There seems to be some improvements in this area. Machine learning papers sometimes provide their data sets and other artifacts on websites like paperswithcode.com.
Have you ever contacted the authors to request their data? I personally have not.
That should continue to increase. Hopefully it will be academic misconduct to not release code - but also further, it should be misconduct for the code not to be able to reproduce the paper's output with a one line command.
chaxor|3 years ago