Paper2Data: Large-Scale LLM Extraction and Metadata Structuring of Global Urban Data from Scientific Literature

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: You, Runwen, Xia, Tong, Wang, Jingzhi, Zhang, Jiankun, Tu, Tengyao, Piao, Jinghua, Chang, Yi, Li, Yong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908974843953152
author You, Runwen
Xia, Tong
Wang, Jingzhi
Zhang, Jiankun
Tu, Tengyao
Piao, Jinghua
Chang, Yi
Li, Yong
author_facet You, Runwen
Xia, Tong
Wang, Jingzhi
Zhang, Jiankun
Tu, Tengyao
Piao, Jinghua
Chang, Yi
Li, Yong
contents Urban data support a wide range of applications across multiple disciplines. However, at the global scale, there is no unified platform for urban data discovery. As a result, researchers often have to manually search through websites or scientific literature to identify relevant datasets. To address this problem, we curate an open urban data discovery portal, \textit{UrbanDataMiner}, which supports dataset-level search and filtering over more than 60{,}000 urban datasets extracted from over 15{,}000 Nature-affiliated publications. \textit{UrbanDataMiner} is enabled by \textit{Paper2Data}, a novel large-scale LLM-driven pipeline that automatically identifies dataset mentions in scientific papers and structures them using a unified urban data metadata schema. Human-annotated evaluation demonstrates that \textit{Paper2Data} achieves high recall (approximately 90\%) in dataset identification and high field-level precision (above 80\%). In addition, \textit{UrbanDataMiner} can retrieve over 9\% of datasets that are not easily discoverable through general-purpose search engines such as Google. Overall, our work provides the first large-scale, literature-derived infrastructure for urban data discovery and enables more systematic and reusable data-driven research across disciplines. Our code and data are publicly available\footnote{https://github.com/Yourunwen/Paper2Data}.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16317
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Paper2Data: Large-Scale LLM Extraction and Metadata Structuring of Global Urban Data from Scientific Literature
You, Runwen
Xia, Tong
Wang, Jingzhi
Zhang, Jiankun
Tu, Tengyao
Piao, Jinghua
Chang, Yi
Li, Yong
Information Retrieval
Artificial Intelligence
Urban data support a wide range of applications across multiple disciplines. However, at the global scale, there is no unified platform for urban data discovery. As a result, researchers often have to manually search through websites or scientific literature to identify relevant datasets. To address this problem, we curate an open urban data discovery portal, \textit{UrbanDataMiner}, which supports dataset-level search and filtering over more than 60{,}000 urban datasets extracted from over 15{,}000 Nature-affiliated publications. \textit{UrbanDataMiner} is enabled by \textit{Paper2Data}, a novel large-scale LLM-driven pipeline that automatically identifies dataset mentions in scientific papers and structures them using a unified urban data metadata schema. Human-annotated evaluation demonstrates that \textit{Paper2Data} achieves high recall (approximately 90\%) in dataset identification and high field-level precision (above 80\%). In addition, \textit{UrbanDataMiner} can retrieve over 9\% of datasets that are not easily discoverable through general-purpose search engines such as Google. Overall, our work provides the first large-scale, literature-derived infrastructure for urban data discovery and enables more systematic and reusable data-driven research across disciplines. Our code and data are publicly available\footnote{https://github.com/Yourunwen/Paper2Data}.
title Paper2Data: Large-Scale LLM Extraction and Metadata Structuring of Global Urban Data from Scientific Literature
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2604.16317