Inconsistent documentation for `k_threshold` in `loo_moment_match()`?

Apologies for opening two issues in a row. I think there may be a small inconsistency in the documentation for the k_threshold used by loo_moment_match() between the function documentation and moment matching vignette.

Function documentation:

loo/R/loo_moment_matching.R

Lines 28 to 30 in 6e7001e

    
           #' @param k_threshold Threshold value for Pareto k values above which the moment 
        
           #'   matching algorithm is used. The default value is `1 - 1 / log10(S)`, 
        
           #'   where `S` is the sample size.

Vignette:

loo/vignettes/loo2-moment-matching.Rmd

Lines 169 to 171 in 6e7001e

    
           determines the Pareto $k$ threshold, above which moment matching is used. By 
        
           default, it operates on all observations whose Pareto $k$ value is larger than 
        
           the sample size ($S$) specific threshold $\min(1 - 1 / \log_{10}(S), 0.7)$ (which is $0.7$ for $S>2200$).

Should the function documentation be updated to say that the default value is min(1 - 1 / log10(S), 0.7)?

Yes, thank you for pointing this out! The vignette is correct about the current default, so the function documentation needs to be updated.

	#' @param k_threshold Threshold value for Pareto k values above which the moment
	#' matching algorithm is used. The default value is `1 - 1 / log10(S)`,
	#' where `S` is the sample size.

	determines the Pareto $k$ threshold, above which moment matching is used. By
	default, it operates on all observations whose Pareto $k$ value is larger than
	the sample size ($S$) specific threshold $\min(1 - 1 / \log_{10}(S), 0.7)$ (which is $0.7$ for $S>2200$).