Paperdoi:10.33774/coe-2026-pq545
Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist
Cambridge Open Engage preprint (2026-11-18; not peer reviewed)
TL;DR
Argues that a wearable 'cognitive stress' claim must beat physical exertion, not just rest. On a public PhysioNet stress vs aerobic vs anaerobic feature set (100 sessions, 41 people) it defines three checks: how much model importance sits on time-trend features (22.9% of top-30), an exertion-control effect-size ratio (HR-trend slope: stress vs aerobic d = −1.53, aerobic vs anaerobic d = −0.26), and leave-one-participant-out accuracy (0.76). Claims that fail stay 'arousal', not 'cognitive stress'.
- Form factor: wrist wearable features (public PhysioNet induced-stress / structured-exercise set) + WESAD
Abstract
Wrist research and consumer pipelines often treat elevated heart rate or skin conductance as evidence of psychological strain, a practice documented across ambulatory stress surveys and laboratory affect studies. That habit confuses constructs psychophysiology has long kept apart: seated cognitive/psychosocial demand versus physical exertion. This paper asks what a measurement model must clear if the claim is specifically cognitive. We audit a public PhysioNet induced-stress and structured-exercise feature matrix (100 sessions; 41 participants; STRESS, AEROBIC, ANAEROBIC), complement it with WESAD and electrodermal/physiological-computing standards, and define three quantities with explicit pass criteria: a temporal eligibility ratio R_t/s, an exertion-control effect-size ratio R_d on named features with 95% confidence intervals, and an exploratory person-wise leave-one-participant-out (LOPO) check. Under a frozen Random Forest and keyword contract, temporal-keyword features hold 22.9% of top-30 importance (R_t/s=0.30). For heart-rate trend slope, stress-versus-aerobic d=-1.53 (95% CI [-2.08,-0.99]) while aerobic-versus-anaerobic d=-0.26 (95% CI [-0.76,0.23]), so point R_d=5.80 (session bootstrap 95% CI [1.75,106], very wide). Pooled LOPO accuracy is 0.76 (participant-bootstrap 95% CI [0.67,0.84]) versus stratified session 5-fold 0.76 (SD 0.07). We drop cross-corpus mean-EDA "sign flip" comparisons from the gate because WESAD stress-versus-rest and PhysioNet stress-versus-exercise are not matched contrasts. A cognitive wearable claim that cannot meet the stated criteria remains an arousal claim.
Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Devices
Keywords
Datasets used
How it works
Cite this paper
Finch, E., Pokhrel, S., & Hughes, T. (2026). Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist. Cambridge Open Engage preprint. https://doi.org/10.33774/coe-2026-pq545
Finch, Eleanor, Shreyanka Pokhrel, and Tom Hughes. 2026. "Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist." Cambridge Open Engage preprint. https://doi.org/10.33774/coe-2026-pq545.
Finch, E., Pokhrel, S. and Hughes, T. (2026) 'Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist', Cambridge Open Engage preprint. doi: 10.33774/coe-2026-pq545.
Finch, Eleanor, et al. "Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist." Cambridge Open Engage preprint, 2026. https://doi.org/10.33774/coe-2026-pq545.
E. Finch, S. Pokhrel, and T. Hughes, "Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist," Cambridge Open Engage preprint, 2026, doi: 10.33774/coe-2026-pq545.
@misc{finch2026before,
title = {{Before a Wearable May Claim Cognitive Stress: A Three-Quantity Measurement Checklist}},
author = {Finch, Eleanor and Pokhrel, Shreyanka and Hughes, Tom},
year = {2026},
howpublished = {Cambridge Open Engage preprint},
doi = {10.33774/coe-2026-pq545}
}Added to the ChatPPG research hub