{"id":"https://openalex.org/W3009242205","doi":"https://doi.org/10.1007/s11192-020-03382-z","title":"unarXive: a large scholarly data set with publications\u2019 full-text, annotated in-text citations, and links to metadata","display_name":"unarXive: a large scholarly data set with publications\u2019 full-text, annotated in-text citations, and links to metadata","publication_year":2020,"publication_date":"2020-03-02","ids":{"openalex":"https://openalex.org/W3009242205","doi":"https://doi.org/10.1007/s11192-020-03382-z","mag":"3009242205"},"language":"en","primary_location":{"id":"doi:10.1007/s11192-020-03382-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-020-03382-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11192-020-03382-z.pdf","source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11192-020-03382-z.pdf","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":true,"raw_author_name":"Tarek Saier","raw_affiliation_strings":["Institute AIFB, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5028-0109","affiliations":[{"raw_affiliation_string":"Institute AIFB, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","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":"Michael F\u00e4rber","raw_affiliation_strings":["Institute AIFB, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5458-8645","affiliations":[{"raw_affiliation_string":"Institute AIFB, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035495986"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":3.6567,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94189839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"125","issue":"3","first_page":"3085","last_page":"3108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9980999827384949,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.79461669921875},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7837852239608765},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7570176124572754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7004881501197815},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.6793283224105835},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6019603610038757},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5893222093582153},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5606419444084167},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5193260908126831},{"id":"https://openalex.org/keywords/citation-analysis","display_name":"Citation analysis","score":0.4690459370613098},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4622234106063843},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4477338194847107},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4347701668739319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09599095582962036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79461669921875},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7837852239608765},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7570176124572754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7004881501197815},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6793283224105835},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6019603610038757},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5893222093582153},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5606419444084167},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5193260908126831},{"id":"https://openalex.org/C105345328","wikidata":"https://www.wikidata.org/wiki/Q206276","display_name":"Citation analysis","level":3,"score":0.4690459370613098},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4622234106063843},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4477338194847107},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4347701668739319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09599095582962036},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11192-020-03382-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-020-03382-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11192-020-03382-z.pdf","source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics","raw_type":"journal-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000118786","is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000118786","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics, 125, 3085\u20133108","raw_type":"doc-type:article"},{"id":"pmh:oai:RePEc:spr:scient:v:125:y:2020:i:3:d:10.1007_s11192-020-03382-z","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s11192-020-03382-z","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5445/ir/1000118786","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000118786","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s11192-020-03382-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11192-020-03382-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11192-020-03382-z.pdf","source":{"id":"https://openalex.org/S148561398","display_name":"Scientometrics","issn_l":"0138-9130","issn":["0138-9130","1588-2861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320108","host_organization_name":"Springer Nature (Netherlands)","host_organization_lineage":["https://openalex.org/P4310320108","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature (Netherlands)","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientometrics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3009242205.pdf","grobid_xml":"https://content.openalex.org/works/W3009242205.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W62810358","https://openalex.org/W205371894","https://openalex.org/W791527587","https://openalex.org/W926830766","https://openalex.org/W1015675232","https://openalex.org/W1603719052","https://openalex.org/W1848279521","https://openalex.org/W1932742904","https://openalex.org/W1981073939","https://openalex.org/W1996250712","https://openalex.org/W1997423738","https://openalex.org/W2036090952","https://openalex.org/W2054691916","https://openalex.org/W2088336913","https://openalex.org/W2090017022","https://openalex.org/W2097716833","https://openalex.org/W2106578604","https://openalex.org/W2107972503","https://openalex.org/W2141619255","https://openalex.org/W2146936057","https://openalex.org/W2150569271","https://openalex.org/W2153568396","https://openalex.org/W2167639507","https://openalex.org/W2178628967","https://openalex.org/W2253675773","https://openalex.org/W2321621029","https://openalex.org/W2462443510","https://openalex.org/W2572504498","https://openalex.org/W2573225424","https://openalex.org/W2620015753","https://openalex.org/W2740245131","https://openalex.org/W2740900805","https://openalex.org/W2750900007","https://openalex.org/W2768378990","https://openalex.org/W2798010889","https://openalex.org/W2803318469","https://openalex.org/W2806922180","https://openalex.org/W2879432308","https://openalex.org/W2894170875","https://openalex.org/W2907933766","https://openalex.org/W2941922035","https://openalex.org/W2963369195","https://openalex.org/W2963386804","https://openalex.org/W2963752057","https://openalex.org/W2963805586","https://openalex.org/W2969049331","https://openalex.org/W2972398143","https://openalex.org/W4238015202","https://openalex.org/W4240811499","https://openalex.org/W6731987836","https://openalex.org/W7000635770"],"related_works":["https://openalex.org/W2093597205","https://openalex.org/W2389846579","https://openalex.org/W2392495745","https://openalex.org/W132250100","https://openalex.org/W1965294778","https://openalex.org/W2099984331","https://openalex.org/W2361032643","https://openalex.org/W2153568396","https://openalex.org/W2148539344","https://openalex.org/W3009242205"],"abstract_inverted_index":{"Abstract":[0],"In":[1,57],"recent":[2],"years,":[3],"scholarly":[4,49],"data":[5,45,50,64,109,123],"sets":[6,51],"have":[7],"been":[8],"used":[9,44],"for":[10,130,153],"various":[11],"purposes,":[12,132],"such":[13,32],"as":[14,150,160],"paper":[15],"recommendation,":[16,18],"citation":[17,19,23,120,144],"context":[20],"analysis,":[21],"and":[22,34,93,117,143],"context-based":[24,145],"document":[25],"summarization.":[26],"The":[27,122],"evaluation":[28,139],"of":[29,112,140],"approaches":[30],"to":[31,98,105,156],"tasks":[33],"their":[35],"applicability":[36],"in":[37,54,164],"real-world":[38],"scenarios":[39],"heavily":[40],"depend":[41],"on":[42,67,75],"the":[43,80,99,137],"set.":[46],"However,":[47],"existing":[48],"are":[52],"limited":[53],"several":[55],"regards.":[56],"this":[58,165],"paper,":[59],"we":[60,161],"propose":[61],"a":[62,151],"new":[63,154],"set":[65,110],"based":[66],"all":[68,71],"publications":[69,95],"from":[70,78],"scientific":[72],"disciplines":[73],"available":[74,129],"arXiv.org.":[76],"Apart":[77],"providing":[79,103],"papers\u2019":[81],"plain":[82],"text,":[83],"in-text":[84,158],"citations":[85],"were":[86,96],"annotated":[87],"via":[88],"global":[89],"identifiers.":[90],"Furthermore,":[91],"citing":[92],"cited":[94],"linked":[97],"Microsoft":[100],"Academic":[101],"Graph,":[102],"access":[104],"rich":[106],"metadata.":[107],"Our":[108],"consists":[111],"over":[113],"one":[114],"million":[115,119],"documents":[116],"29.2":[118],"contexts.":[121],"set,":[124],"which":[125],"is":[126],"made":[127],"freely":[128],"research":[131,141],"not":[133],"only":[134],"can":[135],"enhance":[136],"future":[138],"paper-based":[142],"approaches,":[146],"but":[147],"also":[148],"serve":[149],"basis":[152],"ways":[155],"analyze":[157],"citations,":[159],"show":[162],"prototypically":[163],"article.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
