Every claim keeps its page. What was refused is shown beside what passed.
Where report series stop. A gap in the catalogue is not proof that reporting did.
These title-derived gaps are checked against broader collection activity to test for a collection-wide scanning cutoff; each individual cause remains unknown.
Motions and roll calls, found by pattern rather than by model.
A title-keyword census found roughly 13,600 minutes, agendas, hansard and commission-hearing items. The civic parser is promising, but it does not yet have the measurement path's hand-read benchmark. Such records are cheap to read: "It was moved by X and seconded by Y that Z. CARRIED." is a form that has barely changed in a century, so a pattern finds it. No model, no GPU, and a person can check it.
The control is the clerk's own tally. That "-16." at the end of a roll was written by someone in the room; if the names don't add up to it, the roll was misread and it says so rather than publishing a division quietly missing two people.
Two readings that both cite a page and still disagree. Nobody decides between them; both stay up.
Prose uses sentence evidence; experimental table records retain cell locators but abstain without localized cell proof. The evidence check establishes what the cited page says, not which interpretation is correct.
Flagging one tells us people think it is wrong. It does not change the record: an objection with no evidence cannot outrank a sentence on a page, because then somebody would have to judge the objection. To change what is shown, bring a page and a sentence.
Cite a page, quote a sentence. Nobody reviews it — the archive is asked whether that sentence is on that page, and whether your number is in it.
Unread documents, ranked by what reading them would make answerable. The same order appears in the reader's pick list.
Eleven million pages cannot be read alphabetically, and reading by subject only serves whoever picked the subject. A question one document away is a question somebody already wanted.
It is also the honest replacement for a progress bar. "You processed 40 documents" is a fact about you. "You made the Grand River answerable, and it had been waiting on one town since 1961" is a fact about the world.
Plants down each river, in the order the water reaches them.
Each plant is tied to the nearest river gauge, then ordered by catchment area, which necessarily grows downstream. The towns sort themselves without any flow routing.
Measured against pages a person read by hand. Failures included.
An archive misread at scale is worse than one never read, because the errors look like findings.
Answers only from the record. Every number carries its page.
It cannot answer from memory, and it will not describe a title-series gap without the collection-wide control and its limits.