video1.0<iframe src="https://www.loom.com/embed/5a413159256a41c99f9a49b9e0b514ad" frameborder="0" width="1668" height="1251" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12511668Loomhttps://www.loom.com12511668https://cdn.loom.com/sessions/thumbnails/5a413159256a41c99f9a49b9e0b514ad-9fbb9ca169b9568e.gif298.816This Loom presents a Paperclip-based evidence digest to identify wearable signals correlating with cognitive impairment and select the most accurate sensory hardware. The creator copies a question into Cloud Code, runs a pipeline that takes about half an hour, and produces a scaffolded evidence digest organized by sub-questions. Across studies, the strongest and most consistent signals are gait and mobility metrics and circadian rest activity metrics, with delirium showing a partial carve-out. The synthesis also notes that the literature has not formally connected hardware measurement accuracy to downstream cognitive detection performance, and mentions a bug where DOIs can be hallucinated due to non-deterministic processing.