CoDaS prioritizes wearable candidate biomarkers via multi-agent hypothesis generation, deterministic stats, adversarial checks, and literature grounding, recovering circadian-instability and fitness signals with modest incremental predictive value.
The train/test split prevents data leakage, but an improvement on this metric is expected by the design of the check
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data
CoDaS prioritizes wearable candidate biomarkers via multi-agent hypothesis generation, deterministic stats, adversarial checks, and literature grounding, recovering circadian-instability and fitness signals with modest incremental predictive value.