Erik Bernhardsson

Can this be rebased/merged? Happy to help in any form

What's going on here – can this be merged? Let me know if there's anything I can do. I'm tempted to fork this repo for now since this is holding...

Yes of course – would just be nice not to have to rely on our own custom verision

I think that would be interesting! I think the downside is 1. Would make it more complex 2. Not sure if there's any obvious public datasets for this?

> if an additional artificial, categorial random variable is introduced, allowing to filter to fractions of the original dataset between 0-100% I think that makes sense, but it would be...

You could sort of infer it by adding the index build time and the extrapolated query time for the full dataset. In a way I like this metric because it...

A bunch of algos will fail on every dataset unfortunately – I'd say 80-90%+ will succeed though. Like @maumueller said, in the case of Glove it might be because the...

Feel free to submit a pull request!

I recently ran a benchmark, and I wasn't able to get Jaccard working, so I think something is weird with it. If you know how to fix it, I'd love...

> I just ran puffinn on kosarak and that works fine. It's indeed the shared file that still uses the old format. Could you update it @erikbern by creating locally...