Johannes Buchner

Please reopen if this is still an issue after addressing the extremely large negative log-likelihood issue.

I guess it might be easiest to create corner plots of the live points, because the posterior will be ill defined (all probability in one point) for most of the...

This is addressed in master now.

That line of code figures out how many digits to print. It builds a format string, "%.3f", for example.

But yes, it is just for printing. Is it possible that your transform made some infinites? It looks like the values are getting extremely large (1e150).

Closing, please reopen if the issue still persists

At some point it makes sense to just use the sampler object directly instead of going through that compat layer.

Are you calling from BXA?

This is solved in the latest version of BXA, which allows full control of ultranest

I think this is solved.