Submissions

Counterfactual reasoning has a long history in the field of psychology, and is core to many cognitive processes such as causal explanations, responsibility attributions, and moral judgments. With the number of machine learning approaches using elements of causal modeling on the rise, there has been increasing interest in the development of methods that perform counterfactual computations. In this workshop, we aim to bring together the empirical study of human counterfactual reasoning and the mathematical rigor of causal machine learning. We invite researchers from a broad range of disciplines including computer science, cognitive psychology, and philosophy to submit their latest work related to counterfactual reasoning and its applications. We especially encourage emerging scholars and members of under-represented groups to apply. 

We welcome submissions of full papers as well as work-in-progress and accept submissions of work recently published or currently under review. Topics of interest include (but are not limited to):

• empirical studies on causal and counterfactual reasoning in humans, including its emergence, development, and function

• structural causal models & conditions for counterfactual identifiability

• computation of bounds for counterfactual quantities

• causal algorithmic recourse

• counterfactual notions of fairness

• deep learning models for counterfactual inference

• counterfactual-based methods for personalized healthcare

• offline reinforcement learning

• position papers about the role of counterfactual reasoning in explainable AI

Submission guidelines

Submissions must be at most 8 pages long (not including references). An unlimited number of pages for supplemental material can be included, which reviewers are not required to take into account. The main content, references and appendices should be submitted as a single pdf file and adhere to the ICML format (LaTeX template). Papers should be anonymized and submitted via CMT.

Accepted papers will be presented as posters, and a subset of them will be selected for oral presentation. Please note that this is a primarily in-person workshop, and at least one author of each accepted paper is expected to attend the workshop in person.

The workshop will not have formal proceedings, but authors of accepted papers can choose to have either a link to an arXiv version of their paper or a pdf published on the workshop webpage.

Important Dates

• Submission deadline: May 26, 2023 (AoE)

• Notification of acceptance: June 19, 2023

• Camera-ready version deadline: July 14, 2023

• Workshop date: July 29, 2023