{"ID":6497798,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09149","arxiv_id":"2607.09149","title":"Taxonomy Maintenance In The Wild Over Evolving Scholarly Data: Reliability, Efficiency, and Cost-Effectiveness","abstract":"The 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 box-embedding 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 embeddings and 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-of-the-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.","short_abstract":"The 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 ro...","url_abs":"https://arxiv.org/abs/2607.09149","url_pdf":"https://arxiv.org/pdf/2607.09149v1","authors":"[\"Daomin Ji\",\"Hui Luo\",\"Zhifeng Bao\",\"Junhao Gan\",\"Zi Huang\"]","published":"2026-07-10T07:03:08Z","proceeding":"cs.DB","tasks":"[\"cs.DB\"]","methods":"[\"Large Language Model\"]","has_code":false}