Back to corpus
research noteexperiment writeup candidatescore 40

Motion Autocomplete Gen 8

| Gen | Focus | Key Addition | |-----|-------|--------------| | 1-5 | Foundation | Motion detection, Markov prediction, time patterns | | **6** | **Intent Recognition** | **Precursor detection, WHY-inference, goal chains** | | 7 | Holistic Awareness | Wearables + Spatial + Social + Health + Calendar | | **8** | **Living Space** | **Smart Home + Voice Override + Circadian Rhythm** |

Open full HTMLDownload HTMLCorpus JSONPaper schema

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

**AI that predicts your next physical movement and prepares context before you arrive.** | Gen | Focus | Key Addition | |-----|-------|--------------| | 1-5 | Foundation | Motion detection, Markov prediction, time patterns | | **6** | **Intent Recognition** | **Precursor detection, WHY-inference, goal chains** | | 7 | Holistic Awareness | Wearables + Spatial + Social + Health + Calendar | | **8** | **Living Space** | **Smart Home + Voice Override + Circadian Rhythm** | ### 🧠 Precursor Detector (`intent/precursor-detector.ts`) The body broadcasts intent before conscious action — a weight shift, a glance, a reach. These micro-movements give us 500-2000ms of lead time. | Precursor Type | Detection Method | Lead Time | |---------------|------------------|-----------| | weight-shift | Accelerometer center-of-gravity change | 800-1500ms | | gaze-redirect | Eye tracking / head turn | 500-1000ms | | hand-preparation | Gyroscope hand positioning | 300-800ms | | screen-disengage | Keyboard/mouse activity drop | 1000-2000ms | | postural-adjustment | Subtle position changes | 500-1000ms | | breathing-change | Heart rate variability | 1500-3000ms | ### 🎯 Intent Engine (`intent/intent-engine.ts`) Understanding WHY people move, not just WHAT they do.

Promotion decision

What has to happen next

Attach run IDs, datasets, metrics, and reproduction commands.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.