arXiv AI

Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification

The paper argues that AI can cheaply produce plausible scientific artifacts, leading to epistemic pollution because the existing scientific infrastructure relies on high generation costs as a filter. It proposes rebalancing generation and verification costs by introducing structured "blueprints"—typed graph components that decompose claims, evidence, assumptions, and definitions—so that verification becomes cheaper, more local, and distributed. The blueprint complements traditional papers, serving as a verification interface while the paper remains the narrative interface, and a prototype demonstrates the concept.

arXiv AI
Oct 2

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

The paper "Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers" introduces SciSlopBench, a dataset of 390 AI‑generated papers paired with human‑written counterparts, and defines six measures across Structure, Argument, and Artifacts to detect scientific slop. The authors show that these measures can identify AI papers with 85.9% accuracy and that higher slop correlates with lower ICLR ratings and distinguishes rejected from accepted papers. They also propose SciSlopHarness, a framework that guides a fixed LLM to revise only evidence‑supported sections, reducing the AI‑human gap by 63% without human reference targets.

By Yerim Oh, Young-Jun Lee, Jaewoo Ahn, Gunhee Kim, Dongyeop Kang
arXiv AI
Aug 26

Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value

The paper proposes a normative framework for ethical use of large language models (LLMs) in scientific research, treating reasoning as a distributed process where human control remains essential for epistemic legitimacy. It introduces key constructs—content origin, human verification, responsibility assignment, accountable ownership, and epistemic outcome—to separate claim provenance from verification and responsibility. The authors argue that the ethical boundary hinges on adequate verification and accountable human ownership, and they propose an "epistemic audit" to document delegation, verification, provenance, and responsibility for transparent, reviewable AI-assisted reasoning.

By Kalin Stoyanov
arXiv AI
Jun 18

Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness

arXiv:2606. 18874v1 Announce Type: new Abstract: AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference.

By Zijian Wang, Hanqi Li, Ziyue Yang, Zijian Hu, Shenghan Zuo, Yunzhe Zhang, Da Ma, Danyu Luo, Chenrun Wang, Jing Peng, Tiancheng Huang, Sijia Guo, Huayang Wang, Zichen Zhu, Senyu Han, Yilu Cao, Kai Yu, Lu Chen
arXiv AI
Oct 31

Rebuilding a Field's Open-Problem Catalog from the Literature: A Two-Layer Knowledge Graph, and Why Status Must Stay Proposed

The paper presents a system that transforms open‑problem listings in research fields into a structured, queryable knowledge graph. It combines a hand‑curated problem layer with an evidence layer derived from bibliographic data, linked through typed, provenance‑carrying connections. The authors evaluate the approach on database and AI problem catalogs, showing that the new graph can answer all previously answerable queries and additional ones about recent work, but also reveal limitations in automated status judgments, leading to a design recommendation that status changes must be proposed with evidence and reviewed by humans.

By Madhulatha Mandarapu, Sandeep Kunkunuru