, { "affiliations": [ { "name": "Bauhaus-Universit\u00e4t Weimar" } ], "person_or_org": { "family_name": "Eiselt", "given_name": "Andreas", "name": "Eiselt, Andreas", "type": "personal" } }, { "affiliations": [ { "name": "Universidad Polyt\u00e9cnica de Valencia" } ], "person_or_org": { "family_name": "Barr\u00f3n-Cede\u00f1o", "given_name": "Alberto", "name": "Barr\u00f3n-Cede\u00f1o, Alberto", "type": "personal" } }, { "affiliations": [ { "name": "Universidad Polyt\u00e9cnica de Valencia" } ], "person_or_org": { "family_name": "Rosso", "given_name": "Paolo", "name": "Rosso, Paolo", "type": "personal" } } ], "description": "
The PAN plagiarism corpus 2011 (PAN-PC-11) is a corpus for the evaluation of automatic plagiarism detection algorithms. For research purposes the corpus can be used free of charge.
\n\nThe PAN-PC-11 contains documents in which plagiarism has been inserted automatically as well as documents in which plagiarism has been inserted manually. The former have been constructed using a so-called random plagiarist, a computer program which constructs plagiarism according to a number of parameters, while the latter have been obtained with crowdsourcing via Amazon's Mechanical Turk.
", "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2011-06-01", "publisher": "Zenodo", "references": [ { "reference": "Benno Stein, Martin Potthast, Alberto Barr\u00f3n-Cede\u00f1o, Paolo Rosso, Efstathios Stamatatos, and Moshe Koppel. 4th International Workshop on Uncovering Plagiarism, Authorship, and Social Software Misuse (PAN 2010). SIGIR Forum, 45 (1) : 45-48, June 2011." } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "subjects": [ { "subject": "plagiarism" }, { "subject": "plagiarism detection" }, { "subject": "documents" }, { "subject": "PAN" } ], "title": "PAN Plagiarism Corpus 2011 (PAN-PC-11)" }, "parent": { "access": { "owned_by": { "user": 65747 } }, "communities": { "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2019-10-08T12:14:16.763411+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "15e3c329-b60b-4e66-86e8-8572ddccbf2c", "links": {}, "metadata": { "curation_policy": "", "page": "PAN (pan.webis.de) is a series of scientific events and shared tasks on digital text forensics and stylometry.
", "title": "PAN" }, "revision_id": 0, "slug": "pan", "updated": "2019-11-06T11:14:54.540579+00:00" }, { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2018-06-09T20:15:32.768721+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "32031607-a92a-4ccf-9ca7-6cc3a8a3426f", "links": {}, "metadata": { "description": "The Webis Group addresses challenges of the information society by conducting basic research, developing technology, and implementing and evaluating prototypes for future information systems.", "page": "Data curated by the Webis Group (webis.de)
", "title": "Webis", "type": { "id": "organization" }, "website": "https://webis.de" }, "revision_id": 1, "slug": "webis", "updated": "2023-10-16T06:20:44.424792+00:00" } ], "ids": [ "15e3c329-b60b-4e66-86e8-8572ddccbf2c", "32031607-a92a-4ccf-9ca7-6cc3a8a3426f" ] }, "id": "3250094", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3250094", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3250095", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:3250095", "provider": "oai" } }, "revision_id": 14, "stats": { "all_versions": { "data_volume": 3582571156429.0, "downloads": 3951, "unique_downloads": 1774, "unique_views": 3017, "views": 3473 }, "this_version": { "data_volume": 3575339597708.0, "downloads": 3943, "unique_downloads": 1769, "unique_views": 2997, "views": 3451 } }, "status": "published", "updated": "2022-06-11T07:06:00.720042+00:00", "versions": { "index": 1, "is_latest": true } }