deletions | additions       diff --git a/subsubsection_Position_based_metric_When__.tex b/subsubsection_Position_based_metric_When__.tex  index b5c9aa6..3820f8c 100644  --- a/subsubsection_Position_based_metric_When__.tex  +++ b/subsubsection_Position_based_metric_When__.tex 
...
During the first minutes of the play we get less clusters embedding more players (2 clusters with 6 players) which might be due, in part, to the disorganization of the team at the beginning.  Those results are encouraging. It seems MI-based metric with position is relevant for the cues about a match we were looking for adjusting accurately $C_{penalty}$. With this first tests it seems a correct value for $C_{penalty}$ should be such that $C_{penalty} \in \[1.3,1.5\]$ [1.3,1.5]$