Run the pipeline
Lint a paper.
Upload a PDF or give an arXiv id. The file goes through the real compiler and the real rules — the same code path the command line uses. Compiling takes a couple of minutes because a model reads the paper once; you will see which stage is running rather than a spinner.
While you wait
These reports are already stored. They came out of the same pipeline, run over papers in our corpus — open one and read the evidence.