{"id":"https://openalex.org/W7140296077","doi":"https://doi.org/10.1109/access.2026.3677777","title":"A Tool for Extracting Citation Graphs From Scholarly PDF Articles","display_name":"A Tool for Extracting Citation Graphs From Scholarly PDF Articles","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140296077","doi":"https://doi.org/10.1109/access.2026.3677777"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3677777","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3677777","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3677777","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027086183","display_name":"Angelo Di Iorio","orcid":"https://orcid.org/0000-0002-6893-7452"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Angelo Di Iorio","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6893-7452","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006728922","display_name":"Ivan Heibi","orcid":"https://orcid.org/0000-0001-5366-5194"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ivan Heibi","raw_affiliation_strings":["Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Centre, University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5366-5194","affiliations":[{"raw_affiliation_string":"Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Centre, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130562080","display_name":"Silvio Peroni","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvio Peroni","raw_affiliation_strings":["Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Centre, University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0530-4305","affiliations":[{"raw_affiliation_string":"Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Centre, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027095197","display_name":"Marta Soricetti","orcid":"https://orcid.org/0009-0008-1466-7742"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marta Soricetti","raw_affiliation_strings":["Department of Classical Philology and Italian Studies, Research Centre for Open Scholarly Metadata, University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0009-0008-1466-7742","affiliations":[{"raw_affiliation_string":"Department of Classical Philology and Italian Studies, Research Centre for Open Scholarly Metadata, University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26305992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"48277","last_page":"48297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13607","display_name":"Academic Publishing and Open Access","score":0.11259999871253967,"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"}},"topics":[{"id":"https://openalex.org/T13607","display_name":"Academic Publishing and Open Access","score":0.11259999871253967,"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":0.07079999893903732,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0658000037074089,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5253999829292297},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.35339999198913574},{"id":"https://openalex.org/keywords/citation-analysis","display_name":"Citation analysis","score":0.3294000029563904},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.2985999882221222},{"id":"https://openalex.org/keywords/co-citation","display_name":"Co-citation","score":0.29120001196861267},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.28450000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954000234603882},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5432000160217285},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C105345328","wikidata":"https://www.wikidata.org/wiki/Q206276","display_name":"Citation analysis","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2777765086","wikidata":"https://www.wikidata.org/wiki/Q1785764","display_name":"Co-citation","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3677777","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3677777","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:65790aa25c76446fac756da710908b9d","is_oa":true,"landing_page_url":"https://doaj.org/article/65790aa25c76446fac756da710908b9d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 48277-48297 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3677777","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3677777","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4298482835292816}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,45,99,125,145],"Citation":[4],"Extraction":[5],"tool":[6],"(CEX),":[7],"a":[8,38,49,56,103],"software":[9],"designed":[10],"to":[11,43,91],"extract":[12],"in-text":[13,114],"reference":[14,115],"pointers":[15],"from":[16,55],"scholarly":[17,50,154],"PDFs":[18,88],"together":[19],"with":[20],"their":[21],"sentence-level":[22],"citation":[23,32,62,118],"contexts":[24],"and,":[25],"when":[26],"possible,":[27],"section":[28,141],"titles,":[29],"enabling":[30],"downstream":[31],"intent":[33],"classification.":[34],"CEX":[35,105],"builds":[36],"on":[37,102,124,152],"trained":[39],"version":[40],"of":[41,48,85],"GROBID":[42],"obtain":[44],"structured":[46],"full-text":[47],"article":[51],"in":[52,69],"TEI":[53],"format":[54,71],"PDF":[57],"source,":[58],"and":[59,72,117,148,156],"then":[60],"identifies":[61],"information":[63],"that":[64],"is":[65,89],"provided":[66],"as":[67,144],"output":[68],"JSON":[70],"RDF":[73],"(i.e.":[74],"JSON-LD":[75],"format)":[76],"for":[77,113],"Linked":[78],"Open":[79,126],"Data":[80],"integration.":[81],"A":[82],"new":[83],"dataset":[84],"227":[86],"annotated":[87],"introduced":[90],"retrain":[92],"GROBID\u2019s":[93],"segmentation":[94],"model,":[95],"improving":[96],"performance":[97],"over":[98],"baseline.":[100],"Evaluation":[101],"curated":[104],"Gold":[106],"Standard":[107],"(113":[108],"articles)":[109,131],"yields":[110],"high":[111,133],"accuracy":[112],"pointer":[116],"context":[119],"extraction,":[120],"while":[121],"large-scale":[122],"testing":[123],"Research":[127],"Europe":[128],"corpus":[129],"(1,109":[130],"confirms":[132],"precision":[134],"but":[135],"lower":[136],"recall.":[137],"The":[138],"results":[139],"highlight":[140],"title":[142],"extraction":[143],"main":[146],"bottleneck":[147],"outline":[149],"future":[150],"work":[151],"SSH":[153],"articles":[155],"multilingual":[157],"documents":[158],"via":[159],"hybrid":[160],"strategies.":[161]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-03-26T00:00:00"}
