校准解释：带不确定信息和反事实分析（英文版）

英文标题：Calibrated Explanations: with Uncertainty Information and Counterfactuals中文摘要：本文介绍了一种基于 Venn-Abers 的新型特征重要性解释方法 Calibrated Explanations，该方法能校准底层模型、生成特征重要性解释并对概率估计和特征重要性权重进行不确定性量化。此外，该方法对模型没有偏见、规则易于理解、可生成反事实解释和不确定性量化。英文摘要：Artificial Intelligence (AI) has become an integral part of decision supportsystems (DSSs) in various domains, but the lack of transparency in thepredictive models used in AI-based DSSs can lead to misuse or disuse.Explainable Artificial Intelligence (XAI) aims to create A