Launched this week
DeepInquiry
A fact API that groups sources before counting
1 follower
A fact API that groups sources before counting
1 follower
Facts by API. Sources are grouped by website and mapped parent company before counting; Wikipedia mirrors and aggregators are set aside when other kinds exist. Each fact has its sources, a gold/silver/bronze tier and a signature you can verify.
Hi Product Hunt.
DeepInquiry started from a simple problem: "verified by two sources" usually is not. Two outlets running the same wire story, or quoting the same Wikipedia edit, are one source counted twice.
So every fact here is graded on how many separate source groups stand behind it. Sources are grouped by website and mapped parent company, Wikipedia mirrors and aggregators are set aside when other kinds exist, and what remains is scored. Each fact comes back with its sources, a tier, a 0-1 score and a signature, so an app or an AI model can cite it and anyone can check it.
What this does not do: our grouping separates different websites, and different parent companies for the websites we have mapped; every other site counts as its own owner. It does not detect wire reprints or copied wording, and it does not reliably detect several outlets reporting one study or announcement. The score is coarse: a high value does not mean the evidence is independent. We did not test whether the claims are true.
Today there are 2,827 facts, with 1,118 candidate claims turned away. The free plan covers 500 requests a month with no card.
I would value feedback on two things: which facts you think are wrong, and what you would build with this.