diff --git a/paper/img/sl_compas__all.png b/paper/img/sl_compas_all.png
similarity index 100%
rename from paper/img/sl_compas__all.png
rename to paper/img/sl_compas_all.png
diff --git a/paper/imputation.tex b/paper/imputation.tex
index 641e8d4a1464092ef1304664ca32abb33fd293f9..cad6d550fac7e829515f921a17ed93084a3a8278 100644
--- a/paper/imputation.tex
+++ b/paper/imputation.tex
@@ -208,7 +208,7 @@ In particular, we consider the full probabilistic model defined in Equations \re
 % 
 %Notice that by ``parameters'' here we refer to all quantities that are not considered as known with certainty from the input, and so parameters include unobserved features \unobservable.
 %
-We use prior distributions given in Appendix~X�to ensure the identifiability of the parameters.
+We use prior distributions given in Appendix~X to ensure the identifiability of the parameters.
 %Formally, we obtain the parameter posterior by
 %\begin{equation}
 %	\prob{\parameters | \dataset} = \frac{\prob{\dataset | \parameters} \prob{\parameters}}{\prob{\dataset}} .
diff --git a/paper/sl.tex b/paper/sl.tex
index b3e7bb8a1280ca8007fa2da2b2e1e8203e12964c..50c2f51f87469f4c0fcb68ba5d47c74733a9828f 100755
--- a/paper/sl.tex
+++ b/paper/sl.tex
@@ -101,8 +101,7 @@ The approach is also demonstrated to be robust to different variations in the de
 
 \input{imputation}
 
-%\input{experiments} 
-%Antti: took out to compile, a figure is missing
+\input{experiments} 
 
 \input{related}