Correspondence Prover
Every change tested against evidence it has never seen.
In one paragraph
The Correspondence Prover is the first of two gates every CRIS system change must pass. It runs the current version and the proposed one side by side on evidence the system has never seen, and checks, area by area, that the new version matches the real world at least as well as the old. The result is a correspondence proof: not a mathematical certainty, but a signed, measurable demonstration that anyone with access can check and re-run.
It carries ↔, correspondence, the second operator of the Fourth Law: "the relation that must hold between what is observed and what is reasoned". In practice it is the system that stands between a proposed change and the world.
Where it sits
The Prover carries the second stage of the loop, Verify. In the CRL Engine's Workflow A it is Gate 1, at step 3, before the C-Gate.
A more continuous tomorrow.
Observe
Observe the world as it is, and record where each observation came from.
Verify
Verify every observation, and every change a system makes to itself, against evidence it has not seen.
Reason
Reason only from what has been verified, in steps someone else can trace.
Accumulate
Accumulate what was verified, so knowledge adds up instead of being overwritten.
Benefit
Benefit people and the environment: participants share in the value they create, and every change is weighed against our public benefit purpose.
Continue
Continue, changing anything except correspondence with reality and continuity of purpose.
- 1Propose a changeReasoning Core · Iᵢ
- 2Gather fresh evidenceObservation Mesh · Eᵢ
- Gate 1Proof passes?Correspondence Prover · ↔No → reject and record
- 4Record in ledgerKnowledge Ledger · Σ
- Gate 2C-Gate passes?Purpose and benefit · CNo → reject and record
- 6Staged rolloutSandbox, testnet, then partners
- 7Promote successorWith a rehearsed rollback path
Rules for this system are proposed in the AI Constitution, Articles 4 and 5: the correspondence requirement and evidence. They are approved by the Board for implementation.
What a proof is
A proof takes the current version of a system, the candidate that would replace it, and evidence the system has never seen, and shows, domain by domain, whether the candidate matches reality at least as well. It is a record that can be checked, not a claim to be trusted.
Inputs
Output · proof object
- Candidate
- The proposed version
- Baseline
- The live version
- Evidence set
- Which held-out evidence was used
- Domains
- The result in each domain
- Contradictions
- Every disagreement, with sources
- Verdict
- Pass, staged or fail
- Conditions
- Limits and monitoring, if staged
- Signed
- The Prover’s key and the time
| Part of the proof | What it records |
|---|---|
| Candidate and baseline | Which version is proposed and which is live |
| Evidence set | Which held-out evidence from the vault was used |
| Domains | The result in each domain the change could affect |
| Contradictions | Every place where model and evidence disagree, with sources |
| Verdict | Pass, staged or fail |
| Conditions | For a staged verdict, the limits and monitoring required |
| Signature | The Prover's key and time, so tampering is detectable |
Whatever the verdict, the proof is written to the Knowledge Ledger. A failed proof is not wasted: the book calls rejected upgrades "knowledge", because they teach the next cycle what not to do.
How it works
Every proof follows five steps. Both versions face exactly the same evidence, so the comparison is fair.
- 1SelectThe domains the change could affect
- 2Run bothCandidate and current on the same held-out evidence
- 3CompareDomain by domain; a loss fails
- 4DetectList every contradiction
- 5SignIssue the proof to the ledger
- Select the evaluation domains the change could affect.
- Run both the candidate and the current version on the same held-out evidence.
- Compare correspondence domain by domain; a loss in any domain fails the proof unless a board-approved tolerance allows a staged trial.
- Detect contradictions and list every conflict between model output and evidence.
- Sign the proof and issue it to the Knowledge Ledger.
Held-out evidence
The Prover is the only system allowed to read the held-out vault kept by the Observation Mesh. The system under test never sees it. This is what makes the promise on this page true: every change is tested against evidence it has never seen.
Domain by domain
A new version cannot buy a loss in one area with gains in others. If it is less faithful anywhere, it does not pass, however much it improves elsewhere. The chart below is an illustration of the rule, not a real result.
This rule protects against the slow, hidden drift the book calls correspondence drift, the first of the four ruptures. The Prover is its guard.
Read about correspondence drift on the ruptures page.
Contradictions
When a system's model and the evidence disagree, the Prover does not average the disagreement away. It lists each contradiction with its sources, so the system can learn from it and the people responsible can see it.
Chapter 4.2 of the book calls contradiction "a signal, not a failure": a disagreement between model and world is how a system learns. The Prover surfaces each one, the Reasoning Core treats it as a hypothesis to fix, the Observation Mesh adjusts the trust of the sources involved, and the Knowledge Ledger keeps the record.
Verdicts
Every proof ends in one of three verdicts. Pass: the change goes on to the C-Gate. Staged: a small loss within a margin our board has approved allows a limited, monitored trial. Fail: the change is not used, and the failure is recorded so the next attempt can learn from it.
The candidate goes on to the C-Gate (Gate 2).
A limited, monitored trial with conditions; proved again before promotion.
Not promoted; recorded as knowledge; sent back with the contradictions.
| Verdict | Condition | Next step |
|---|---|---|
| Pass | At least as faithful in every domain | Candidate goes to the C-Gate |
| Staged | A small loss within a tolerance the board has approved | Limited, monitored trial; proved again before promotion |
| Fail | Less faithful in any domain, beyond tolerance | Not promoted; recorded; sent back with the contradictions |
For domains where evidence is uncertain, the Prover issues probabilistic proofs with a stated confidence (book Chapter 8.4). Tolerances and confidence thresholds are approved by the board, as part of governing the loop rather than each version. The Prover never sets them.
Two jobs and who checks it
The same method checks contributions on the Continuity Intelligence Exchange: each observation is compared with other evidence before it is accepted. And the Prover is checked in turn: every proof is signed, a sample is re-run independently by the Continuity Audit Suite, people review the proofs behind each release, and the method is assessed against an external standard.
- 1Signed proofsEvery proof is signed and stored, so tampering is detectable
- 2Independent re-runsThe Continuity Audit Suite re-runs a sample of proofs
- 3Human reviewThe C-Gate review board and the Audit Council read major proofs
- 4Third-party standardExternal assessment of the method
| Check | Who | How often |
|---|---|---|
| Signed proofs | The Prover, automatically | Every proof |
| Independent re-runs | Continuity Audit Suite | A sample of proofs, on schedule |
| Human review | C-Gate review board; Audit Council for major versions | Every release; major versions |
| Third-party standard | External assessor | Yearly, with the benefit report |
The Prover is the first of the five layers of assurance around every CRIS system.
- Automated checksProofs and drift tests
- Human reviewC-Gate board, every release
- Independent auditAudit Council, major versions
- External standardThird-party certification
- Public reportBenefit report, every year
Status and read more
This status is set by the CRIS team and links to the evidence behind it. The CRIS roadmap places the first CRL prototype, and with it the first real proofs, in 2027.
Current status: Status to be confirmed
| Level | Evidence required | Who sets it |
|---|---|---|
| Research | Concept page and draft proof format published | CEO |
| Prototype | Proofs issued for a test CRL cycle using held-out evidence; proofs stored in the ledger | CEO, on the Labs and Systems leads’ advice |
| Pilot | Proofs used in a partner deployment on testnet; Audit Suite re-runs a sample; Audit Council review | CEO |
| Live | Production use; external assessment of the method passed | CEO, with notice to the board |
For developers: the correspondence proof format, draft 0.1, and the Verify path.
- Recursion Without Rupture: Chapter 4.2 (contradiction as signal), Chapter 5.2 (↔, correspondence) and Chapter 8 (correspondence proofs and verified change).
- Correspondence proof format: draft 0.1, open for comment.
- Related systems: Observation Mesh, CRL Engine, C-Gate, Knowledge Ledger, CIX, Continuity Audit Suite.
