OnScripthttps://onscript.news/corrections/feed.xml2026-07-28T00:00:00Zhttps://onscript.news/corrections/corr-2026-07-28-fingerprint-method-attestation.html2026-07-28T00:00:00Z

The published instrument fingerprint misdescribed the live measurement instrument. Its method-version registry attested document-families-v1 and surface-eligibility-v2 while the running modules were at document-families-v2 and surface-eligibility-v3, and its schema-version registry attested corrections schema 2 while the running schema was 3. The registry held hand-copied version strings rather than reading them from the owning modules, so it went stale when later work advanced those modules. The fingerprint also keyed code identity on the repository commit, which data commits move, so one measurement could carry a different identity on its day record than on its post manifest. The 2026-07-25 day record and post manifest are the committed instances. Every number and every citation on those surfaces was correct. The defect was in how the instrument described itself, not in any measurement.

https://onscript.news/corrections/corr-2026-07-23-composite-claim-binding.html2026-07-23T00:00:00Z

Some daily composite claims attached the size of a transitively connected topic cluster to a verbatim phrase carried by only part of that cluster, while the three displayed receipts could support a different phrase from the same cluster. The composite quote appeared in all three receipts in 2 of 38 stored blocks and in none of them in 14 of 38. The rendered label was absent from at least one receipt in 28 of 63 blocks. The two complete misses were the Democratic block on 2026-07-15 and the Republican block on 2026-07-22. The same code and the same correction apply to both parties.

https://onscript.news/corrections/corr-2026-07-21-private-person-window.html2026-07-21T00:00:00Z

A phrase containing the name of a private individual — a person named in members' statements about a fatal law-enforcement incident — appeared in the synchronized-phrase table on that day's page, on the phrases index, and on the home page. OnScript measures elected officials' public statements and does not rank or page private citizens, regardless of how newsworthy the underlying event is. A different name-window form of the same name was already withheld, but the suppression list did not carry every window an n-gram can slide across, so this form was not matched. Every citation involved was valid and every number was correct — the citation verifier has no opinion about privacy, by construction, so no receipts audit could have caught this.

https://onscript.news/corrections/corr-2026-07-20-missing-published-days.html2026-07-20T00:00:00Z

The composite Daily Lines and talking points for two already-published days went MISSING from this site. The daily collection run rewrites the day record it is working on, and when it landed on a day that had already been published it overwrote that day's composite half with nothing — deleting the two party composites, their talking points, and the day's cross-party phrase pairings. Nothing published was WRONG: no number changed, no citation broke, and the underlying record of what members actually said was never touched. Content that had been published simply stopped being there, and one day's page went on displaying composites whose backing data had been removed. Because every surviving number stayed correct, no receipts audit or citation check could have surfaced this — it is an absence, and the verifier has no opinion about absence. It was found by the pre-launch health review, before this site had an audience.

https://onscript.news/corrections/corr-2026-07-18-connective-clusters.html2026-07-18T00:00:00Z

Some daily talking points were bound by a connective or attribution phrase rather than a message — e.g. “into the trump administration’s” or “democratic colleagues in demanding the”. Each such key is string-valid (every cited statement contains it verbatim, which is why they clustered) and cleared the >=3 quorum, but the shared span is grammar, not a shared message, so the receipts pointed at unrelated topics. The citation verifier checks verbatim-ness, quorum and attribution — not whether the shared span is a message — so no receipts audit could have caught it. Flagged talking points: 19 across 7 day(s), categorized by reason (18 incomplete syntactic span, 1 attribution frame), both parties (15 D / 4 R — the gate is party-blind; the skew tracks the caucus).

https://onscript.news/corrections/corr-2026-07-16-private-person-phrases.html2026-07-16T00:00:00Z

Phrases containing the names of private individuals appeared in the synchronized-phrase table, in per-phrase adoption-curve pages, in the receipts of one talking point, and in the Democratic composite for this day (and in table rows on 2026-07-09). OnScript measures elected officials' public statements and does not rank, page, quote or narrate private citizens. Every citation involved was valid and every number was correct — the citation verifier has no opinion about privacy, by construction, so no receipts audit could have caught this.