# Right on Time: Revising Time Series Models by Constraining their Explanations

arXiv: https://arxiv.org/abs/2402.12921 · HTML: https://mlsanity.com/paper/2402.12921/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 29 of 29)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Long-term Forecasting with TiDE: Time-series Dense Encoder](https://mlsanity.com/paper/2304.08424/) (2023)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded](https://mlsanity.com/paper/1902.03751/) (2019)
- [Deep Learning for Time Series Forecasting: Tutorial and Literature Survey](https://mlsanity.com/paper/2004.10240/) (2020)
- [Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations](https://mlsanity.com/paper/2011.12854/) (2020)
- [Darts: User-Friendly Modern Machine Learning for Time Series](https://mlsanity.com/paper/2110.03224/) (2021)
- [Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders](https://mlsanity.com/paper/1902.00450/) (2019)
- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [Towards a Rigorous Evaluation of XAI Methods on Time Series](https://mlsanity.com/paper/1909.07082/) (2019)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [Sequential Deconfounding for Causal Inference with Unobserved Confounders](https://mlsanity.com/paper/2104.09323/) (2021)
- [Explainable AI for Time Series via Virtual Inspection Layers](https://mlsanity.com/paper/2303.06365/) (2023)
- [Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders](https://mlsanity.com/paper/2303.02320/) (2023)
- [Learning by Self-Explaining](https://mlsanity.com/paper/2309.08395/) (2023)
- [Time to Focus: A Comprehensive Benchmark Using Time Series Attribution Methods](https://mlsanity.com/paper/2202.03759/) (2022)
- [One Explanation Does Not Fit XIL](https://mlsanity.com/paper/2304.07136/) (2023)

## Built on by (most cited first, 7 of 7)

- [Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation](https://mlsanity.com/paper/2412.05152/) (2024)
- [xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories](https://mlsanity.com/paper/2410.16928/) (2024)
- [QuAnTS: Question Answering on Time Series](https://mlsanity.com/paper/2511.05124/) (2025)
- [Interpretable end-to-end Neurosymbolic Reinforcement Learning agents](https://mlsanity.com/paper/2410.14371/) (2024)
- [Forecasting Company Fundamentals](https://mlsanity.com/paper/2411.05791/) (2024)
- [Multi-level Neural Networks for high-dimensional parametric obstacle problems](https://mlsanity.com/paper/2504.05026/) (2025)
- [PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention](https://mlsanity.com/paper/2608.07681/) (2026)

## Abstract (arXiv)

Deep time series models often suffer from reliability issues due to their tendency to rely on spurious correlations, leading to incorrect predictions. To mitigate such shortcuts and prevent "Clever-Hans" moments in time series models, we introduce Right on Time (RioT), a novel method that enables interacting with model explanations across both the time and frequency domains. By incorporating feedback on explanations in both domains, RioT constrains the model, steering it away from annotated spurious correlations. This dual-domain interaction strategy is crucial for effectively addressing shortcuts in time series datasets. We empirically demonstrate the effectiveness of RioT in guiding models toward more reliable decision-making across popular time series classification and forecasting datasets, as well as our newly recorded dataset with naturally occuring shortcuts, P2S, collected from a real mechanical production line.