ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction

Abstract:We study when a wearable stress system should surface a prediction rather than change it. In low-stakes reflection and summary settings, aggregate accuracy is insufficient because withholding can reduce error while leaving some people with little or no information. We formulate fixed-label reliability routing: after a locked classifier emits a protocol-defined stress/non-stress label, a post-hoc gate surfaces that unchanged label or withholds it as unavailable. ReliaGate assembles established confidence, signal-quality/trust, agreement, train-standardized atypicality, and train-fitted geometry cues into a post-hoc correctness score. We evaluate four wearable datasets using subject-disjoint folds, validation-selected routing, paired held-out-subject intervals, and pooled and per-subject analyses. WESAD point estimates favored ReliaGate, UBFC-Phys primary coverage/risk intervals favored ReliaGate, and E4 checks were mixed. ReliaGate provides an operational framework for studying surfaced-label error, output availability, and accepted-output distribution across subjects, without revising labels or providing clinical or finite-sample risk guarantees.

Accepted at WellComp 2026, held with UbiComp/ISWC 2026. 7 pages, 4 tables, and 1 figure. To appear in UbiComp Companion '26. ACM DOI: https://doi.org/10.1145/3798063.3841770

Machine Learning (cs.LG); Human-Computer Interaction (cs.HC)

arXiv:2608.15951 [cs.LG]

(or arXiv:2608.15951v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.15951 arXiv-issued DOI via DataCite (pending registration)