cross-validate

# /cross-validate Format a physics or mathematics claim for cross-model validation. Use this when Claude has produced a result you want to check against a second AI model (Gemini, ChatGPT, or a fresh Claude context). Different models fail in different ways on the same physics, so agreement between models is meaningful evidence; disagreement tells you exactly where to look harder. Inspired by the "hallucination orthogonality" principle and council-mode verification in [flonat/claude-research](https://github.com/flonat/claude-research), and the physics-specific failure modes documented by Tim Andersen ([How to use Claude to do physics](https://timandersen.substack.com/p/how-to-use-claude-to-do-physics-and)). ## Usage ``` /cross-validate "the Gaussian integral sqrt(pi) follows from squaring and polar coordinates" /cross-validate (no argument — validate the last substantial result) ``` ## Steps **Step 1 — State the claim precisely.** Write the claim as a self-contained statement including: - The exact formula or result - All notation and conventions needed to read it (do not assume the other model shares your conventions) - The domain of validity or the specific input values Example: > Claim: The Gaussian integral I = ∫_{-∞}^{∞} e^{-x²} dx equals √π. > Check this by computing I² = ∫∫ e^{-(x²+y²)} dx dy in polar coordinates, > and confirm the radial integral gives π. **Step 2 — List the specific checkpoints.** Identify what a second model should verify. Focus on the kn...