Decifact

Cross-System Decision Comparability

Two systems can both pass audit. That doesn't mean their decisions can be reconciled.

Decifact checks whether two independently governed decisions were ever on the same basis to begin with — before anything depends on it.

Read the Quickstart → Explore Decifact →

Both hospitals followed their own governance process. Here's what happens when their decisions need to work together:

Hospital A

UK-AI-Framework-v1
"deploy_ai_triage approved"
FORMALLY_INCOMPARABLE
comparability result

Hospital B

UAE-AI-Framework-v2026
"deploy_ai_triage approved"

The hospitals are not necessarily disagreeing.

Under the current Phase 1 implementation, Decifact checks whether the compared records share the governance reference used as the comparison-basis proxy.

If that proxy does not match, the result is FORMALLY_INCOMPARABLE.

Scenarios

When valid is not enough

Hospital Triage

Hospital A (UK framework) and Hospital B (UAE framework) both approve AI-assisted triage. Same intent. Different governance foundations. Are they comparable?

Cross-Ministry

Agriculture Ministry and Finance Ministry both approve the same AI system. Each approval is internally valid. Can they be placed on the same comparison basis?

Multi-Agent

Agent A produces: BUY NVDA
Agent B produces: SELL NVDA
Both operating under valid policies. Is this a disagreement — or an incomparability?

Classifications

Three outcomes

EQUIVALENT

A comparison basis is detected under the current implementation, and the compared governance conditions are equivalent within the declared scope.

NON_EQUIVALENT

A comparison basis is detected under the current implementation, but the compared governance conditions or determinations differ within the declared scope.

This is a genuine difference, not merely a missing basis.

FORMALLY_INCOMPARABLE

No shared comparison basis detected under the current Phase 1 policy_reference-equality proxy.

Not a disagreement. A structural finding — not proof that no broader comparison or translation mechanism could establish one.

FORMALLY_INCOMPARABLE is not an error. It is a first-class governance result.

Decifact

Decifact does not govern either system.

Comparability

Before comparison

A comparison candidate must first be sufficiently constituted and reconstructable. Decifact treats this as a pre-comparability readiness boundary.

This readiness stage is specification-only and is not yet enforced by the current Phase 1 implementation.

A judgment held before comparison has not yet received one of Decifact's three comparison outcomes.

What comparability cannot determine.

  • Whether either decision is correct — two decisions can be comparable and both wrong
  • Whether a system's behavior conforms to its own declarations — that's a claim-vs-conduct question, not a claim-vs-claim question
  • Whether the governing definitions, evidence thresholds, authority conditions, or relevant time state remain current after the comparison was performed
  • Whether a decision or its governance conditions can be independently reconstructed later
  • Whether a decision should be executed — a decision can be comparable and still be inadmissible

Start here

QUICKSTART.md — understand and run Decifact in 5 minutes
Playground — view source, run locally with FastAPI
Requires local API server. See QUICKSTART.
API Reference — /compare /canonicalize /verify-equivalence
Governance equivalence vs cross-system decision comparability
Research on governance comparability and comparison basis

Working on cross-system decisions?

Building multi-agent systems, cross-domain governance, or decision verification infrastructure?

If what you saw on this page maps to a problem you're working on — let's talk.

xsa52000@gmail.com