[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85140-en":3,"doc-seo-85140-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85140,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","The Backbone of Science: Analysis of Citation Networks Between Papers and Their Sources","The bibliography of scientific papers contains references with uneven relevance to the paper’s actual development. Identifying the sources—the works that inspired a paper—enables citation-based insights into the genesis of research projects beyond standard citation counts. An analysis of the backbone of science models citation links between papers and their sources, extracted from full texts using Large Language Models (LLMs). Two related prompts yield small, non-random reference sets producing similar backbone network structures, with more heterogeneous in-degree distributions yet stable rankings for highly cited papers and authors.","arXiv :2607 .0977 1v 1 [ cs .DL] 7 Jul 2026  \nThe backbone of science: analysis of citation networks between papers  \nand their sources  \nWonhee Jeong 1 , Dimitri Marinelli2 , Satyaki Sikdar3 , Gaurang Singh Yadav 1 , and Santo  \nFortunato 1, *  \n1 Center for Complex Networks and Systems Research (CNetS), Indiana University, Bloomington, IN, USA  \n2 Institute of Complex Systems (UBICS) and Department of Condensed Matter Physics,  \nUniversity of Barcelona, Barcelona, Spain  \n3 Department of Computer Science, Loyola University Chicago, Chicago, IL, USA  \n* corresponding author: [santo@iu.edu](santo@iu.edu)  \nJuly 14, 2026  \nAbstract  \nThe bibliography of scientific papers lists items with variable degree of relevance for the contents of the paper itself. If we could identify the sources, i.e., the works that actually inspired the paper, their citations can help us uncover the genesis of scientific projects and would be more representative of the actual importance of papers and authors than the standard citation counts, when all references are considered. Here we present an analysis of the backbone of science, i.e., the network of citations between papers and their sources. The latter are extracted from the full body of papers via Large Language Models (LLMs), which are currently very capable of correctly identifying the context in which a paper is cited. Using two different but related prompts, we find that the LLMs select only a small set of references, not taken at random, and that the resulting backbone networks are quite similar to each other with respect to their in-degree distributions, modularity, transitivity, and degree correlations. Backbone networks have higher heterogeneity in their in-degree distributions, compared to the full network, but the most cited papers are usually the same, with some important exceptions. Citation rankings among authors are also remarkably stable. We conclude that the full citation network, despite its redundancy with respect to the backbones, presents a reliable picture of the relative citation impact of papers and authors.  \n1 Introduction  \nThe list of references of a scientific paper is supposed to include all previous works that, in one way or another, are closely linked to it. Some may be general references, like review articles and books, that summarize the state of the field of the paper. Most of the others are usually related to the specific contents of the paper, which may have used an idea, problem formulation, or a method introduced in them. Not all references are equally important for the genesis of the paper, though. We call sources the building blocks of the focal paper, i.e., those references which provided a key idea or methodology, without which the paper would not have been possible. Let us suppose that we identified all sources of all papers. The resulting citation network could be considered the backbone of science, in that it only includes the papers providing the main ingredients of all others. Besides its intrinsic value, the backbone of science allows us to derive a more reliable estimate of the impact of papers and authors than the full citation network, which entails a lot of redundancy due to the many references having only a marginal role in the conception and design of the papers.  \nIn this work, we compare the full citation network with its backbone. A key question is how to identify the sources, and how to do it at scale, for thousands of papers. For this, we used Large Language Models (LLMs) [31], which are increasingly adopted by scholars in their citation practices [30] . Most of the times LLMs are used to find relevant citations for a given work [1, 2], or even specific paragraphs [21], though hallucinations might lead to incorrect references [15] . Also, one can use LLMs to help scholars screen citations [16] .  \nHere we query LLMs with prompts that specifically request to output a selection of relevant references. We used two different, albeit similar, ","cbCaime962peed8B","https://ap.wps.com/l/cbCaime962peed8B","pdf",7143519,6,1,26,"English","en",105,"# Abstract\n# Introduction\n# Results\n## Characterization of Extraction Selectivity and Backbone Networks","[{\"question\":\"What are “sources” in the backbone of science framework?\",\"answer\":\"Sources are the key references that provided a main idea or methodology without which the focal paper would not have been possible. They represent the building blocks behind a paper’s development.\"},{\"question\":\"How are citation backbones extracted in this work?\",\"answer\":\"Large Language Models extract source references from the full body text of papers using two related prompts. The selected references define backbone networks that are much sparser than the full citation networks.\"},{\"question\":\"What structural and ranking properties are compared between full citation networks and backbones?\",\"answer\":\"The backbone networks are structurally similar across prompts, with comparable in-degree distribution behavior, modularity, transitivity, and degree correlations. Rankings of papers and authors based on full-network citations remain remarkably stable in the backbones, despite reduced redundancy.\"}]",1784201333,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"the-backbone-of-science-analysis-of-citation-networks-between-papers-and-their-sources","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/the-backbone-of-science-analysis-of-citation-networks-between-papers-and-their-sources/85140/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What are “sources” in the backbone of science framework?","Question",{"text":76,"@type":77},"Sources are the key references that provided a main idea or methodology without which the focal paper would not have been possible. They represent the building blocks behind a paper’s development.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are citation backbones extracted in this work?",{"text":81,"@type":77},"Large Language Models extract source references from the full body text of papers using two related prompts. The selected references define backbone networks that are much sparser than the full citation networks.",{"name":83,"@type":74,"acceptedAnswer":84},"What structural and ranking properties are compared between full citation networks and backbones?",{"text":85,"@type":77},"The backbone networks are structurally similar across prompts, with comparable in-degree distribution behavior, modularity, transitivity, and degree correlations. Rankings of papers and authors based on full-network citations remain remarkably stable in the backbones, despite reduced redundancy.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]