{"id":"https://openalex.org/W4393698249","doi":"https://doi.org/10.5281/zenodo.4313164","title":"unarXive: A Large Scholarly Data Set with Publications' Full-Text, Annotated In-Text Citations, and Links to Metadata","display_name":"unarXive: A Large Scholarly Data Set with Publications' Full-Text, Annotated In-Text Citations, and Links to Metadata","publication_year":2020,"publication_date":"2020-12-09","ids":{"openalex":"https://openalex.org/W4393698249","doi":"https://doi.org/10.5281/zenodo.4313164"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.4313164","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4313164","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.4313164","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/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Saier, Tarek","raw_affiliation_strings":["University of Freiburg"],"raw_orcid":"https://orcid.org/0000-0001-5028-0109","affiliations":[{"raw_affiliation_string":"University of Freiburg","institution_ids":["https://openalex.org/I161046081"]}]},{"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/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"F\u00e4rber, Michael","raw_affiliation_strings":["University of Freiburg"],"raw_orcid":"https://orcid.org/0000-0001-5458-8645","affiliations":[{"raw_affiliation_string":"University of Freiburg","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.14059999585151672,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.14059999585151672,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.13609999418258667,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.12600000202655792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8625565767288208},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7013418674468994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6169382929801941},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5983908176422119},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5898120999336243},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3936813771724701},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3524860143661499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08654618263244629}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8625565767288208},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7013418674468994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169382929801941},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5983908176422119},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5898120999336243},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3936813771724701},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3524860143661499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08654618263244629},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.4313164","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4313164","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.4313164","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4313164","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/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2027108423","https://openalex.org/W1855666948","https://openalex.org/W2758561209","https://openalex.org/W1548095260","https://openalex.org/W2781711915","https://openalex.org/W2112817590","https://openalex.org/W1555291398"],"abstract_inverted_index":{"Description":[0],"unarXive":[1,224],"is":[2,19,59,101,153,178,204,225,261],"a":[3,14,81,154],"scholarly":[4],"data":[5,18,33,57,139,177,202,211],"set":[6,58,140,203,212],"containing":[7],"publications'":[8],"full-text,":[9],"annotated":[10],"in-text":[11],"citations,":[12],"and":[13,27,67,87,116,145,248,283],"citation":[15],"network.":[16],"The":[17,196,258],"generated":[20,34,161],"from":[21,35,162],"all":[22,62,163],"LaTeX":[23],"sources":[24],"on":[25,61,68,188,217],"arXiv":[26,63,275],"therefore":[28],"of":[29,55,74,105,157,164,175,223],"higher":[30],"quality":[31],"than":[32],"PDF":[36],"files.":[37],"Typical":[38],"use":[39,174,191],"cases":[40],"are":[41,213],"Citation":[42,44,284],"recommendation":[43],"context":[45],"analysis":[46],"Bibliographic":[47],"analyses":[48],"Reference":[49],"string":[50],"parsing":[51],"This":[52,98,220],"version":[53,104,113,156,222,260],"(v3)":[54],"our":[56,210],"based":[60],"publications":[64],"until":[65],"2020-07-31":[66],"the":[69,84,88,110,137,147,176,181,201,228,264],"Microsoft":[70],"Academic":[71],"Graph":[72],"as":[73],"2020-08-18.":[75],"As":[76],"additional":[77],"contribution,":[78],"we":[79],"included":[80],"table":[82],"with":[83,180,242],"publication":[85],"date":[86],"scientific":[89],"discipline":[90],"for":[91,94,199,209,278],"each":[92],"paper":[93],"easier":[95],"filtering.":[96],"Note:":[97,149],"Zenodo":[99,151],"record":[100,152],"an":[102,142,255,289],"old":[103],"unarXive.":[106],"You":[107],"can":[108],"find":[109],"most":[111],"recent":[112],"at":[114,215],"https://zenodo.org/record/7752754":[115],"https://zenodo.org/record/7752615":[117],"Access":[118],"\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":[119],"D":[120,127],"O":[121,125],"W":[122],"N":[123],"L":[124,132],"A":[126,129,237],"S":[128],"M":[130],"P":[131],"E":[133],"\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":[134],"To":[135],"download":[136],"whole":[138],"send":[141],"access":[143],"request":[144],"note":[146],"following:":[148],"this":[150],"\"full\"":[155],"unarXive,":[158],"which":[159],"was":[160],"arXiv.org":[165],"including":[166],"non-permissively":[167],"licensed":[168],"papers.":[169],"Make":[170],"sure":[171],"that":[172],"your":[173],"compliant":[179],"paper's":[182],"licensing":[183],"terms.\u00b9":[184],"\u00b9":[185],"For":[186],"information":[187],"papers'":[189],"licenses":[190],"arXiv's":[192],"bulk":[193],"metadata":[194],"access.":[195],"code":[197],"used":[198],"generating":[200],"publicly":[205],"available.":[206],"Usage":[207],"examples":[208],"provided":[214],"here":[216],"GitHub.":[218],"Citing":[219],"initial":[221],"described":[226,262],"in":[227,263],"following":[229,265],"journal":[230],"article.":[231],"Tarek":[232,268],"Saier,":[233,269],"Michael":[234,270],"F\u00e4rber:":[235],"\"unarXive:":[236],"Large":[238],"Scholarly":[239],"Data":[240],"Set":[241],"Publications'":[243],"Full-Text,":[244],"Annotated":[245],"In-Text":[246],"Citations,":[247],"Links":[249],"to":[250,254,288],"Metadata\",":[251],"Scientometrics,":[252],"2020,[link":[253],"author":[256,290],"copy]":[257,291],"updated":[259],"conference":[266],"paper.":[267],"F\u00e4rber.":[271],"\"unarXive":[272],"2022:":[273],"All":[274],"Publications":[276],"Pre-Processed":[277],"NLP,":[279],"Including":[280],"Structured":[281],"Full-Text":[282],"Network\",":[285],"JCDL":[286],"2023.[link":[287]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
