Diurnal Bond · Nobody's awake to countersign the weekend · Patent Pending
Status

Cryptographic core built and proven. 37 of 37 smoke tests pass. Sign p50 ~6ms, verify p50 ~2.4ms, ML-DSA-65 signature 3,309 bytes constant. Filed July 26, 2026 as provisional patent, USPTO application 64/119,279. Real production integrations with on-call and paging systems are pilot-ready, not yet deployed.

The incident that compounded over a weekend had no one awake to say no.

Diurnal Bond™ binds consequential agent actions, inference under elevated risk, tool calls, egress, model swaps, and policy changes, during weekends, on-call windows, after-hours periods, or declared incidents, to k-of-n countersigning from geographically distributed human attestors. k is not a fixed number picked once and forgotten. It is computed dynamically from a signed risk manifold, so nobody can quietly lower the bar for a Saturday at 2am and nobody can prove after the fact that the bar was ever different.

Force multiple humans awake before the weekend action can commit.

What it is: a k-of-n countersigning requirement whose k is bound to a signed, tamper-evident risk manifold keyed by time regime and action class, so the required signer count for a Saturday model swap can't be secretly set to zero. What it is not: Diurnal Bond does not decide whether the action itself is safe. It decides how many humans, in how many places, have to be awake and agree before a risky action in a low-oversight window can proceed.
Honest status: read this first

The cryptographic core is built and proven: 37 of 37 smoke tests pass across all seven upstream primitives sharing the same signer and envelope. Diurnal Bond's regime declaration and countersigning receipts are ML-DSA-65 signed (NIST FIPS 204), constant 3,309-byte signatures. Real integrations with paging systems, on-call rotation tools, and geographically distributed attestor pools are pilot-ready but not yet deployed at a customer. We say so plainly. Nothing on this page claims a live weekend countersign happened outside our own test harness.

What's real today, and what's pilot-ready

These numbers come from the reference implementation and its test suite. The risk manifold logic, the k-of-n threshold computation, and the receipt signing are real and measured. Live integration with a customer's on-call rotation is the next step, and it hasn't happened yet.

37/37
smoke tests pass · all seven upstream primitives
~6ms
sign p50 · regime and attestation receipts
~2.4ms
verify p50 · offline, no network call
3309bytes
ML-DSA-65 signature · constant size, every receipt

Envelope format is USAP_VERSION='usap.v1', shared across all seven upstream primitives filed under the same provisional. Filed July 26, 2026. USPTO application 64/119,279.

The incident compounded over a weekend. Nobody was awake to countersign.

The OpenAI and Hugging Face incident did not happen in a single moment during business hours. It ran over a weekend, and 17,000 events accumulated before anyone with the authority to stop it was looking. That is not a monitoring failure. It is a structural one: nothing in the system required a second, awake, geographically separate human to agree before the risky action was allowed to repeat.

Business-hours assumptions leak everywhere

Approval chains, escalation policies, and on-call rotations are usually built for a five-day week. Weekend and after-hours windows quietly inherit weaker review, fewer eyes, and looser thresholds, and nothing makes that gap visible or provable.

17,000 events, zero countersigns

Across the weekend the agent repeated the same class of action thousands of times. No signed record exists anywhere that a second human, awake and independent, ever looked at the risk and agreed to let it continue. Read the incident analysis.

Diurnal Bond is the forcing function

Diurnal Bond ties the required countersign count k to the actual time regime and action class, via a signed risk manifold. A Saturday model swap requires more independent, awake signers than a Tuesday afternoon inference call, and that requirement can't be edited without leaving a signed trace.

Motivating incident: Hive incident analysis: OpenAI and Hugging Face, 17,000 events · Signature standard: NIST FIPS 204 (ML-DSA).

The mechanism: k is computed, not chosen

A fixed policy of "two approvers on weekends" can be quietly rewritten by whoever controls the config file. Diurnal Bond makes the required signer count k a function of a signed risk manifold, keyed by regime and action class, with the manifold's own digest bound into every regime-declaration receipt. Change the manifold, and the change itself is signed and dated. You cannot lower k for a specific Saturday without leaving a record that k was lowered.

RegimeExample action classWhat changesWhy it can't be gamed
business_hoursinferencek is typically low, sometimes 1Manifold digest still signed and bound, even when k=1
on_calltool_callk rises, attestor pool narrows to on-call rosterRoster membership is part of the signed attestor_kid_set
weekendegress, model_swapk rises further, attestors must be geographically distributedregion field on every attestation receipt, checked independently
after_hourspolicy_changek rises, validity_window shrinksAny attestation outside the window fails verification
incident_activeanyk rises to the manifold's ceilingDeclaring incident_active itself is a signed, auditable event
maintenancemodel_swapk set by the maintenance-specific row of the manifoldMaintenance windows are pre-declared, not self-declared mid-action
The money shot side-by-side, one screen
Why a static approval policy misses this
Static weekend approval policy
✓ policy document says "two approvers required"
✓ config file matches the document

LOOKS FINE ON PAPER

Diurnal Bond regime check
✗ risk_manifold_digest for this weekend does not match the last signed manifold
✗ required_k was silently lowered from 3 to 1 without a signed mutation

BROKEN: manifold edited without a trace, action proceeds under the wrong k

A static policy document can say anything. Only a signed risk manifold, checked against the countersigning receipts actually produced, tells you whether the required bar was really met, on that Saturday, for that action class.

The receipt schema

Two receipt types. diurnal.regime declares the time regime, the action class, and the dynamically computed k, with the risk manifold's digest bound in so it can't be edited invisibly. diurnal.attestation is the signed countersign itself, one per attestor, tied back to the regime declaration. Both are ML-DSA-65 signed under the shared usap.v1 envelope.

// diurnal.regime: declared before any action in a non-default window is allowed
{
  "usap_version": "usap.v1",
  "receipt_type": "diurnal.regime",
  "regime": "weekend",                     // business_hours | on_call | weekend | after_hours | maintenance | incident_active
  "action_class": "egress",                // inference | tool_call | egress | model_swap | policy_change
  "risk_manifold_digest": "sha256:9f2a...", ← binds the manifold, can't be edited invisibly
  "required_k": 3,
  "total_n": 7,
  "attestor_kid_set": ["kid:attestor-01","kid:attestor-04","kid:attestor-07", "..."],
  "validity_window": {
    "not_before": "2026-07-25T00:00:00Z",
    "not_after": "2026-07-27T08:00:00Z"
  },
  "signature": "ML-DSA-65, 3309 bytes"
}

// diurnal.attestation: one signed countersign per attestor, must reach required_k
{
  "usap_version": "usap.v1",
  "receipt_type": "diurnal.attestation",
  "regime_ref": "sha256:regime-receipt-digest...",
  "attestor_kid": "kid:attestor-04",
  "region": "us-west",
  "ts": "2026-07-25T14:32:09Z",
  "action_class": "egress",
  "signature": "ML-DSA-65, 3309 bytes"
}
The manifold digest is load-bearing

The risk manifold itself is signed and its digest lives inside every regime declaration. Edit the manifold to quietly lower k for a specific weekend, and the digest changes, which breaks the chain of trust against any prior regime declaration referencing the old manifold.

Attestors are geographically bound

The region field on every attestation is not decorative. Verification can require the k attestors to span a minimum number of distinct regions, so "three approvers" can't secretly mean three people in the same office who all went home at 6pm.

Fail-closed by default

If fewer than required_k valid attestations exist inside the validity_window, the action does not get to claim it was countersigned. There is no code path that lets an action proceed and backfill the missing signatures later.

Diurnal Bond does not evaluate whether the underlying action is a good idea. It evaluates whether enough of the right people, awake, in enough different places, actually agreed to it, and it makes that fact checkable offline by anyone holding the receipts and Hive's public key.

How the regime flow works, end to end

Diurnal Bond sits in front of any action classifier that already tags requests by action_class. It adds the regime lookup, the k computation, and the countersign collection, then emits signed receipts that a verifier can check without ever calling back to Hive.

The regime declaration flow
  • Determine the current time regime (business_hours, weekend, on_call, after_hours, maintenance, or incident_active).
  • Look up required_k and the eligible attestor_kid_set from the signed risk manifold for that regime and action_class.
  • Bind the manifold's own digest into the regime declaration so it cannot be substituted later.
  • Publish the regime declaration receipt with its validity_window.
  • Collect attestations from independent, geographically distributed attestors until k is reached, or the action is blocked.
What makes it hard to game

k is not a static number anyone can memorize and route around. It's derived from the manifold at declaration time, and the manifold's digest travels with every receipt. A verifier can independently confirm k was computed correctly for that regime and action class, not just trust that it was.

Public verifier: standalone, offline, zero network calls to Hive. Anyone holding the regime declaration, the attestations, and Hive's public key can check whether the required k was actually met, and whether the attestors were actually distributed the way the manifold demanded.

Integration surface

Sits alongside existing on-call and paging tooling. Pilot-ready for PagerDuty-style rotation systems and any workflow engine that already tags actions by class; not yet deployed at a live customer.

Overhead

Regime lookup and manifold digest check add negligible latency to the action path. Countersign collection is asynchronous and off the hot path; the action either waits for k or fails closed within its validity window.

Fail-open on convenience, fail-closed on the receipt

If the countersigning infrastructure itself is unreachable, the underlying action fails closed rather than proceeding uncountersigned. There's no silent bypass mode.

Signature standard: NIST FIPS 204 (ML-DSA) · Reference implementation: hive-typed-signer, one file per primitive.

What we don't claim

Honesty is the product. Here is exactly where the edges are.

Not a judgment of the action itself

Diurnal Bond proves that enough of the right people, geographically distributed and awake, agreed to let an action proceed. It does not evaluate whether the action was wise, safe, or correct. That judgment still belongs to the humans who countersigned.

Not a replacement for on-call staffing

If an organization genuinely has nobody awake and available to meet the required k during a weekend, Diurnal Bond blocks the action. It doesn't magically produce qualified attestors. It makes the staffing gap visible instead of hidden.

Live integration is pilot-ready, not deployed

The cryptographic core, the manifold digest binding, and the k computation are built and tested. Wiring this into a real paging system and a real on-call rotation at a customer is the next step, and it has not happened yet.

Where Diurnal Bond sits in the Hive canon

Diurnal Bond™ is one of seven upstream primitives filed together, July 26, 2026, USPTO application 64/119,279, all sharing the ML-DSA-65 signer and the usap.v1 envelope. It governs the time and consensus axis: who has to be awake and agree before a risky action proceeds in a low-oversight window. The other six cover environment integrity, policy disclosure, intent alarms, network enforcement, egress metering, and post-incident reproducibility.

PrimitiveWhat it provesAxisWhen
Diurnal BondConsequential actions in weekend, on-call, or after-hours windows require k-of-n countersigning, where k is computed from a signed risk manifold.Time and consensuscrypto core proven integration pilot-ready
Provenance-Bonded SandboxEnvironment integrity, continuously, from provisioning through every heartbeat.Environment integritycrypto core proven
Refusal LedgerEvery refusal-policy mutation is on record, and the runtime value stays inside declared bounds without disclosing it.Policy disclosurecrypto core proven
HowlerAn alarm about intent formation fired before the effect emitted, and a third party can independently replay it.Intent alarmcrypto core proven
Perimeter BondThe exact enforcement bytecode that intercepted syscalls is bound into every attempt receipt.Network enforcementcrypto core proven
Egress BondData leaving the perimeter is metered per semantic class against pre-committed caps, without exposing which rows contributed.Egress meteringcrypto core proven
Forensic RailPost-incident analysis runs under a bonded consortium credential and is deterministic-replay-bonded for independent reproduction.Post-incident reproducibilitycrypto core proven
CarnacThe downstream gate: challenge, escalate, or stop an agent action before it executes.Downstream gatenow
HiveSealWhere the signing key lives in silicon: a key-side root.Key-side rootnow
AFiRAttested Fragmented Inference Routing: signed routing of an inference across fragments and providers.Compute axisnow
SiGRA specific model at a specific config produced a specific output, signed and checkable offline.Compute axisnow

See also: the OpenAI and Hugging Face incident analysis, the motivating case for Diurnal Bond and three of its six sibling primitives.

Pilot Diurnal Bond on real weekend and on-call workloads

We're looking for design partners running agent workloads with real on-call rotations to take the crypto core into a live paging and countersigning flow. You bring the rotation and the action classifier. We wire the risk manifold, the regime declaration, and the k-of-n countersign collection, run the smoke tests against your action classes, and you walk out with receipts a regulator, auditor, or court can check offline.

Diurnal Bond: weekend and after-hours countersigning. Patent Pending. Binds consequential agent actions in low-oversight time windows to k-of-n countersigning from geographically distributed attestors, where k is computed from a signed risk manifold, signed independently with ML-DSA-65 (FIPS 204), checkable offline. Crypto core built and proven: 37 of 37 smoke tests pass. Filed July 26, 2026, USPTO application 64/119,279. Real on-call integrations are pilot-ready, not yet deployed. We never fake a receipt.

Private by design. Hive does not store your prompts. Every request is already receipted by a one-way SHA-256 fingerprint, not the words. Proof, not surveillance.