Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
- License
- MIT
- Signals
- PPG, IMU, EDA, Temp
- Type
- Task model
- Form factor
- Not reported
- Parameters
- Not reported
- Architecture
- Not reported
- Venue
- Not reported
- Year
- Not reported
- arXiv
- Not reported
- DOI
- Not reported
- Weights
- Not released
- Licence
- MIT (opens in a new tab)
- Caveats
- Not reported
- Added
- Oct 19, 2026
- Updated
- Oct 19, 2026
Original description
Authenticated aggregate-only reproduction and provenance code for the paper accepted at WellComp 2026.
Jaden Moon, Yvonne Wu, Arvind Pillai, and Andrew T. Campbell. 2026. ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction. The 9th Workshop on Computing for Well-being (WellComp 2026), ACM UbiComp/ISWC 2026.
A locked upstream model emits a protocol-defined stress/non-stress label. ReliaGate estimates whether that fixed label is likely to be correct and either surfaces it unchanged or withholds it. Routing changes availability, not the predicted class.
Verbatim fromGitHub· Description from the repository README; licence: MIT
How it works
Datasets linked in the hub; pretraining vs evaluation roles follow the paper.
- Inputs
- PPG, IMU, EDA, Temp
- Approach
- code release · no weights
Devices· 2
Full photo credits and licences are on each device page. An icon means we have no openly licensed or manufacturer-cleared photo of that exact device yet.
Datasets· 3
Papers· 1
Authors· 4
Cite
APA
ReliaGate. (n.d.).
BibTeX
@misc{reliagatereliagate,
title = {{ReliaGate}}
}Built from the hub record. Check it against the publisher before submitting.
History
Added to the ChatPPG research hub