Hilde Weerts

I 100% agree with referring to anybody as people/person in any case. My two cents re. female/women: as far as I know male/female/intersex person is used when we talk about...

Awesome @Michael-AI-ML! Please let us know if you have any questions!

Hi @yanhong-zhao-ef - I'm so sorry for the late response! Would you still be willing to pick up this issue? That would be amazing! Do note that larger issues like...

I am generally not opposed to Step 1 (although I don't really see the need for changing `metric` into `metrics`). When we get to Step 2 things get a bit...

> It may be that there is a more general API hiding within, and that we end up changing MetricFrame to wrap (or subclass) that. But I think it would...

The reasoning behind `shared_sample_params` is a bit unclear to me still. It seems like a pretty niche situation but I might be missing something? It seems to me that generally...

Thanks a lot for these examples - this makes things a lot clearer for me! Given these examples, I find Alternative A pretty intuitive. If I understand correctly, the most...

All the datasets in our dataset module rely on OpenML, so if we would want to incorporate them in Fairlearn the first step would be to publish (the versions of...

I like the suggested outline! It seems quite comprehensive and I think the order makes a lot of sense. I am not sure whether I fully understand what you mean...

We should probably delete the subsection "Fairness assessment and unfairness mitigation" in "Fairness in Machine Learning" or put a more concise version right under "Typers of Harm" and then crosslink...