alastairr

I know there are a lot of tools out there for searching ArXiv for relevance, but given the volumes on ArXiv now, relevance is rarely enough.

Does anyone know or use any tools that use any types of impact / authority / quality metrics to filter out weak or derivative works that might otherwise have flooded a relevance-only search?

I've noticed this more and more recently, especially with Opus 4.6. Not super frequently, but enough that it stands out given how capable 4.6 is. Has anyone else seen this? Any theories as to what causes it?

I'm looking for any products for learning new topics and that are designed for helping users retain new knowledge - eg. with spaced repetition or smart use of follow-up questions.

I can almost get chatgpt to do this, and their voice mode is great for question / answer, but it's not really setup to understand / track what you know and what your learning objectives are.

Curious to find out any positive experiences of any new tools out there.