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

翻译：大语言模型代理通常充当学术论文的首要（有时是唯一）读者，用于快速浏览次级声明、提取可复现步骤并泛化研究范围。标准散文体论文在此角色中暴露出反复出现的缺陷：无法以子论文粒度引用的次级声明、超出论文实际验证范围的范围过度延伸、以及埋没在代码库而非论文本身中的图表命令。我们提出`论文.json`方案——一份随PDF携带的配套JSON文件，通过轻量级规范解决上述问题：稳定声明标识符(C1)、显式“未声称”列表(C2)、精确的逐图Shell命令(C3)及稳定定义标识符(C5)。第五项规范(C4)主张：最低可行合规性——在PDF旁手动编写JSON文件——可在不修改人类可读输出前提下，于完成论文后一小时内实现。C1、C2、C3与C5均为开放邀约：读取并执行合规论文的代理将产生支持或反对这些规范的经验证据。本文自身已实现合规：`uv run validator.py paper.json --against paper.typ`验证通过。代码仓库：https://github.com/arquicanedo/paper-json