立场论文：AI 时代的科学应重新平衡知识产物的生成成本与验证成本
Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification
AI 导读
一篇立场论文提出，AI 让论文、综述等看似可信的科学产物生成成本骤降，导致“知识污染”风险，而验证成本并未同步下降，因此应在产物层面重新设计科学的知识基础设施以再平衡生成与验证成本。作者提出 blueprints：将主张、证据、假设和定义表示为带类型图组件的结构化分解产物，与论文互补——论文仍是叙事界面，blueprint 成为验证接口。论文还给出了概念验证原型。
正文 · 原文
Abstract:AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of \emph{epistemic pollution} in our scientific systems, where unreliable but plausible-looking artifacts can accumulate faster than the system can filter them out. The problem is structural: the epistemic infrastructure of science was calibrated to a world where producing a plausible artifact required substantial expertise, labor, and time, so generation cost itself served as a rough filter; AI weakens that filter without comparably lowering verification cost. This position paper argues that \textbf{AI-era science should rebalance the costs of generating and verifying scientific artifacts by redesigning epistemic infrastructure at the level of the artifact}. The current paper-centered system makes verification expensive: papers compress long-context scientific logic into prose, forcing reviewers, human or AI, to reconstruct underlying argument structure before they can evaluate it. As one step in this direction, we propose \textbf{blueprints}: structured, decomposed research artifacts that represent claims, evidence, assumptions, and definitions as typed graph components. Blueprints complement rather than replace papers---the paper remains the narrative interface, the blueprint becomes the verification interface---and are designed to trade an upfront generation cost for cheaper, more local, more distributed verification downstream. We also instantiate the proposal in a proof-of-concept prototype.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.10425 [cs.CY] |
| (or arXiv:2605.10425v2 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10425 arXiv-issued DOI via DataCite |
Submission history
From: Jiaqi W. Ma [view email]
[v1]
Mon, 11 May 2026 12:00:13 UTC (375 KB)
[v2]
Tue, 10 Nov 2026 08:48:00 UTC (745 KB)
来源：arXiv cs.AI · arxiv.org