GroundSignal — The Sidewalk Told on Itself

Description and use

GroundSignal turns phone motion data into a private, inspectable surface report using TabPFN and local storage, without collecting location data.

Problem

How to turn motion data from a phone into useful, privacy‑preserving surface evidence without turning it into surveillance.

Outcome

GroundSignal provides a privacy‑first, local‑first surface‑classification workflow that outputs probability‑aware reports without collecting location data.

Workflow

• Choose mobility mode and phone placement
• Record at least two known surface types
• Start an audit and place phone in pocket/bag/mount
• Move naturally while GroundSignal records motion locally
• Finish audit and inspect surface signals
• Confirm, correct, or discard uncertain predictions
• Export evidence as CSV or JSON

Evidence

GroundSignal started with one question: can the motion already happening in your pocket become useful evidence without becoming surveillance?

Source

The AI core is TabPFN, which is well suited to the small, personal calibration sets this problem creates—and gives me probability evidence instead of a mystery label.

Source

GroundSignal is a local‑first pocket field instrument for the Hacktoberfest 2026 Week 1 Touch Grass challenge.

Source

Raw motion stays on the device. Only bounded derived features and personal calibration labels cross the explicit analysis boundary; probabilities return for local human review.

Source