{
 "id": "https://redfinchadvisory.com/lexicon/verified-test-set",
 "slug": "verified-test-set",
 "prefLabel": "Verified test set",
 "altLabel": [
  "Golden Dataset"
 ],
 "hiddenLabel": [],
 "definition": "A set of test cases that have had correct answers verified by a subject-matter expert.",
 "scopeNote": "When used for evals: cases should reflect your company's real work; synthetic cases are fine when real data can't be used (common in healthcare, e.g. synthetic patient or customer records), as long as they are representative. The expert sign-off is non-negotiable: the expert owns the answer key and ideally stays involved in reviewing how evals score against it.",
 "tier": "explain",
 "group": "Evaluation",
 "broader": [
  "https://redfinchadvisory.com/lexicon/eval"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/benchmark",
   "type": "confused"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/regression-eval",
   "type": "related"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/eval",
   "label": "used by",
   "direction": "out"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/verified-test-set.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}