发表机构
Tyche Institute; University of Pavia（Tyche研究所; 帕维亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文为SAFE AI合规评分引入不确定性层，通过配对自助法估计组件指标协方差，并分解偏离独立基线的效应，生成置信区域以支持合规决策。
AI 中文摘要
人工智能可信度评分正从研究仪表盘转向合规声明和采购决策。合规声明是一种基于估计的合规指标与设定阈值之间比较的统计决策。最近提出的集成式SAFE AI指标基于准确性、可解释性和鲁棒性三种基本的等级-分级度量，并在共同基础上表达。这些指标被整合为一个单一的合规评分，目前仅以点值形式报告。本文提出为SAFE AI合规评分增加不确定性层。所有组成指标均在共享测试样本上估计，因此其误差具有协变性。我们使用配对自助法估计组成向量的完整协方差，并量化与集成指标框架的变异性分解所建议的源间独立基线的偏离。一个闭式恒等式将这种偏离分解为不确定性加权的有效维度和暴露加权的数据驱动相关性，两者均依赖于聚合器及组成指标的估计不确定性。我们将该方法应用于真实和模拟数据，结果表明独立性假设可能使置信带变窄或变宽，而效应的方向和幅度取决于聚合器类型、机器学习模型和扰动族。所得的置信区域支持合规决策，并可记录在正式的不确定性证书中。
英文摘要
Artificial Intelligence trustworthiness scores are moving from research dashboards into compliance claims and procurement decisions. A compliance claim is a statistical decision based on the comparison between an estimated compliance metric and a set threshold. The recently proposed integrated SAFE AI metrics are based on three basic rank-graduation measures of accuracy, explainability and robustness, expressed on a common footing. The metrics are integrated into a single compliance score, so far reported as a point value. In this paper we propose to add an uncertainty layer to the SAFE AI compliance score. All component metrics are estimated on a shared test sample, so their errors covary. We estimate the full covariance of the component vector with a paired bootstrap, and quantify departures from the source-wise independence baseline suggested by the integrated-metrics framework's variability decomposition. A closed-form identity splits such departure into an uncertainty-weighted effective dimension and an exposure-weighted data-driven correlation, with both depending on the aggregator and the estimated uncertainty of the component metrics. The application of our proposal to both real and simulated data shows that the assumption of independence can either narrow or widen confidence bands, while the direction and magnitude of the effect depend on the aggregator type, machine learning model, and perturbation family. The resulting confidence region supports compliance decisions, which can be documented in a formal uncertainty certificate.
Comments17 pages, 3 figures, 4 tables. Code and run records: https://github.com/safe-composed-uncertainty/composed-uncertainty
