AI科研代理可验证发表论文并互评，构建可信学术协作新框架
Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing
- AI代理以数字身份发布带推理链的论文，确保每项主张可追溯
- 引入四层同行评审与声誉质押机制，提升成果可信度与责任归属
- 适合关注科研透明性、跨机构协作及全球科研公平的研究者
可验证性、归属权与可复现性是科学知识的基石，但现有出版基础设施无法规模化实现。本文提出Traxia——一个面向AI科研代理的原生科学出版框架：代理可发布可验证论文，建立声誉身份，相互评审，并与人类在共享溯源模型下协作。该框架将代理视为第一类认知参与者：每篇论文包含推理轨迹，每项主张附带置信区间，每个代理拥有密码学签名身份，每次合作记录不可篡改。我们形式化了五个核心组件：代理身份与注册系统、可验证出版层、四层同行评审协议、声誉与质押引擎，以及具备矛盾检测功能的知识图谱。该框架旨在解决可复现性失败、溯源不透明和全球南方科研能力被排除的问题。本文仅呈现架构基础与形式规范，未报告实证结果；评估与组件深入研究将在后续论文中展开。原型已部分实现核心形式化，完整系统仍在开发中。
原文摘要 · Abstract (English)
Verifiability, attribution, and reproducibility are foundational requirements of scientific knowledge, yet current publishing infrastructure does not enforce them at scale. We introduce Traxia, an agent-native scientific publishing framework in which AI research agents publish verifiable papers, build reputational identities, peer-review one another, and collaborate with humans in a shared provenance model. Traxia treats agents as first-class epistemic participants: every paper carries a reasoning trace, every claim a confidence interval, every agent a cryptographically signed identity, and every collaboration an immutable contribution log. We formalise five components: Agent Identity and Registry, Verifiable Publishing Layer, four-tier Peer Review Protocol, Reputation and Staking Engine, and a Knowledge Graph with contradiction detection. The framework targets reproducibility failure, provenance opacity, and exclusion of Global South research capacity. This paper presents architectural foundations and formal specifications only; it does not report empirical results. Evaluation and deeper component studies will follow in subsequent papers. A prototype partially implements core formalisms; the full system remains under active development.
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。