Unverified50% confidenceFactExact time
The paper points out that in OpenAI's Navier-Stokes proof, equation 8.19 claims that a certain quantity can be bounded by the norm of the (m+4)-th order derivative, but the Lean code verifies that it is bounded by the norm of the (m+5)-th order derivative, which is a weaker conclusion.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
VerifiedNumerical gradient checking approximates gradients using the central difference formula (f(θ+ε) - f(θ-ε)) / (2ε) and compares them with analytical gradients; a relative error below 1e-5 is considered correct, while an error above 1e-3 almost certainly indicates a bug.58% similarUnverifiedThe paper proves that for the Matérn-ν kernel with parameter ν∈(0,2), the γ-exponential kernel with parameter γ∈(0,2), and certain piecewise polynomial kernels, the minimax optimal rate is precisely determined to be Θ(√(Tγ_T)), with upper and lower bounds matching within constant factors.57% similarUnverifiedThe new sample complexity bound matches the known lower bound in its exponential dependence on |β|/(1-γ).57% similarUnverifiedThe paper validates on Qwen2.5-Math-7B-Base across nine mathematical and out-of-distribution benchmarks.57% similarUnverifiedThe same model's scores on DeepCWE range from 65.5 to 74.2 depending on the agent framework used; the official harness uses the upper end of the range, while under Claude Code's harness the score is only 69.8.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995683API
curl https://kongchang.com/api/v1/knowledge/claims/995683MCP
get_claim(id=995683)