We bootstrapped from the preprocessed data for 1000 times, and compute the distribution of the search-wise CTR. Then we changed the re-sample size from 1k to 10k, and then create the following joy plots for every wiki:

arwiki

dewiki

fawiki

fiwiki

frwiki

hewiki

idwiki

itwiki

jawiki

kowiki

nlwiki

nowiki

plwiki

ptwiki

ruwiki

svwiki

viwiki

zhwiki