Scholarlink

This paper presents TheoremView, a novel framework for extracting proofs and theorems from raw PDF scientific papers without requiring  source files. Our approach combines three modalities (font, text, and vision) with sequential modeling to capture long-term dependencies and layout information. By eliminating OCR preprocessing, TheoremView reduces computational overhead for real-time applications while providing robust automated theorem extraction. Our framework is publicly available at https://theoremkb.org/demo , with a demonstration video at https://theoremkb.org/video .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

TheoremView: A Framework for Extracting Theorem-Like Environments from Raw PDFs

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Shrey Mishra,
  • Neil Sharma,
  • Antoine Gauquier,
  • Pierre Senellart

摘要

This paper presents TheoremView, a novel framework for extracting proofs and theorems from raw PDF scientific papers without requiring  source files. Our approach combines three modalities (font, text, and vision) with sequential modeling to capture long-term dependencies and layout information. By eliminating OCR preprocessing, TheoremView reduces computational overhead for real-time applications while providing robust automated theorem extraction. Our framework is publicly available at https://theoremkb.org/demo , with a demonstration video at https://theoremkb.org/video .