# Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI

arXiv: https://arxiv.org/abs/2605.10425 · HTML: https://mlsanity.com/paper/2605.10425/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 21 of 21)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025)
- [SciFact-Open: Towards open-domain scientific claim verification](https://mlsanity.com/paper/2210.13777/) (2022)
- [Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards](https://mlsanity.com/paper/2505.04966/) (2025)
- [Scientific production in the era of Large Language Models](https://mlsanity.com/paper/2601.13187/) (2026)
- [When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research](https://mlsanity.com/paper/2505.11855/) (2025)
- [REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?](https://mlsanity.com/paper/2507.18901/) (2025)
- [HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences](https://mlsanity.com/paper/2601.18724/) (2026)
- [The Last Human-Written Paper: Agent-Native Research Artifacts](https://mlsanity.com/paper/2604.24658/) (2026)
- [Academic journals' AI policies fail to curb the surge in AI-assisted academic writing](https://mlsanity.com/paper/2512.06705/) (2025)
- [Position: The ML Community Must Build an AI-Augmented Peer-Review Ecosystem](https://mlsanity.com/paper/2506.08134/) (2025)
- [Stop DDoS Attacking the Research Community with AI-Generated Survey Papers](https://mlsanity.com/paper/2510.09686/) (2025)
- [Micropublications: a Semantic Model for Claims, Evidence, Arguments and Annotations in Biomedical Communications](https://mlsanity.com/paper/1305.3506/) (2013)
- [The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research](https://mlsanity.com/paper/2602.18458/) (2026)
- [Nanopublication-Based Semantic Publishing and Reviewing: A Field Study with Formalization Papers](https://mlsanity.com/paper/2203.01608/) (2022)
- [An Intelligent Infrastructure as a Foundation for Modern Science](https://mlsanity.com/paper/2508.10051/) (2025)

## Abstract (arXiv)

AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of 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. We argue that AI-era science should treat this as an engineering problem: redesigning epistemic infrastructure to rebalance the costs of generation and verification. 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 blueprints as preliminary epistemic infrastructure: structured, decomposed research artifacts that represent claims, evidence, assumptions, and definitions as typed graph components. Blueprints are designed to trade an upfront generation cost for cheaper, more local, more distributed verification downstream. We have instantiated the proposal in a proof-of-concept prototype.