发表机构
Axiom Research Group; The Nelson Mandela African Institution of Science and Technology; African Institute for Mathematical Sciences; The University of Tokyo（阿克西姆研究集团; 纳尔逊·曼德拉非洲科学技术研究院; 非洲数学科学研究所; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SEAM是一种与生成器无关的科学机器学习框架，可跨多维度计算局部到全局的一致性，能在局部预测准确时检测不兼容解释并归因故障，为模型提供全局解释一致性审计。
AI 中文摘要
科学机器学习通常在子域、基准划分或单个预测的解释层面验证模型，但这类局部检查无法确定生成的解释能否组装成一个全局可接受的解释。我们引入科学解释可容许性机器（Scientific Explanation-Admissibility Machines, SEAM），这是一种与生成器无关的框架，可跨区域、传感器、机制和模型组件计算这种局部到全局的一致性问题。有限解释层束实例化SEAM-Ω，通过带有状态、闭包和观测通道以及可选契约元数据的结构化表示每个区域；比较相邻解释在重叠部分的一致性；将不一致转化为通道解析的障碍。该障碍可定位不一致性，并通过将每个修复限制在某个解释允许的修订范围内来测试相互竞争的声明性说明。精确可行性可反驳或保留某个说明；当无法进行精确修复时，感知残差的正则化记录会提供单独标记的经验归因。该框架还可区分不一致性与不可识别性，并在分布偏移下监控学习到的生成器。我们建立了最小成本干预和守恒契约可检测性的定理，以及不可识别性和闭包可恢复性的配套结果。在涉及合成偏微分方程系统和分布外傅里叶神经算子（FNO）监测的19项实验中，SEAM即使在局部预测准确时也能检测到不兼容的解释，并将故障归因于特定通道和重叠部分。SEAM为现有求解器和学习模型增加了全局解释一致性审计，以测试它们的局部解释是否构成连贯的科学说明。
英文摘要
Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction. Yet such local checks cannot establish whether the resulting explanations can be assembled into one globally admissible explanation. We introduce Scientific Explanation-Admissibility Machines (SEAM), a generator-agnostic framework that makes this local-to-global consistency question computable across regions, sensors, regimes, and model components. The finite explanation-sheaf instantiation SEAM-$Ω$ represents each region by a structured explanation with state, closure, and observation channels together with optional contract metadata; compares neighboring explanations on their overlaps; and converts disagreement into a channel-resolved obstruction. This obstruction locates inconsistency and tests competing declared accounts by restricting each repair to the revisions that one account permits. Exact feasibility refutes or retains an account; when exact repair is unavailable, residual-aware regularized records provide a separately labeled empirical attribution. The framework also separates inconsistency from non-identifiability and monitors learned generators under distribution shift. We establish theorems for minimum-cost intervention and conservation-contract detectability, together with companion results for identifiability and closure recoverability. Across nineteen experiments involving synthetic partial differential equation systems and out-of-distribution Fourier neural operator (FNO) monitoring, SEAM detects incompatible explanations even when local predictions are accurate, and attributes failures to specific channels and overlaps. SEAM adds a global explanation-consistency audit to existing solvers and learning models, testing whether their local explanations form a coherent scientific account.
Comments43 pages, 9 figures
