# A foundation model for electrodermal activity data

arXiv: https://arxiv.org/abs/2603.16878 · HTML: https://mlsanity.com/paper/2603.16878/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 90 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Metrics for Multi-Class Classification: an Overview](https://mlsanity.com/paper/2008.05756/) (2020)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Large-scale Training of Foundation Models for Wearable Biosignals](https://mlsanity.com/paper/2312.05409/) (2023)
- [ECG-FM: An Open Electrocardiogram Foundation Model](https://mlsanity.com/paper/2408.05178/) (2024)
- [Data Diversity Matters for Robust Instruction Tuning](https://mlsanity.com/paper/2311.14736/) (2023)
- [PaPaGei: Open Foundation Models for Optical Physiological Signals](https://mlsanity.com/paper/2410.20542/) (2024)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence](https://mlsanity.com/paper/2007.13018/) (2020)
- [Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings](https://mlsanity.com/paper/2502.01108/) (2025)
- [Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals](https://mlsanity.com/paper/2412.09758/) (2024)
- [Mantis: Lightweight Foundation Model for Time Series Classification](https://mlsanity.com/paper/2502.15637/) (2025)
- [A multimodal sensor dataset for continuous stress detection of nurses in a hospital](https://mlsanity.com/paper/2108.07689/) (2021)
- [Momentary Stressor Logging and Reflective Visualizations: Implications for Stress Management with Wearables](https://mlsanity.com/paper/2401.16307/) (2024)
- [Boosting DNN Cold Inference on Edge Devices](https://mlsanity.com/paper/2206.07446/) (2022)
- [SingLEM: Single-Channel Large EEG Model](https://mlsanity.com/paper/2509.17920/) (2025)
- [Too Good To Be True: performance overestimation in (re)current practices for Human Activity Recognition](https://mlsanity.com/paper/2310.11950/) (2023)

## Built on by (most cited first, 1 of 1)

- [Detecting Agitation Before Behavioral Escalation in Autistic Youth Through Multimodal Wearable Sensing](https://mlsanity.com/paper/2609.24791/) (2026)

## Abstract (arXiv)

Foundation models have recently extended beyond natural language and vision to timeseries domains, including physiological signals. However, progress in electrodermal activity (EDA) modeling is hindered by the absence of large-scale, curated, and openly accessible datasets. EDA reflects sympathetic nervous system activity and is widely used to infer cognitive load, stress, and engagement. Yet very few wearable devices provide continuous, unobtrusive sensing, and the only large-scale archive to date is proprietary. To address this gap, we compile EDAMAME, a collection of EDA traces from 24 public datasets, comprising more than 25,000 hours from 634 users. Using this resource, we train UME, the first dedicated foundation model for EDA. In eight out of ten scenarios, UME outperforms baselines and matches generalist timeseries foundation models while using 20x fewer computational resources. Our findings, however, also highlight the intrinsic challenges of EDA modeling, motivating further research to unlock its full potential. All datasets, model weights, and code are released to support further research.