{"id":"https://openalex.org/W2941922035","doi":"https://doi.org/10.5281/zenodo.2609187","title":"Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks","display_name":"Bibliometric-Enhanced arXiv: A Data Set for Paper-Based and Citation-Based Tasks","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2941922035","doi":"https://doi.org/10.5281/zenodo.2609187","mag":"2941922035"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.2609187","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2609187","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.2609187","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":null,"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":18,"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/T11719","display_name":"Data Quality and Management","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9890999794006348,"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/citation","display_name":"Citation","score":0.7773202657699585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7311275601387024},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6453172564506531},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6125674843788147},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5709738731384277},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5411301255226135},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5093578100204468},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5052796006202698},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47675666213035583},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28607654571533203},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2596210241317749},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08909478783607483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08574649691581726},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08317002654075623}],"concepts":[{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.7773202657699585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311275601387024},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6453172564506531},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6125674843788147},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5709738731384277},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5411301255226135},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5093578100204468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5052796006202698},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47675666213035583},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28607654571533203},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2596210241317749},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08909478783607483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08574649691581726},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08317002654075623},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.2609187","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2609187","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.2609187","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.2609187","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":16,"referenced_works":["https://openalex.org/W926830766","https://openalex.org/W1015675232","https://openalex.org/W1848279521","https://openalex.org/W1932742904","https://openalex.org/W1997423738","https://openalex.org/W2106578604","https://openalex.org/W2146936057","https://openalex.org/W2167639507","https://openalex.org/W2178628967","https://openalex.org/W2572504498","https://openalex.org/W2740245131","https://openalex.org/W2740900805","https://openalex.org/W2750900007","https://openalex.org/W2803318469","https://openalex.org/W2806922180","https://openalex.org/W2963752057"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W4252684102","https://openalex.org/W2352307597","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":[1,179],"is":[2,19,56,108,133,159,180,216],"a":[3,14,109],"scholarly":[4],"data":[5,18,33,94,132,157,166],"set":[6,95,158,167],"containing":[7],"publications'":[8],"full-text,":[9],"annotated":[10],"in-text":[11],"citations,":[12],"and":[13,27,71,100,203,238],"citation":[15],"network.":[16],"The":[17,151,213],"generated":[20,34,116],"from":[21,35,117],"all":[22,118],"LaTeX":[23],"sources":[24],"on":[25,143,172],"arXiv":[26,230],"therefore":[28],"of":[29,60,112,119,130,178],"higher":[30],"quality":[31],"than":[32],"PDF":[36],"files.":[37],"Typical":[38],"use":[39,129,146],"cases":[40],"are":[41,168],"Citation":[42,44,239],"recommendation":[43],"context":[45],"analysis":[46],"Bibliographic":[47],"analyses":[48],"Reference":[49],"string":[50],"parsing":[51],"Note:":[52,104],"This":[53,175],"Zenodo":[54,106],"record":[55,107],"an":[57,97,210,244],"old":[58],"version":[59,68,111,177,215],"unarXive.":[61],"You":[62],"can":[63],"find":[64],"the":[65,92,102,131,136,156,183,219],"most":[66],"recent":[67],"at":[69,170],"https://zenodo.org/record/7752754":[70],"https://zenodo.org/record/7752615":[72],"Access":[73],"\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":[74],"D":[75,82],"O":[76,80],"W":[77],"N":[78],"L":[79,87],"A":[81,84,192],"S":[83],"M":[85],"P":[86],"E":[88],"\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":[89],"To":[90],"download":[91],"whole":[93],"send":[96],"access":[98],"request":[99],"note":[101],"following:":[103],"this":[105],"\"full\"":[110],"unarXive,":[113],"which":[114],"was":[115],"arXiv.org":[120],"including":[121],"non-permissively":[122],"licensed":[123],"papers.":[124],"Make":[125],"sure":[126],"that":[127],"your":[128],"compliant":[134],"with":[135,197],"paper's":[137],"licensing":[138],"terms.\u00b9":[139],"\u00b9":[140],"For":[141],"information":[142],"papers'":[144],"licenses":[145],"arXiv's":[147],"bulk":[148],"metadata":[149],"access.":[150],"code":[152],"used":[153],"for":[154,164,233],"generating":[155],"publicly":[160],"available.":[161],"Usage":[162],"examples":[163],"our":[165],"provided":[169],"here":[171],"GitHub.":[173],"Citing":[174],"initial":[176],"described":[181,217],"in":[182,218],"following":[184,220],"journal":[185],"article.":[186],"Tarek":[187,223],"Saier,":[188,224],"Michael":[189,225],"F\u00e4rber:":[190],"\"unarXive:":[191],"Large":[193],"Scholarly":[194],"Data":[195],"Set":[196],"Publications'":[198],"Full-Text,":[199],"Annotated":[200],"In-Text":[201],"Citations,":[202],"Links":[204],"to":[205,209,243],"Metadata\",":[206],"Scientometrics,":[207],"2020,[link":[208],"author":[211,245],"copy]":[212,246],"updated":[214],"conference":[221],"paper.":[222],"F\u00e4rber.":[226],"\"unarXive":[227],"2022:":[228],"All":[229],"Publications":[231],"Pre-Processed":[232],"NLP,":[234],"Including":[235],"Structured":[236],"Full-Text":[237],"Network\",":[240],"JCDL":[241],"2023.[link":[242]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}