In force
Verification Policy
How Orbis Signal enforces source traceability, epistemic discipline, and quality controls before publication — through pipeline architecture, not a human fact-check desk.
This policy binds how claims are verified before publication: source traceability, evidence locking, cross-stage validation, the quality scorecard, and what we do not verify.
This binds
No traditional fact-check desk. Traceability, a locked evidence record, and a fail-closed quality gate.
This does not replace
- Sources & Attribution — Tier definitions and how sources appear in briefings
- Corrections Policy — How to report a factual error after publication
- Methodology — The illustrated production path
Orbis Signal does not operate a traditional human fact-checking desk or subscribe to third-party fact-check APIs.
Every claim in a published briefing must trace back to a locked evidence record. Downstream stages cannot access the open web or introduce new source URLs.
Confirmed claims require at least one tier-1 source. Tier-3 sources alone cannot support confirmed or inference-level judgments.
Every dimension of the eight-dimension quality scorecard must meet a defined minimum. Failures that still fail after one revision are not published.
Verification confirms traceability and editorial discipline, not absolute truth. We do not independently re-report events or contact primary sources for confirmation.
1. Our verification approach
Orbis Signal does not operate a traditional human fact-checking desk or subscribe to third-party fact-checking APIs. Instead, we enforce verification through a structured production pipeline built around source traceability, epistemic labelling, continuity discipline, and automated quality controls.
Every claim in a published briefing must trace back to a locked evidence record created during web-grounded research. Downstream analytical and writing stages cannot access the open web and cannot introduce new source URLs. This architectural boundary is our primary integrity mechanism.
2. The evidence record
Before any analytical assessment or briefing draft is produced, research stages collect atomic claims and tier-labelled sources from live web search. These are consolidated into a single evidence record per topic that is locked for the remainder of the pipeline.
Each evidence record contains:
- Claims — discrete, verifiable statements with unique identifiers
- Sources — HTTPS URLs with publisher, title, and tier classification
- Selected signals — the developments chosen for the edition
No analytical judgment or published sentence may reference a source URL that is not present in this record. This rule is enforced in code, not merely by instruction.
3. Cross-stage validation
After each analytical stage, automated validators check structural integrity:
- Every key judgment must cite valid claim identifiers from the evidence record
- Every source URL in the briefing must exist in the evidence record — invented or hallucinated URLs are rejected
- Confirmed claims must be supported by at least one tier-1 (primary) source
- Tier-3 sources alone cannot support confirmed or inference-level judgments
- Epistemic types and confidence bands must be present on key judgments
4. Quality control scorecard
Before publication, each briefing passes structural rule checks and an eight-dimension quality scorecard. Every dimension must meet a defined minimum standard. Briefings that fail may be revised once under correction guidance; those that still fail are not published.
The eight dimensions are:
- Clarity — structural hierarchy and unambiguous references
- Novelty — non-obvious insights and a non-trivial consensus gap
- Reliability — source quality and claim integrity
- Signal — strategic density and actionable watchlist items
- Strategic utility — decision relevance for a business professional at work
- Compression — brevity without loss of nuance
- Distinction — epistemic discipline and calibrated language
- Continuity — for recurring storylines, update-style framing that leads with what changed rather than restating prior baseline coverage
5. What we do not verify
Our verification model confirms traceability and editorial discipline, not absolute truth. We do not independently re-report events, contact primary sources for confirmation, or adjudicate disputed facts beyond what available evidence supports.
We rely on the quality of publicly available reporting and official releases. When sources conflict or evidence is thin, we label uncertainty explicitly rather than presenting contested claims as confirmed.
Readers who identify factual errors should follow our Corrections Policy.
6. Production audit trail
Each production run records stage outputs, quality scores, provider attempts, and the editorial policy version in force. This audit trail supports post-publication review and correction workflows, even though production itself is fully automated.
Related: Sources & Attribution, AI Usage Disclosure.