Every model call produces one answer. That answer exists in a single context, under a single corpus version, signed by a single key. Hive DELTA adds the fifth dimension: a cryptographic proof of what the inference would have produced under a different condition — and the signed delta between the two.
Inference has always had more axes than anyone used. D5 is not a feature — it is a reclassification of what a signed inference receipt can contain.
One prompt, one response. Linear. No memory of the space traversed.
UniversalCCACW — Compile, Compress, Amplify, Certify, Writeback. Staged transformation, still a single line.
Live · HiveECHO + MEMBRANE + QUORUM + ATTEST. Parallel primitives on the same input, different lenses on one moment.
Live · XCALIBURSMSH lineage chain. Inference aware of its signed history — prior receipts, prior corpus commits. T₂ is a function of T₁ and T₀.
Live · SMSHHAHS-Δ. Signed proof of what the inference would have produced under a different corpus, rule version, or identity context — and the delta between branches.
Preliminary · DELTAHAHS-Δ runs two inference branches from the same corpus root commitment. Each branch gets its own ML-DSA-65 signed receipt. The delta — the difference between branch A and branch B — is itself a signed artifact anchored to both parent receipts.
The actual inference. The answer under the committed corpus and current rule version. Ed25519 + ML-DSA-65 signed. HAHS envelope, cert_id anchored to chain.
The counterfactual. Same corpus root, different rule version. What would the model have said yesterday? ML-DSA-65 signed. counterfactual_ref points to Branch A cert_id.
A third artifact is produced: the signed delta between Branch A and Branch B. It carries both parent cert_ids, a SpectralZK proof that both branches diverged from the same corpus root, and the semantic divergence score. The delta is what the regulator, auditor, or CFO holds.
HAHS-Δ extends the existing HAHS receipt envelope. The canonical schema adds counterfactual_ref — all other fields are inherited unchanged. Every existing HAHS consumer is forward-compatible.
Fields shown in amber are new to HAHS-Δ. All other fields are inherited from HAHS v1 and are byte-compatible with existing verifiers. See HAHS canon spec.
Every vertical that runs regulated inference has a counterfactual question. HAHS-Δ is the first primitive that produces a signed answer to that question.
What would this contract clause produce under California law vs. Delaware law? Signed delta. Both branches admissible.
What would minimum weight be if the torque sensor reading were X instead of Y? The receipt shows the decision and its counterfactual. The dispute resolves at the verifier.
What would this policy decision produce under EU-AI Act v1 vs. v2? Signed delta for auditors. No spreadsheet. A receipt.
What would this agent payment route produce under rate regime A vs. B? Signed oracle delta for treasury ops and CFO sign-off.
What would the clinical decision support have recommended under the prior protocol version? Signed delta for incident review and HIPAA audit trails.
What would the structural compliance assessment produce under IBC 2021 vs. IBC 2024? Signed delta for permit submission and dispute resolution.
Produces one answer per call. Logs it. Maybe stores it. If you need to know what it would have said under different conditions, you run it again manually, with no cryptographic proof the two runs started from the same state. No signed artifact. No auditable delta.
Produces two signed branches from the same corpus root and a third artifact: the signed delta. SpectralZK proves both branches diverged from the same committed corpus without revealing its contents. ML-DSA-65 signs every artifact. The delta is court-admissible, regulator-readable, and CFO-holdable. Not a log. A receipt.
The HAHS-Δ schema is specified. The counterfactual_ref and semantic_divergence fields are defined and forward-compatible with the live HAHS v1 envelope. The ML-DSA-65 signing path (NIST FIPS-204) is live on hivemorph today and applies directly to HAHS-Δ receipts.
The SpectralZK delta proof — the cryptographic proof that two branches diverged from the same corpus root without revealing its contents — is the research frontier. It requires a ZK circuit over the Merkle commitment scheme used in HAHS-Δ. This is active development. It is not claimed as live. When it ships, it moves to Hive Verified with a published benchmark and Cohen’s d computed against a null baseline.
The semantic divergence score (semantic_divergence) is implementable today using the SMSH compression kernel as an embedding layer. The ZK proof that the score was computed correctly over the signed corpus is the hard part.