Agreements · Semantic Instruments

An agreement can become
a shared, inspectable instrument.

An agreement is more than a signature. It can include claims, references, responsibilities, conditions, and different understandings of the people involved. An agreement ledger gives those parts a visible home before anyone asks software to act on them.

The result is not a system that decides what people “really meant”. It is a record of what each person put forward, what they accepted, what remains open, and the exact rule set they jointly authorise for a defined purpose.

A four-part path

From individual understanding to a bounded shared tool

Different understandings are data

Agreement does not require pretending everyone began in the same place

Claims and references

A party may rely on a policy, a lived experience, a professional standard, a dataset, or a community account. The ledger records the source and its intended role instead of calling every input “fact”.

Scope and confidence

A person can say “I accept this for this situation”, “I need more evidence”, or “I agree only with this exception”. These qualifiers help prevent a broad rule being inferred from narrow consent.

Dissent and revision

A disagreement is not a broken record. It can be retained with the agreement, revisited when conditions change, and reflected in a later version without rewriting history.

Illustrative example

A community referral agreement

A resident group, a local service, and a community worker want a consistent way to prepare referrals. They do not hand authority to the software; they write a narrow shared procedure for handling a referral package.

Recorded materialParty perspectivesConsolidated term
Claim: referrals need enough information to be reviewed.Service: identity and contact fields are needed. Resident group: people must be told what is missing.Require the declared referral fields; return a clear missing-information status.
Reference: local service criteria and the group's consent guidance.Worker: a person must review sensitive cases. Service: criteria can change by version.Include the criteria version and route sensitive or uncertain cases to human review.
Boundary: a prepared referral is not a decision on eligibility.All parties accept this limit.Never output “eligible”; use ready, held, or needs-human-review.

When an agreement takes effect

An instrument receives authority only from a current, declared agreement

Writing a rule is not the same as authorising it. The agreement lifecycle makes that distinction visible: a software agent may use an instrument only while the relevant human agreement is current, within scope, and supplied with the declared information.

01 · PROPOSED

Record

Claims, references, terms, and party positions are visible. No agent authority exists yet.

02 · RATIFIED

Consent

The named parties meet the declared consent condition and approve the specific version.

03 · ACTIVE

Use

The bounded instrument can follow the ratified procedure and retain a receipt.

04 · HELD

Pause

Missing inputs, an unmet condition, or an unresolved exception hold the run rather than invent an outcome.

05 · SUPERSEDED

Review

A revised or withdrawn agreement stops new reliance; earlier receipts retain their context.

Temporal provenance and review

A decision can be reasonable when made and still require relief when the circumstances change

A human-centric instrument records the evidence, assumptions, authority, and limits that were available at the time of a decision. Later evidence does not rewrite that original context. It creates a new, time-linked record that can trigger review, revision, pause, relief, or remedy for ongoing negative effects.

T₀ · DECIDE

Record the basis

Capture the versioned evidence, known uncertainties, mandate, and reason the decision was made.

T₁ · LEARN

Add later evidence

Link new material, changed conditions, affected parties, and the date it became available without overwriting T₀.

T₂ · REVIEW

Reassess effect

Apply the declared review trigger: confirm, qualify, hold, revise, or stop further reliance on the earlier rule.

T₃ · REMEDY

Act on continuing harm

Record relief, correction, escalation, or a revised agreement—and retain the full chain for later review.

What the temporal rule requires

  • As-of evidence: an agent must be able to distinguish material available when a decision was made from material learned later.
  • Material-change triggers: agreements declare which new facts, impacts, expiry dates, or challenges require reconsideration.
  • No silent carry-forward: a prior decision cannot be treated as permanently current when its time, scope, or evidence conditions have expired or changed.
  • Relief path: affected people need a named route to seek correction, review, pause, replacement, or remedy.

Optional integrity anchoring

Link the record without making public disclosure compulsory

An agreement, provenance record, review event, or receipt may remain in the relevant local or controlled environment. When the parties choose, it can also carry an integrity commitment: a content digest, a Merkle-tree inclusion proof, or a reference pinned to a distributed ledger (DLT). Later records can link to the earlier commitment and to the revised version.

Local only
Keep the record private with its own version and receipt chain.
Merkle-linked
Commit a collection of records to one root while proving inclusion only when needed.
DLT-pinned
Anchor a chosen digest or reference to an external, shared chronology when that is appropriate.

An anchor can help show that a particular commitment existed and has not changed relative to that chain. It does not itself prove the underlying statement is true, that a person consented, or that a record has a particular legal effect. Sensitive material and unnecessary personal references should not be placed in a public ledger.

Zero-knowledge proof support

Prove a declared condition without disclosing all of the underlying evidence

Where a suitable proof circuit exists, QualiaDB/Webizen can use zero-knowledge proofs to show that a defined predicate or policy condition has been satisfied without exposing the private witness material. This lets an agreement or instrument ask the narrow question it needs answered while retaining privacy over supporting records.

Selective evidence

Prove a threshold, range, authorised condition, or other supported predicate without disclosing the private value, source record, or full credential.

Bounded verification

The verifier checks the specific circuit, public inputs, and proof. The result says only that the declared condition was satisfied for that circuit.

Accountable receipt

A receipt can record the proof type, policy or circuit version, verification result, permitted purpose, and time—without publishing the private witness.

How this supports agreements and provenance

  • Eligibility without excess disclosure: establish that a required condition is met without exposing unrelated personal or organisational evidence.
  • Private rights conditions: demonstrate that a licence, role, permission, or agreed policy condition has been satisfied without disclosing the entire protected agreement.
  • Integrity of bounded computation: where a supported circuit exists, verify a defined computation or policy gate without revealing its private inputs.
  • Public anchoring with private substance: combine a proof with an optional Merkle or DLT commitment while keeping sensitive evidence outside the public record.

Disclosure is not binary

A proof may be broadly checkable while the protected evidence remains available only through a separate authorised process

Zero knowledge means that verifying the proof does not reveal its private witness. It does not mean that the underlying record is metaphysically unknowable to every other person or system. A protected-person, witness-protection, safeguarding, or similar instrument may deliberately separate a public or routine proof from controlled custody of the supporting evidence. An authorised court or other accountable decision-maker may be able to request or receive the necessary material under the applicable process, without making it available to routine verifiers, software agents, or the public.

1 · Routine verifier

Receives the declared statement, public inputs, proof, and a scoped verification receipt. It need not receive names, locations, source records, or other witness material.

2 · Protected custody

Holds the sealed underlying material under a declared custody and access policy. Holding encrypted material does not itself confer permission to inspect, copy, or disclose it.

3 · Authorised review

May receive the least material necessary only when an accountable human authority, stated purpose, time limit, and applicable procedure permit it—for example, a court acting through the relevant legal process.

What the accompanying disclosure instrument must state

  • Protected scope: which material or references are protected, at an appropriate level of detail.
  • Permitted recipients and purpose: which roles may seek disclosure, for which defined purpose, and what they may receive.
  • Procedure and human authority: the accountable people, mandate, threshold or order required before release; an AI agent cannot self-authorise disclosure.
  • Minimisation, time, and remedy: the least disclosure necessary, expiry/revocation conditions, receipt chain, review, and challenge path.

Identifiers and evidentiary basis

References help establish what a record is about; evidence establishes what may be relied upon

An instrument may contain one or more scoped identifiers connected with a person, organisation, licence, qualification, role, device, or permission. For example, it may refer to a professional licence, a board-approved role, a course credential, or a device permission such as an API key. These references make the relevant records linkable and checkable; they do not define a human being or create authority on their own.

What an instrument can record

  • Reference: which person, role, credential, organisation, device, or resource a statement concerns.
  • Provenance: who issued a statement, when, under what agreement, and from which source material.
  • Scope: the purpose, time, jurisdiction, system, or conditions under which it may be used.
  • Verification: whether the declared evidence and permissions can be checked against the relevant record.

What makes it an evidentiary basis

  • It preserves the statement together with its source, version, conditions, and any qualification or challenge.
  • It can establish an operative fact within the stated agreement—for example, that a licence was verified against a named issuer on a particular date.
  • Authorised people or bounded software can use that record as input to a declared procedure.
  • It does not turn a record into universal truth, erase context, or replace human judgement where that judgement is required.

This is why instruments can support advanced software and AI systems: they provide structured, attributable material for a limited task while preserving the basis on which the task was performed.

Layer 4 · Formal Specification · Identifier Fabric (IDF-01–IDF-05)

Four Disjoint Planes & Typed Cross-Plane Morphisms in Agreement Governance

Agreement records are validated against ontologies/identifier_fabric_shapes.ttl across four disjoint planes:

1. Entity (Who Plane) NaturalAgent (living-SHACL), LegalEntity, and SystemAgent. Never merged by similarity, handle, wallet, location, or biometrics; owl:sameAs is forbidden on the Who plane (SameAsError::WhoPlaneForbidden).
2. Claim Plane Scoped, signed assertions (VerifiableCredential, idf:ClaimOpinion, idf:RoleCapacityGrant, deontic/epistemic norms) with provenance and expiry. VCs prove cryptographic origin integrity of an issuer's statement, not universal ontological truth.
3. Handle Plane Revocable, rotatable network or directory locators (DNI / idf:DigitalNetworkIdentifier, idf:RelationScopedLocator, DNS, email, did:qi endpoints). Revoking a handle closes the channel without erasing the Entity.
4. Instrument Plane Cryptographic keys, hardware tokens, and software tools (idf:Instrument, idf:AiAgent, idf:CoAttestationBundle) classified by InstrumentProofClass (CryptographicOriginIntegrity, HardwareChannelPossession, SemanticClaimEvaluation) and closed KeyRole (IdentityAssertion, CredentialSigning, TransportHandshake, StorageEncryption, RecoveryBootstrap).

Cross-plane links use typed evidence morphisms (idf:supportedByInstrument, idf:assertedAbout, idf:observedAtHandle), while the F5 (compile-time VibeScript) and F6 (runtime ingress/query) Anti-Feature Firewalls reject person_score, identity_confidence, and same_person.

Structural rule · who acted, and in what capacity

Human accountability must remain traceable when an entity or agent acts

This is a required property of a human-centric system, not an optional provenance feature. Where an agreement or instrument involves an incorporated entity, it must preserve the accountable human decision-makers or authorised representatives, the role in which they acted, and the scope of that authority. The point is accountable provenance, not indiscriminate disclosure of personal information.

When an incorporated entity acts

The instrument must distinguish the incorporated entity from the people who made or authorised the relevant decision. Its provenance records:

  • the entity and the particular agreement or decision;
  • the authorised human role or decision-making body;
  • the mandate, scope, time, and version under which it acted; and
  • the review or challenge path if the decision is disputed.

When an AI agent acts

An AI agent may carry out a bounded task for a natural person acting personally, or for a natural person exercising an authorised role for an incorporated entity. It is never the source of authority itself. The receipt must record:

  • the human principal and, where relevant, the authorised role;
  • the specific instrument, mandate, and limits it was allowed to follow;
  • the inputs, outcome, and any held or escalated condition; and
  • who can review, challenge, revise, or stop further use.

Provenance as a Semantic Instrument

The account of how something came to exist can itself be inspectable, attributable, and reusable

A provenance instrument is a bounded package that records the origin and development of a work, decision, dataset, agreement, or technical artefact. Other Semantic Instruments can refer to it as evidence: not merely that a record exists, but how it was made, who contributed, which authority applied, and what terms governed its use.

Creation trail

Versions, source material, technical artefacts, dates, contribution events, reviews, and the relationship between them.

Human contribution

The people and roles involved in creation, approval, assignment, stewardship, or later authorised use—within an appropriate privacy scope.

Rights context

Applicable agreements, licences, assignments, confidentiality conditions, and the limits on what an agent or recipient may do.

Protectable-IP use cases, including patents

  • Invention disclosure: preserve an attributed chronology of a technical idea, its versions, contributors, supporting artefacts, and relevant decisions before or alongside a formal filing process.
  • Rights and authority: relate a work to its assignment, licence, employer or organisational authority, named application or registration references, and the scope of permitted use.
  • Controlled evidence: keep sensitive material under declared access conditions, or preserve a commitment/digest and provenance record where full disclosure would be inappropriate.
  • AI-use boundary: allow an advanced system to use a work only under the stated licence, purpose, attribution, confidentiality, and human-review conditions.

Community of Experts · proposed instrument profile

Research artefacts can travel with the community context that makes their use accountable

Advanced research in a field may produce models, datasets, methods, findings, visualisations, and supporting source material. A Community of Experts (COE) Semantic Instrument can record the field-specific community’s scope of review and the conditions under which those artefacts may be relied upon. It is a credential about a defined community process—not a claim that a model is universally correct or that an expert community replaces human responsibility.

HMC: the research package

The Hyper Media Container carries the inspectable material: a description, definition graph, manifest, artefacts, model documentation, references, and integrity information. It can include compact semantic payloads while declaring larger models or data volumes as dependencies.

An HMC is transparent and integrity-checkable. Confidentiality or restricted access requires separate, declared protection and access conditions; it is not implied simply by putting material in a container.

COE instrument: the accountable use context

The companion Semantic Instrument states what the expert community reviewed, the applicable field and purpose, the people and roles authorised to attest, the evidence and dissent considered, and the limits of permitted reliance by people or software agents.

Its receipt can bind a later use to the research-package version, review status, rights conditions, declared model limits, and the human review or escalation path.

COE recordWhat it establishes within scopeWhat it does not establish
Research packageWhich artefacts, versions, sources, and model dependencies were supplied.That every result is correct, safe, or suitable for every purpose.
Community attestationWhich defined review, contribution, or approval process occurred and under what terms.That the community has unlimited authority or that its view is beyond challenge.
Use contractThe authorised task, licence conditions, declared limits, and review route for a person or AI agent.Permission for an agent to extend its task, disclose protected material, or substitute for required human judgement.

When it becomes an instrument

The agreement gets a readable label and a runnable boundary

The label says

  • what the shared procedure is for and who agreed to it;
  • which references, versions, and inputs it relies on;
  • what it must not decide or imply; and
  • how it can be revised or superseded.

The run records

  • the agreement and instrument version used;
  • the parties and consensus condition that authorised it;
  • the supplied commitments and any held condition; and
  • the outcome, without erasing the original agreement record.

Important boundary

An agreement instrument supports coordination; it does not replace consent or professional judgement.

People remain responsible for deciding whether to adopt an agreement, whether its sources are appropriate, and when it should be reviewed. For a closer look at the records that make this possible, continue to the agreement ledger.

Explore the agreement ledger