Hacker News Reader

We can compare algorithms by their accuracy. Here is a benchmark: https://github.com/open-spaced-repetition/fsrs-benchmark

Yeah that's fine, but I meant peer-reviewed neuroscience.

I found some analysis of the confidence intervals on this data that showed the results are not meaningful for ranking as they have shown

It would be nice if you could report this on Github. You can do it here: https://github.com/open-spaced-repetition/fsrs4anki/issues/n...

I've shared it here in the original ticket that added the benchmark confidence intervals https://github.com/open-spaced-repetition/fsrs-benchmark/iss...