# Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventions

arXiv: https://arxiv.org/abs/2512.14559 · HTML: https://mlsanity.com/paper/2512.14559/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review](https://mlsanity.com/paper/2010.10596/) (2020)
- [LSTM Fully Convolutional Networks for Time Series Classification](https://mlsanity.com/paper/1709.05206/) (2017)
- [Bake off redux: a review and experimental evaluation of recent time series classification algorithms](https://mlsanity.com/paper/2304.13029/) (2023)
- [Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)](https://mlsanity.com/paper/2005.13997/) (2020)
- [Instance-based Counterfactual Explanations for Time Series Classification](https://mlsanity.com/paper/2009.13211/) (2020)
- [Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications](https://mlsanity.com/paper/2103.04244/) (2021)
- [On the Adversarial Robustness of Causal Algorithmic Recourse](https://mlsanity.com/paper/2112.11313/) (2021)
- [Counterfactual Explanations for Machine Learning on Multivariate Time Series Data](https://mlsanity.com/paper/2008.10781/) (2020)
- [Evaluating Robustness of Counterfactual Explanations](https://mlsanity.com/paper/2103.02354/) (2021)
- [Conditional Generative Models for Counterfactual Explanations](https://mlsanity.com/paper/2101.10123/) (2021)
- [Self-Interpretable Time Series Prediction with Counterfactual Explanations](https://mlsanity.com/paper/2306.06024/) (2023)
- [Promoting Counterfactual Robustness through Diversity](https://mlsanity.com/paper/2312.06564/) (2023)
- [Generating robust counterfactual explanations](https://mlsanity.com/paper/2304.12943/) (2023)
- [Motif-guided Time Series Counterfactual Explanations](https://mlsanity.com/paper/2211.04411/) (2022)
- [Generating Sparse Counterfactual Explanations For Multivariate Time Series](https://mlsanity.com/paper/2206.00931/) (2022)
- [M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps](https://mlsanity.com/paper/2411.02649/) (2024)
- [Shapelet-Based Counterfactual Explanations for Multivariate Time Series](https://mlsanity.com/paper/2208.10462/) (2022)
- [Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification](https://mlsanity.com/paper/2402.01343/) (2024)
- [TSInterpret: A unified framework for time series interpretability](https://mlsanity.com/paper/2208.05280/) (2022)
- [Towards a Comprehensive Human-Centred Evaluation Framework for Explainable AI](https://mlsanity.com/paper/2308.06274/) (2023)
- [XTSC-Bench: Quantitative Benchmarking for Explainers on Time Series Classification](https://mlsanity.com/paper/2310.14957/) (2023)
- [Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification](https://mlsanity.com/paper/2408.12666/) (2024)

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

- [What-If Explanations Over Time: Counterfactuals for Time Series Classification](https://mlsanity.com/paper/2603.27792/) (2026)
- [IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution](https://mlsanity.com/paper/2608.04777/) (2026)

## Abstract (arXiv)

Counterfactual explanations are increasingly proposed as interpretable mechanisms to achieve algorithmic recourse. However, current counterfactual techniques for time series classification are predominantly designed with static data assumptions and focus on generating minimal input perturbations to flip model predictions. This paper argues that such approaches are fundamentally insufficient in clinical recommendation settings, where interventions unfold over time and must be causally plausible and temporally coherent. We advocate for a shift towards counterfactuals that reflect sustained, goal-directed interventions aligned with clinical reasoning and patient-specific dynamics. We identify critical gaps in existing methods that limit their practical applicability, specifically, temporal blind spots and the lack of user-centered considerations in both method design and evaluation metrics. To support our position, we conduct a robustness analysis of several state-of-the-art methods for time series and show that the generated counterfactuals are highly sensitive to stochastic noise. This finding highlights their limited reliability in real-world clinical settings, where minor measurement variations are inevitable. We conclude by calling for methods and evaluation frameworks that go beyond mere prediction changes without considering feasibility or actionability. We emphasize the need for actionable, purpose-driven interventions that are feasible in real-world contexts for the users of such applications.