jargon

Applied AI·Evaluation and reliability

someone had to sit down and write the correct answers for two hundred cases, and without that your scoring is vibes.

Ground truth / labels

Also calledlabels

Draft summary, pending review

The known-correct answers your scoring compares against, produced by humans or a trusted process. Expensive to create, and worth it: unlabelled 'vibes' evaluation does not survive contact with a regression.