summary-faithfulness

Criteria

key	type	primitive	tier
`no_new_facts`	must_not	llm_judge@1	2
`covers_key_points`	scored	llm_judge@1	2
`no_editorializing`	must_not	llm_judge@1	1

summary-faithfulness

**Judges:** whether a summary is faithful to its source — no invented facts/numbers/causality, the key points preserved, no editorial opinion added. Source text travels as references. **Use when:** you generate summaries whose readers won't check the source (exec digests, meeting notes, news briefs, legal/medical abstracts).

curl -s -X POST $API/v1/rubrics -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d @templates/summary-faithfulness/rubric.json
curl -s -X POST $API/v1/verify -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"rubric_id":"<id>","submission":{"inline":"<the summary>"},"options":{"wait_ms":45000}}'

MCP: `verify_submit` with the summary as `submission.inline` and the source document as a reference.