{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:01:11Z","timestamp":1775250071237,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union\u2019s Horizon Europe Framework Program through the next Generation Research Assessment to Promote Open Science (GraspOS) Project","award":["101095129"],"award-info":[{"award-number":["101095129"]}]},{"name":"Knowledge Graphs, AI Services and Next Generation Instrumentation for R&D in Social Sciences and Humanities (GRAPHIA) Project","award":["101188018"],"award-info":[{"award-number":["101188018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3677777","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T19:57:30Z","timestamp":1774468650000},"page":"48277-48297","source":"Crossref","is-referenced-by-count":0,"title":["A Tool for Extracting Citation Graphs From Scholarly PDF Articles"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6893-7452","authenticated-orcid":false,"given":"Angelo Di","family":"Iorio","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Bologna, Bologna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5366-5194","authenticated-orcid":false,"given":"Ivan","family":"Heibi","sequence":"additional","affiliation":[{"name":"Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Centre, University of Bologna, Bologna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-4305","authenticated-orcid":false,"given":"Silvio","family":"Peroni","sequence":"additional","affiliation":[{"name":"Department of Classical Philology and Italian Studies, Digital Humanities Advanced Research Centre, University of Bologna, Bologna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1466-7742","authenticated-orcid":false,"given":"Marta","family":"Soricetti","sequence":"additional","affiliation":[{"name":"Department of Classical Philology and Italian Studies, Research Centre for Open Scholarly Metadata, University of Bologna, Bologna, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Document Management\u2013Portable Document Format\u2013Part 2: PDF 2.0. ISO","year":"2020"},{"key":"ref2","volume-title":"Open Citation: Definition","author":"Peroni","year":"2018"},{"key":"ref3","article-title":"Joint declaration of data citation principles","author":"Data Citation Synthesis Group","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/asi.20609"},{"issue":"8","key":"ref5","first-page":"979","article-title":"Journal impact factor: A brief review","volume":"161","author":"Garfield","year":"1999","journal-title":"CMAJ: Can. Med. Assoc. J. J. de l\u2019Association Medicale Canadienne"},{"issue":"7548","key":"ref6","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/520429a","article-title":"Bibliometrics: The Leiden Manifesto for research metrics","volume":"520","author":"Hicks","year":"2015","journal-title":"Nature"},{"issue":"7687","key":"ref7","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1038\/d41586-018-00104-7","article-title":"Funders should mandate open citations","volume":"553","author":"Shotton","year":"2018","journal-title":"Nature"},{"issue":"1","key":"ref8","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1162\/qss_a_00023","article-title":"OpenCitations, an infrastructure organization for open scholarship","volume":"1","author":"Peroni","year":"2020","journal-title":"Quant. Sci. Stud."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00668-6_8"},{"key":"ref10","volume-title":"The OpenCitations Data Model","author":"daquino","year":"2023"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.websem.2012.08.001","article-title":"FaBiO and CiTO: Ontologies for describing bibliographic resources and citations","volume":"17","author":"Peroni","year":"2012","journal-title":"J. Web Semantics"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-025-05418-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04346-8_62"},{"issue":"1","key":"ref14","first-page":"60","article-title":"Insights to the state-of-the-art PDF extraction techniques","volume":"16","author":"Hashmi","year":"2020","journal-title":"IPSI Trans. Internet Res."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28032-0_31"},{"key":"ref16","first-page":"181","article-title":"Structured document labeling and rule extraction using a new recurrent fuzzy-neural system","volume-title":"Proc. 5th Int. Conf. Document Anal. Recognit. (ICDAR)","author":"Sainz-Palmero"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/376284.375682"},{"key":"ref18","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Lafferty"},{"key":"ref19","first-page":"9","article-title":"Conditional structure versus conditional estimation in NLP models","volume-title":"Proc. ACL Conf. Empirical Methods Natural Language Processing (EMNLP)","volume":"10","author":"Klein"},{"key":"ref20","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref21","article-title":"Document parsing unveiled: Techniques, challenges, and prospects for structured information extraction","author":"Zhang","year":"2024","journal-title":"arXiv:2410.21169"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"409","DOI":"10.54097\/bm665j77","article-title":"A study of the OCR development history and directions of development","volume":"72","author":"Wang","year":"2023","journal-title":"Highlights Sci., Eng. Technol."},{"key":"ref23","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref24","article-title":"InternVL3.5: Advancing open-source multimodal models in versatility, reasoning, and efficiency","author":"Wang","year":"2025","journal-title":"arXiv:2508.18265"},{"key":"ref25","article-title":"Nougat: Neural optical understanding for academic documents","author":"Blecher","year":"2023","journal-title":"arXiv:2308.13418"},{"key":"ref26","article-title":"Vary: Scaling up the vision vocabulary for large vision-language models","author":"Wei","year":"2023","journal-title":"arXiv:2312.06109"},{"key":"ref27","article-title":"Focus anywhere for fine-grained multi-page document understanding","author":"Liu","year":"2024","journal-title":"arXiv:2405.14295"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110836"},{"key":"ref29","article-title":"General OCR theory: Towards OCR-2.0 via a unified end-to-end model","author":"Wei","year":"2024","journal-title":"arXiv:2409.01704"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/science.122.3159.108"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16802-4_42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-015-0249-8"},{"key":"ref33","first-page":"432","article-title":"EXCITE\u2014A toolchain to extract, match and publish open literature references","volume-title":"Proc. ACM\/IEEE Joint Conf. Digit. Libraries (JCDL)","author":"Hosseini"},{"key":"ref34","volume-title":"How Scholarcy Contributes To and Makes Use of Open Citations","author":"Gooch","year":"2019"},{"key":"ref35","volume-title":"CORE + GROBID: Structured Text From 34 Million Scientific Documents (and Counting)","author":"Pride","year":"2023"},{"issue":"1","key":"ref36","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1038\/s41597-023-02208-w","article-title":"CORE: A global aggregation service for open access papers","volume":"10","author":"Knoth","year":"2023","journal-title":"Scientific Data"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-024-00404-6"},{"key":"ref38","article-title":"Citation parsing and analysis with language models","author":"Sarin","year":"2025","journal-title":"arXiv:2505.15948"},{"key":"ref39","volume-title":"MarkItDown: A Python Tool for Converting Files To Markdown, 2025","author":"Corporation","year":"2025"},{"key":"ref40","volume-title":"Inside the Publishing Revolution: The Adobe Story","author":"Pfiffner","year":"2003"},{"key":"ref41","first-page":"1","article-title":"Converting unstructured and semi-structured data into knowledge","volume-title":"Proc. 11th RoEduNet Int. Conf.","author":"Rusu"},{"key":"ref42","volume-title":"A Comparative Analysis of Three Tools for Bibliographic Reference Extraction From PDF Articles","author":"Pagnotta","year":"2025"},{"key":"ref43","volume-title":"CEX Project\u2013Dataset and Gold Standard","year":"2024"},{"key":"ref44","volume-title":"Opencitations\/CEC: Alpha Version","author":"Pagnotta","year":"2024"},{"key":"ref45","volume-title":"Data for Testing and Evaluating References Extraction and Parsing Tools","author":"Cioffi","year":"2022"},{"key":"ref46","volume-title":"Investigating the Performance of GROBID and OUTCITE","author":"Pagnotta","year":"2023"},{"key":"ref47","volume-title":"CEX Project\u2013trained GROBID Citation Models","year":"2024"},{"key":"ref48","volume-title":"CEX Project\u2013Grobid Segmentation Model Training Dataset","author":"Soricetti","year":"2025"},{"issue":"7","key":"ref49","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1108\/JD-10-2022-0234","article-title":"An analysis of citing and referencing habits across all scholarly disciplines: Approaches and trends in bibliographic referencing and citing practices","volume":"79","author":"Santos","year":"2023","journal-title":"J. Documentation"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1067\/mod.2000.109032"},{"key":"ref51","first-page":"3586","article-title":"Structural scaffolds for citation intent classification in scientific publications","volume-title":"Proc. Conf. North","author":"Cohan"},{"key":"ref52","first-page":"101","article-title":"Stanza: A PyThon natural language processing toolkit for many human languages","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics, Syst. Demonstrations","author":"Qi"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06981-9_18"},{"key":"ref54","volume-title":"CEX Project\u2014GoldStandard Fulltext","author":"Soricetti","year":"2025"},{"key":"ref55","volume-title":"Open Research Europe: An Update","author":"Woods","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0280637"},{"key":"ref57","article-title":"A comparative study of PDF parsing tools across diverse document categories","author":"Adhikari","year":"2024","journal-title":"arXiv:2410.09871"},{"issue":"1","key":"ref58","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","article-title":"Structured information extraction from scientific text with large language models","volume":"15","author":"Dagdelen","year":"2024","journal-title":"Nature Commun."},{"key":"ref59","volume-title":"Training the Grobid Reference Extraction Models Slides","author":"Foppiano"},{"key":"ref60","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref61","article-title":"Gemma 3 technical report","volume-title":"arXiv:2503.19786","author":"Team","year":"2025"},{"key":"ref62","volume-title":"Dhlab-EPFL\/LinkedBooksMonographs: LinkedBooksMonographs (version 1.1)","author":"Romanello","year":"2017"},{"key":"ref63","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref64","volume-title":"Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities Slides","author":"Zhu"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11456017.pdf?arnumber=11456017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:55:00Z","timestamp":1775246100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11456017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3677777","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}