{"id":"https://openalex.org/W4393880093","doi":"https://doi.org/10.5281/zenodo.7752615","title":"unarXive: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network (open subset)","display_name":"unarXive: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network (open subset)","publication_year":2023,"publication_date":"2023-03-27","ids":{"openalex":"https://openalex.org/W4393880093","doi":"https://doi.org/10.5281/zenodo.7752615"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.7752615","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.7752615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.7752615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035495986","display_name":"Tarek Saier","orcid":"https://orcid.org/0000-0001-5028-0109"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Saier, Tarek","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0001-5028-0109","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051563182","display_name":"Johan Krause","orcid":"https://orcid.org/0000-0002-5080-3587"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Krause, Johan","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-5080-3587","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031600582","display_name":"Michael F\u00e4rber","orcid":"https://orcid.org/0000-0001-5458-8645"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"F\u00e4rber, Michael","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0001-5458-8645","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.8686000108718872,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.8686000108718872,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8101000189781189,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7775999903678894,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6704866886138916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6620585918426514},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.6331918835639954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5822096467018127},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5255053043365479},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15799665451049805}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6704866886138916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6620585918426514},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6331918835639954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5822096467018127},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5255053043365479},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15799665451049805}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.7752615","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.7752615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.7752615","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.7752615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Description":[0],"unarXive":[1],"is":[2,27,92,121],"a":[3,22],"scholarly":[4],"data":[5,26,41,82,119],"set":[6,120],"containing":[7],"publications'":[8],"structured":[9],"full-text,":[10],"annotated":[11],"in-text":[12],"citations,":[13],"linked":[14],"non-text":[15],"content":[16],"(mathematical":[17],"notation,":[18],"figure/table":[19],"captions)":[20],"and":[21,35],"citation":[23],"network.":[24],"The":[25,113],"generated":[28,42],"from":[29,43,104],"all":[30,100],"LaTeX":[31],"sources":[32],"on":[33],"arXiv":[34],"therefore":[36],"of":[37,50,96],"higher":[38],"quality":[39],"than":[40],"PDF":[44],"files.":[45],"Typical":[46],"uses":[47],"are":[48],"Training":[49],"ML":[51],"models":[52],"(citation":[53],"recommendation,":[54],"summarization,":[55],"LLMs)":[56],"Citation":[57],"context":[58],"analysis":[59],"Bibliographic":[60],"analyses":[61],"Access":[62],"\u250f\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2513\u2503":[63],"D":[64,71],"O":[65,69],"W":[66],"N":[67],"L":[68,76],"A":[70,73],"S":[72],"M":[74],"P":[75],"E":[77],"\u2503\u2517\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u2501\u251b":[78],"Regarding":[79],"the":[80,86,93,109,118],"full":[81,110],"set,":[83],"please":[84],"note":[85],"following:":[87],"Note:":[88],"this":[89],"Zenodo":[90],"record":[91],"\"open":[94],"subset\"":[95],"unarXive,":[97],"which":[98],"contains":[99],"permissively":[101],"licensed":[102],"papers":[103],"arXiv.org.":[105],"You":[106],"can":[107],"find":[108],"version":[111],"here.":[112],"code":[114],"used":[115],"for":[116],"generating":[117],"publicly":[122],"available.":[123]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
