研究人员开发了Agentic Reproducibility Assessment (ARA)系统，旨在通过自动评估研究论文的可复现性来辅助科学同行评审。ARA从论文中构建工作流图，连接来源、方法和输出，然后对其可重构性进行评分。在对计算可复现性研究的大型基准测试中，ARA表现出显著的准确性，在关键评估中优于先前的方法，并显示出扩大可复现性评估规模的潜力。 AI
影响 自动化了科学出版中一个关键但耗时的环节，有望加速研究验证。
排序理由 该集群描述了一篇关于用于科学可复现性评估的新型AI系统的研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.02651v1 Announce Type: cross Abstract: Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, d…
Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, data flows, and result-generating procedures, which…
Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, data flows, and result-generating procedures, which…