Rhys Goodall

More generally since most methods rely on sampling rather than predicting the moments of a Gaussian distribution it may be helpful to add a calibration based on the empirical distribution...

 Thanks, I have been looking it it myself and I just can't see how to actually extract the re-calibrated uncertainties for the Kuleshov et al approach as we can...

 For completeness of this issue here is a revised version of the plot where the miscalibration areas in the calibration plot rows are for a test set and the...

I have just looked around the and I think that function simply identifies a scalar for scaling the uncertainty by to improve calibration based on the chosen metric. https://github.com/uncertainty-toolbox/uncertainty-toolbox/blob/946433b2bca9eb93b06b144cffdb32faf0a9c64f/uncertainty_toolbox/recalibration.py#L215-L216 I...

@YoungseogChung any updates on inverting the uncertainty scaling with isotonic regression?

This is just that there is no provided radius in the data source, https://github.com/materialsproject/pymatgen/blob/master/pymatgen/core/periodic_table.json e.g. for He ```json "He":{ "Atomic mass":4.002602, "Atomic no":2, "Atomic orbitals":{ "1s":-0.570425 }, "Atomic radius":"no data",...

Would also be nice to be able to pass in additional information for the hover labels i.e. a DOI for the entry etc

Additionally if using `PDEntry` `entry_id = getattr(entry, "entry_id", "no ID")` doesn't grab the name as `PDEntry` calls the identifier `name`

@janosh does the stuff you were doing with groups for the frontier plot offer any nice solutions for highlighting here?

I am keen in order to help make it as easy as possible to use roost and [model name were working on] going forward as this is the last year...