[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82220-en":3,"doc-seo-82220-105":30,"detail-sidebar-cat-0-en-105":91},{"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},82220,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Taxonomy Maintenance In The Wild Over Evolving Scholarly Data","Scientific publication growth makes scholarly taxonomies quickly become outdated. The work studies “taxonomy maintenance in the wild” by continuously adapting topic-centric taxonomies to evolving repositories such as arXiv for a given research area. It introduces GIST, a robust framework that extracts partial hierarchies from papers’ “Related Work,” grounds structure induction in curated evidence, and merges them into a unified global taxonomy using geometric box-embedding containment for is-a relations. GIST supports efficient incremental updates via novelty-aware coreset selection and uses cost-effective evidence retrieval under token budgets. Experiments on arXiv show improved Node F1 and Edge F1 with far lower runtime and monetary cost.","Taxonomy Maintenance In The Wild Over Evolving Scholarly Data: Reliability, Efficiency, and Cost-Effectiveness  \nDaomin Ji* RMIT University & The University of Queensland [daomin.ji@student.rmit.edu.au](daomin.ji@student.rmit.edu.au)  \nHui Luo  \nUniversity of Wollongong [huil@uow.edu.au](huil@uow.edu.au)  \nZhifeng Bao† The University of Queensland [baozhifeng.cs@gmail.com](baozhifeng.cs@gmail.com)  \narXiv :2607 .09149v1 [ cs .DB] 10 Jul 2026  \nJunhao Gan The University of Melbourne [junhao.gan@unimelb.edu.au](junhao.gan@unimelb.edu.au)  \nABSTRACT  \nThe rapid growth of scientific publications makes scholarly taxonomies quickly obsolete. We study taxonomy maintenance in the wild, a new problem that moves beyond static construction by continuously adapting taxonomies to evolving scholarly repositories, such as arXiv, for a given research topic. We propose GIST, a robust framework for maintaining evolving taxonomies. Unlike purely LLM-centric approaches, GIST grounds structure induction in expert-curated evidence by extracting partial hierarchies from the “Related Work” sections of papers. It integrates these partial taxonomies into a unified global taxonomy in a geometric boxembedding space, where box containment encodes the inductive bias of is-a relations. To connect semantics with geometric structure, GIST learns a bidirectional mapping between word embeddingsand box embeddings. For efficient incremental updates, GIST uses novelty-aware coreset selection to update the model with representative historical signals and new evidence, avoiding costly full retraining. To handle high-velocity paper streams under user-specific token budgets, GIST further combines a hypothesized concept generator with a cost-effective evidence retrieval module. Experiments on real-world arXiv datasets show that GIST outperforms state-ofthe-art baselines, improving Node F1 and Edge F1 by 11.0% and 13.1% over the strongest baseline while requiring only 9.6% of its runtime and 12.7% of its monetary cost.  \nACM Reference Format:  \nDaomin Ji, Hui Luo, Zhifeng Bao, Junhao Gan, and Zi Huang. 2018. Taxonomy Maintenance In The Wild Over Evolving Scholarly Data: Reliability, Efficiency, and Cost-Effectiveness. In Proceedings of Make sure to enter the correct conference title from your rights confirmation email  \n*This work was done when Daomin Ji was a visiting student at The University of Queensland.  \n†Zhifeng Bao is the corresponding author.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, June 03–05, 2018, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06. . . $15.00 [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nZi Huang  \nThe University of Queensland [huang@itee.uq.edu.au](huang@itee.uq.edu.au)  \n􀀤 !: Expansion  \n 􀀤 \\#: Specialization  \n 􀀤 \": Abstraction  \nFigure 1: The rapid development of research topic GraphRAG  \n(Conference acronym ’XX). ACM, New York, NY, USA, 19 pages. [https:](https:)//[doi.org/XXXXXXX.XXXXXXX](doi.org/XXXXXXX.XXXXXXX)  \n1 INTRODUCTION  \nTaxonomies provide a structured abstraction of domain knowledge by organizing concepts into hierarchical “is-a” relations, and have long served as foundational infrastructure in data management fortasks such as knowledge base construction and logical inference [7, 61], semantic in","cbCaihprCVUmaYvT","https://ap.wps.com/l/cbCaihprCVUmaYvT","pdf",823111,2,1,19,"English","en",105,"# Introduction\n## Problem: Volatile topic-centric taxonomies\n## Example: GraphRAG domain evolution","[{\"question\":\"What problem does the paper address in scholarly taxonomy management?\",\"answer\":\"It addresses how scholarly taxonomies become obsolete as research topics evolve quickly, and how to keep topic-centric “is-a” hierarchies up to date for repositories like arXiv.\"},{\"question\":\"How does GIST build and update evolving taxonomies?\",\"answer\":\"GIST extracts partial hierarchies from the “Related Work” sections of papers, integrates them into a global taxonomy in a geometric box-embedding space, and learns bidirectional mappings between word embeddings and box embeddings for semantics-to-geometry alignment.\"},{\"question\":\"How does the framework achieve efficiency under incremental updates and token budgets?\",\"answer\":\"For incremental updates, GIST uses novelty-aware coreset selection to avoid costly full retraining. For high-velocity streams, it combines a hypothesized concept generator with cost-effective evidence retrieval that respects user-specific token budgets.\"}]",1784178936,48,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"taxonomy-maintenance-in-the-wild-over-evolving-scholarly-data","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/taxonomy-maintenance-in-the-wild-over-evolving-scholarly-data/82220/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-21","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in scholarly taxonomy management?","Question",{"text":75,"@type":76},"It addresses how scholarly taxonomies become obsolete as research topics evolve quickly, and how to keep topic-centric “is-a” hierarchies up to date for repositories like arXiv.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does GIST build and update evolving taxonomies?",{"text":80,"@type":76},"GIST extracts partial hierarchies from the “Related Work” sections of papers, integrates them into a global taxonomy in a geometric box-embedding space, and learns bidirectional mappings between word embeddings and box embeddings for semantics-to-geometry alignment.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the framework achieve efficiency under incremental updates and token budgets?",{"text":84,"@type":76},"For incremental updates, GIST uses novelty-aware coreset selection to avoid costly full retraining. For high-velocity streams, it combines a hypothesized concept generator with cost-effective evidence retrieval that respects user-specific token budgets.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"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":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]