{"ID":2824628,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22903","arxiv_id":"2512.22903","title":"Debugging Tabular Log as Dynamic Graphs","abstract":"Tabular log abstracts objects and events in the real-world system and reports their updates to reflect the change of the system, where one can detect real-world inconsistencies efficiently by debugging corresponding log entries. However, recent advances in processing text-enriched tabular log data overly depend on large language models (LLMs) and other heavy-load models, thus suffering from limited flexibility and scalability. This paper proposes a new framework, GraphLogDebugger, to debug tabular log based on dynamic graphs. By constructing heterogeneous nodes for objects and events and connecting node-wise edges, the framework recovers the system behind the tabular log as an evolving dynamic graph. With the help of our dynamic graph modeling, a simple dynamic Graph Neural Network (GNN) is representative enough to outperform LLMs in debugging tabular log, which is validated by experimental results on real-world log datasets of computer systems and academic papers.","short_abstract":"Tabular log abstracts objects and events in the real-world system and reports their updates to reflect the change of the system, where one can detect real-world inconsistencies efficiently by debugging corresponding log entries. However, recent advances in processing text-enriched tabular log data overly depend on larg...","url_abs":"https://arxiv.org/abs/2512.22903","url_pdf":"https://arxiv.org/pdf/2512.22903v1","authors":"[\"Chumeng Liang\",\"Zhanyang Jin\",\"Zahaib Akhtar\",\"Mona Pereira\",\"Haofei Yu\",\"Jiaxuan You\"]","published":"2025-12-28T12:23:41Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CL\"]","methods":"[\"Graph Neural Network\",\"Large Language Model\",\"Language Model\"]","has_code":false}