Anastassia Loukina

We might consider changing `update_files.py` to separate new files and updated files and print those statistics as two different lists.

(1) RMSE between all sets of scores (2) Correlations between all sets of scores (3) Scatter plots between all pairs of scores

It would be good to show a summary table for subgroup analyses: mean/std/min/max for different performance measures across all subgroups.