我们准备好迎接人工智能驱动的发现了吗？在下一次基础物理学突破之前进行人工智能验证
Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough
浏览论文内容
中文总结 AI 辅助
探讨在基础物理学中，随着机器学习日益自主，确保其可靠性至关重要。通过VERaiPHY计划框架，结合统计发现工作流程确定验证时机，强调归纳偏差等局限，思考物理学家角色，以实现机器学习在物理学中负责任的整合。
中文摘要 AI 辅助
机器学习（ML）已成为基础物理学不可或缺的一部分，加速了从数据采集到推理和假设检验的统计工作流程。随着ML系统变得越来越自主，确保它们对发现声明的可靠性变得至关重要。本综述综合了VERaiPHY（物理学中稳健人工智能的验证与评估）计划在粒子物理学、天体物理学和宇宙学中进行严格ML评估的框架。我们通过将ML置于统计发现工作流程中来确定何时验证至关重要。我们强调了基本局限性：归纳偏差不可避免，样本复杂性限制学习，实验约束限制发现。我们思考了物理学家作为实验设计者和评估者不断演变的角色，他们的判断将科学严谨性编码到人工智能系统中。负责任的整合需要在理解ML变革潜力的同时了解其内在边界。
英文摘要
Machine learning (ML) has become integral to fundamental physics, accelerating statistical workflows from data acquisition through inference and hypothesis testing. As ML systems grow increasingly autonomous, ensuring their reliability for discovery claims becomes critical. This review synthesizes the VERaiPHY (Validation & Evaluation for Robust AI in PHYsics) initiative's frameworks for rigorous ML assessment across particle physics, astrophysics, and cosmology. We establish when verification is essential by contextualizing ML within the statistical discovery workflow. We emphasize fundamental limitations: inductive bias is unavoidable, sample complexity bounds learning, and experimental constraints limit discovery. We reflect on physicists' evolving role as both experimental designers and evaluators whose judgments encode scientific rigor into AI systems. Responsible integration requires understanding ML's transformative potential alongside its intrinsic boundaries.
发表机构
- NSF AI Institute for Artificial Intelligence and Fundamental Interactions（NSF人工智能与基本相互作用研究院）
- MIT Laboratory for Nuclear Science（MIT核科学实验室）
- School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）
- Nagoya University（名古屋大学）
- Technical University Munich（慕尼黑技术大学）
- Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
机构由 AI 辅助整理，请以论文原文为准。
