That's awesome! We're just putting publicly available information (abstracts aggregated by the nonprofit Semantic Scholar) through a smarter and better search process, so there's no issues with Google. And we absolutely encourage sharing, people post our search reports and send them to colleagues all the time, so please go ahead on that front.
Appreciate the comments. One thing to note: how much compute it takes to "get everything" varies from search to search, and researchers don't always care about that and usually care most about getting a few specifically relevant results, so we start each search with a first pass with a fixed amount of compute. I know there's a lot to absorb on each search page, but if look near the bottom of the summary, Undermind is predicting is has only found about 80% of the papers with the compute dedicated to this search so far. Logged in users on Pro accounts can "extend" the search until it's gotten 90% or more to ensure exhaustiveness. One other thing I'd be curious about is your notion of "importance" here, can you help us define that here? Any ideas for how would say a very smart human assistant who's not intimately familiar with your community's interests be able to pick out paper 7 from the list according to what you mean by importance? Maybe we need a way to communicate to the system that you're interested in pedagogical or seminal works in the field?
Not OP and I don't know if that would be feasible for you, but a Pro feature could be something like https://asreview.nl to determine importance/relevance?
Yes, this is one of the most important aspects of the tool; in cases where you care about getting everything, make sure to take a look at the estimated percent of papers found at the bottom of the summary section. That gives you a sense of how complete the set of references likely are. We've tuned it to get around half of the total papers for the "median" user query on a first pass. If users desire, they can "extend" the search to have Undermind look for more papers. Additional caveat to remember with the current system is that it only accesses abstracts, so if you'd need to look in the full text to know a work is relevant, we wouldn't be able to catch it.
Thanks for clarifying. I didn't appreciate that it only searches abstracts. That might explain some of the missing references. Anyway, great work, will look forward to using it more.
Yep, will add in full texts as we can in the future. Let me know if the percent of papers found as an indication of an exhaustiveness measure was clear? Reach out to us at support@undermind.ai if you'd be willing to provide more feedback on your experience.
We'll certainly be able to include open access full texts, which is already a substantial fraction of the published papers, and a growing fraction too, as the publishing industry is rapidly moving toward open access. Paywalled full text search would require working with the publishers, which is more involved.
Great! I can definitely ask undermind for an overview paper of the scientific information landscape, unless you have a favourite in quick access to share?
We've thought quite a bit about usage-based pricing, but found that doesn't work psychologically for most people. Generally, people seem happier by paying up front for access, then feel good about having the system available whenever they need it, rather then having to think through cost tradeoffs every time they want to do a search or use up credits. Please do reach out at support@undermind.ai though, we'd love to talk about a solution for you and get your feedback.
