# H-Meta

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Hasini Sirigari](https://cerebralvalley.ai/u/hsirigar)
- **GitHub:** https://github.com/hsirigar/meta-hack
- **Demo video:** https://youtu.be/f3PS5RCXb7s
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4281

Ghostline is an AI agent that runs the scientific method on a phone video. You film a physical system, such as a pendulum or falling coffee filters. Ghostline tracks it, turns pixels into a calibrated time series, and fits competing physical laws (linear vs nonlinear pendulum, linear vs quadratic drag) on the first 60% of the clip only. Each law must then predict the rest, and its prediction is drawn as a translucent "ghost" over the real video. You can see which law follows reality and which drifts away.

The problem: AI tools for science tend to give a confident answer even when the data can't support it. Ghostline is built to be honest about evidence:
• If the models differ by less than the measurement noise, it says "Inconclusive" instead of picking one.
• It then designs the experiment that will decide: it searches the knob you control (release angle, number of filters) for the setting where the models disagree most.
• It freezes every model's predictions into a SHA-256 hash before you film, so the result can't be tuned after the fact.
• On the reveal, it verifies the hash and scores the frozen predictions. If the camera was bumped or tracking was lost, it marks the run INVALID instead of scoring it.
• If no candidate law fits, it says so and names the likely cause.

Numbers come from code, never from the LLM: measurement, fitting, simulation and scoring are deterministic Python. The agent reasons, picks tools and explains.

Results:
• On real footage of a lab pendulum (Jefferson Lab), Ghostline called a 7.6° swing inconclusive, committed predictions for 25°, and the nonlinear law won with a 0.2% period error. The linear law missed by 1.3%.
• On real iPhone footage of a mouse swinging on its cable, it correctly reported that none of the candidate laws fit, because the mouse twists as it swings.
• On 15 synthetic clips run through SAM 3.1, every check came out right, with no false INVALIDs.

## More from Meta Global AI Developer Hackathon

- [Team Decrypton](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4278)
- [Explanimate](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4279)
- [Sonor](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4280)
- [Controls Bench Muse](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4282)
- [NeuroGO](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4283)
- [CasaOS - Meta Muse Agents for Rural Homes](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4284)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/4281. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt