Concept detail
classifier evaluation practice (precision/recall on labeled data)
0 tagged videos · 1 connection videos · degree 0
Publication timeline
- 2026-101 video
Source videos
Observed neighbors
LLM-as-a-judge validation against a golden dataset
Judges are classifiers with a semantic label space, so standard supervised-evaluation discipline transfers directly — including the need for per-class agreement and awareness of degenerate constant predictors.
1 source videos
How to Know If Your AI Agent Is Any Good: Evals With Phoenix & Claude — Laurie Voss, Arize AIRelated tagged insights
No core insights are tagged with this concept.