# TraCE: Trajectory Counterfactual Explanation Scores

arXiv: https://arxiv.org/abs/2309.15965 · HTML: https://mlsanity.com/paper/2309.15965/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [Counterfactual Explanations for Machine Learning on Multivariate Time Series Data](https://mlsanity.com/paper/2008.10781/) (2020)
- [Counterfactual Explanations in Sequential Decision Making Under Uncertainty](https://mlsanity.com/paper/2107.02776/) (2021)
- [On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations](https://mlsanity.com/paper/2201.09051/) (2022)
- [Navigating Explanatory Multiverse Through Counterfactual Path Geometry](https://mlsanity.com/paper/2306.02786/) (2023)

## Built on by (most cited first, 2 of 2)

- [Monitoring Sustainable Global Development Along Shared Socioeconomic Pathways](https://mlsanity.com/paper/2312.04416/) (2023)
- [Interpretable Model-Aware Counterfactual Explanations for Random Forest](https://mlsanity.com/paper/2510.27397/) (2025)

## Abstract (arXiv)

Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box classifier. In this paper, we propose to extend the use of counterfactuals to evaluate progress in sequential decision making tasks. To this end, we introduce a model-agnostic modular framework, TraCE (Trajectory Counterfactual Explanation) scores, which is able to distill and condense progress in highly complex scenarios into a single value. We demonstrate TraCE's utility across domains by showcasing its main properties in two case studies spanning healthcare and climate change.