# Signal-to-Noise

- **Event:** [Built with Opus 4.6: a Claude Code hackathon](https://cerebralvalley.ai/e/claude-code-hackathon)
- **When:** Feb 10 at 12:00 PM – Feb 17 at 10:00 AM (EST)
- **Where:** Location TBA
- **Team:** [Vicente Gonzalez](https://cerebralvalley.ai/u/vichudo)
- **GitHub:** https://github.com/vichudo/denoise-it
- **Demo video:** https://www.loom.com/share/89ff6479f1434a82a518b4587ad7f47d
- **Gallery:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/72

Denoise It is an AI engine that decomposes any content (tweet, headline, article, claim, or URL) into its objective truth vectors (verified facts, statistics, and attributions scored against      
 primary sources) and its affective noise (emotional language, bias, narrative framing, speculation, and missing context, each quoted and named), returning a structured, source-auditable and shareable decomposition where every claim has a receipt and every distortion has a label. Not a summary. Not a simple fact-check. A max(signal/noise) audit extraction.

---

Markdown version of https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/72. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt