How a record is made

Pipeline

1. 1. Observe

   The desk monitors public disclosures, incidents, policy changes, and Lab outputs.

2. 2. Extract

   Candidates become structured entities, events, and sources with schema fields and fingerprints.

3. 3. Verify

   Source tier, corroboration, and confidence are evaluated against public evidence only.

4. 4. Gate

   All ten checks must pass; otherwise the record is quarantined, never silently dropped.

5. 5. Publish

   Approved records promote into the public graph seed and ship with canonical URLs.

Ten-check publication gate

Every record must pass all ten checks before publication.

1. 1. Source exists and is public

   Every claim traces to a URL any reader can open without credentials.

2. 2. Source tier recorded

   Primary, secondary, or tertiary tier is assigned and stored with the record.

3. 3. Severity corroboration

   High- and critical-severity incidents require at least two independent public sources.

4. 4. Required schema fields

   ID, title, summary, canonical path, source refs, and confidence are all present.

5. 5. Confidence threshold

   Confidence score is at or above 0.6 before publication.

6. 6. Duplicate check

   Fingerprint matches an existing published record are blocked.

7. 7. PSF mapping

   Incidents, assessments, and policy changes include PSF domain mapping when relevant.

8. 8. No private data

   Customer, credential, or other non-public data is rejected at the gate.

9. 9. Canonical URL valid

   Title, metadata, and site-relative canonical path pass validation.

10. 10. Retraction path

    Every published record has a documented correction and retraction route.