Unverified50% confidenceFactExact time
If the power-law exponent fitted from small-scale experiments is consistent with that at large scale, this indicates the law has scale invariance and small-scale conclusions can be extrapolated; if the exponent drifts with scale, extrapolation fails.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe researchers transfer the population-level conclusions to finite corpora by controlling the gradient error so that it remains manageable relative to the shrinking progress directions along the scale of each parameter75% similarUnverifiedThe Monte Carlo method has dimension-independence, with its error governed only by sample size and unaffected by dimensionality, whereas the computational cost of deterministic methods grows exponentially with dimensionality.72% similarUnverifiedFor the unconstrained hypothesis class, the relationship between the prediction error of MLIPs and sampling accuracy is exponentially ill-posed in terms of dimensionality: even if the prediction errors of energy and forces decay exponentially with dimensionality, the total variation distance between the learned distribution and the target distribution may still approach its maximum value.72% similarUnverifiedThis Born rule replacement experiment lacks benchmark comparisons with standard attention—under the same parameter count and dataset—on convergence speed, accuracy, and stability in large-scale scenarios.72% similarUnverifiedIn this error bound, the exponent governing the convergence rate is determined by the intrinsic dimension of the data (the Wasserstein-p dimension), rather than the ambient dimension.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133873API
curl https://kongchang.com/api/v1/knowledge/claims/1133873MCP
get_claim(id=1133873)