Summary
WearableQA is a new benchmark introduced by researchers including Ji Soo Lee, Xilun Chen, and Jason Wei to evaluate whether AI systems can reason over real users' longitudinal wearable records. The benchmark contains 4,084 ten-option multiple-choice questions built from wearable time series, blood biomarkers, and demographic data of 200 real users, each with up to 500 days of daily measurements. Unlike prior datasets, WearableQA preserves authentic wearable signal distributions, including device noise and inter-individual variability. The benchmark defines 16 question types along two complementary axes: data reasoning (computation over longitudinal measurements) versus health reasoning (physiological interpretation). Released on arXiv (2609.05405), WearableQA addresses the gap in existing evaluations of AI health reasoning over continuous physiological and behavioral monitoring data.
Paper Overview
Field: NLP
Authors: Ji Soo Lee, Xilun Chen, Pierce Chuang, Ashish Shenoy, Jason Wei, Dohwan Ko, Hyunwoo J. Kim, Benoit Corda
Published: 2026-09-04
arXiv: 2609.05405
Abstract
Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing benchmarks rarely evaluate whether AI systems can reason over a real user's longitudinal wearable record. We introduce WearableQA, a benchmark comprising 4,084 10-option multiple-choice questions constructed from the wearable time series, blood biomarkers, and demographics of 200 real users, each with up to 500 days of daily measurements. WearableQA preserves authentic wearable distributions that include device noise and inter-individual variability. To evaluate distinct reasoning capabilities, we introduce 16 question types organized along two complementary axes: data versus health reasoning, which distinguishes computation over longitudinal measurements from physiological interpretation.
*(Abstract truncated in source; see arXiv page for the full text.)*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634618