为大模型代理设计可操作的论文格式，让机器能精准提取结论和实验命令。
paper.json: A Coordination Convention for LLM-Agent-Actionable Papers
- 用JSON文件标注论文中的每个论点、定义和图表命令，支持精确引用。
- 只需一小时手写即可完成合规，无需重写原文内容。
- 适合希望提升论文可读性和可复现性的研究者与自动化工具开发者。
大语言模型代理常作为学术论文的首读人，需快速提取子论点、复现步骤并判断适用范围。但传统论文存在子论点无法精准引用、范围过度扩展、图表命令藏于代码库等问题。本文提出 `paper.json`，一种随PDF附带的轻量级JSON规范：包含稳定论点编号（C1）、明确不声称列表（C2）、每图精确的终端命令（C3）以及稳定定义编号（C5）。第四个约定（C4）指出，仅需一小时手工编写即可实现最低合规，且不改动原始论文。C1、C2、C3、C5为开放验证机制：任何读取合规论文并执行的代理，其行为可作为这些规范有效性的证据。本文自身即为合规实例：运行 `uv run validator.py paper.json --against paper.typ` 通过验证。代码库：https://github.com/arquicanedo/paper-json
原文摘要 · Abstract (English)
LLM agents routinely serve as first (and sometimes only) readers of academic papers, skimming for sub-claims, extracting reproducibility steps, and generalizing scope. Standard prose papers produce recurring failures in this role: sub-claims that cannot be cited at sub-paper granularity, scope overextension beyond what the paper tests, and figure commands buried in codebases rather than the paper itself. We propose `paper.json`, a companion JSON file that travels with the PDF and addresses each failure with a lightweight convention: stable claim IDs (C1), an explicit does-not-claim list (C2), exact per-figure shell commands (C3), and stable definition IDs (C5). A fifth convention (C4) holds that minimum viable compliance, hand-written JSON alongside the PDF, is achievable in under an hour for a finished paper without touching the human-readable output. C1, C2, C3, and C5 are open invitations: an agent that reads a compliant paper and acts on it produces evidence for or against them. This paper is itself compliant: `uv run validator.py paper.json --against paper.typ` passes. Repo: https://github.com/arquicanedo/paper-json
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。