Counterfactual reasoning -- envisioning hypothetical scenarios, or possible worlds, where some circumstances are different from what (f)actually occurred (counter-to-fact) -- is ubiquitous in human cognition. Conventionally, counterfactually-altered circumstances have been treated as "small miracles" that locally violate the laws of nature while sharing the same initial conditions. In Pearl's structural causal model (SCM) framework this is made mathematically rigorous via interventions that modify the causal laws while the values of exogenous variables are shared. In recent years, however, this purely interventionist account of counterfactuals has increasingly come under scrutiny from both philosophers and psychologists. Instead, they suggest a backtracking account of counterfactuals, according to which the causal laws remain unchanged in the counterfactual world; differences to the factual world are instead "backtracked" to altered initial conditions (exogenous variables). In the present work, we explore and formalise this alternative mode of counterfactual reasoning within the SCM framework. Despite ample evidence that humans backtrack, the present work constitutes, to the best of our knowledge, the first general account and algorithmisation of backtracking counterfactuals. We discuss our backtracking semantics in the context of related literature and draw connections to recent developments in explainable artificial intelligence (XAI).

翻译：反事实推理——构想假设性场景或可能世界，其中某些情况与（事实）发生的实际情形不同（反事实）——在人类认知中无处不在。传统上，反事实改变的情景被视为"微小奇迹"，它们局部违反自然法则，但共享相同的初始条件。在珀尔的结构因果模型（SCM）框架中，这一概念通过干预实现数学上的严谨化：干预修改因果法则，而外生变量的取值保持不变。然而近年来，这种纯粹干预主义的反事实解释日益受到哲学家和心理学家的质疑。他们提出反事实的"回溯"解释，认为在反事实世界中因果法则保持不变；与事实世界的差异反而"回溯"至改变的初始条件（外生变量）。在本研究中，我们探索并在SCM框架内形式化这种替代性的反事实推理模式。尽管有充分证据表明人类会进行回溯推理，但据我们所知，本研究首次系统阐述了回溯反事实的一般性理论并提出了算法化方案。我们结合相关文献讨论了回溯语义学，并联系可解释人工智能（XAI）领域的最新进展。