Sourced. Derived.
Or absent. No fourth state.

The three-state model

Every numeric or factual claim Afrimintel surfaces is in one of three states:

Editorial Judgment — qualitative claims

The three-state model governs numeric and factual claims. A separate discipline applies to qualitative editorial framing — comparative readings ("EU policy continuity through 2030 is more predictable than U.S. policy continuity across administrations"), characterisations of trajectory ("the corridor's effective country-risk profile is dominated by the highest-risk segment"), and decision-shape framings ("this is post-settlement re-entry, not pre-FID screening"). These are not Sourced, not Derived in the strict computational sense, and not Absent — they are editorial judgments.

The discipline that governs them:

• Surfaced as judgment, not as fact. Editorial framings are written so a reader can identify them as editorial calls. We do not present comparative readings, decision-shape framings, or trajectory characterisations as if they were sourced facts.
• Basis named when load-bearing. When an editorial judgment carries decision-aid weight, the basis is named — the institutional-vs-bilateral structural difference behind a U.S./EU stability comparison; the trilateral-coordination-cost framing behind a corridor-level country-risk reading; the operating-vs-disputed distinction behind a re-entry decision shape.
• Subject to the Correction Velocity SLA when challenged. Editorial judgments are not below the correction discipline. A senior reader who flags an editorial framing as incorrect or unsupported gets a response on the same SLA as a numeric correction — material disagreement addressed within 7 business days, non-material within 30. Either the framing is defended with named basis, or it is revised, or it is withdrawn. The Audit Log records the resolution.
• Editorial responsibility owns them. Numeric claims pass through the data quality verification role; editorial judgments are owned at the editorial responsibility level. Both are named at the same accountable owner.

This discipline is added in v1.0.45 in response to a hostile-audit observation that the three-state model governs numbers but not the qualitative framing on which decision-aid value depends. Both layers are now published.

absence_basis: the 17 August 2026 amendment

Absent declares that no figure is carried. Since 17 August 2026 every Absent cell also declares why, through an absence_basis field with four permitted values: not-disclosed (checked against a named primary source), not-yet-verified (the default; no check on record; asserts nothing), not-applicable, and withheld. Only not-disclosed and not-applicable assert anything about the public record. Cross-asset gap statistics may be computed only over those two; a statistic that pools not-yet-verified cells describes Afrimintel’s verification coverage, never operator disclosure, and must be labelled as coverage. Enforced by contract-suite check-49. The governing text is the quality_contract block of the manifest, whose changelog entry for that date reads:

absence_basis discriminator added (check-49). Every Absent cell now declares why it is absent: not-disclosed (checked against a named primary source), not-yet-verified (default; no check on record, asserts nothing), not-applicable, or withheld. Resolves the conflation of disclosure gaps with verification backlog. All 1,472 existing Absent cells default to not-yet-verified; promotion to not-disclosed is one cell, one source, one date. Aggregate gap statistics may not pool not-yet-verified cells.

Working-state tags: retired

Between v1.0.61 and August 2026 the substrate carried two transitional tags, Pending and Inferred-propagated, which this Standard documented as working states rather than a fourth and fifth state. They are retired. The manifest's quality_contract declares no working tags, and the contract suite fails any feed that carries one.

Their job is now done inside the three states. A figure not yet verified is Absent with absence_basis: not-yet-verified, which asserts nothing about the public record. A figure carried from an earlier cycle without a re-walk is either re-verified and Sourced, or it is Absent with that basis. The verification queue and its target dates stay public in sources-verification-log.json; each transition is recorded on the audit log.

Field-level provenance

For records classified as INTELLIGENCE-GRADE (currently 6 deposit dossiers in the platform's database, with a published verification queue of candidates), provenance is captured at field level — not just record level. Each Reserve tonnage, Resource grade, operator name, and reporting basis carries its own tier tag and source citation. A user examining Kamoa-Kakula sees not just "Sourced from Ivanhoe NI 43-101" but the specific document, effective date, and per-field provenance.

Schema fields enforcing this discipline (v1.0.18 schema):

• res_mt_reserve / grade_reserve / res_type_reserve — Proven + Probable Reserve, separated from Resource
• res_mt_resource / grade_resource / res_type_resource — Measured + Indicated + Inferred Resource
• reserve_basis / resource_basis — explicit "100% project basis" vs "attributable to [operator]" disclosure
• operator_interest — source-qualified ownership detail
• dispute_status — enum for contested assets (Manono pattern)
• transparency_flag — enum for opaque or recovery-stage operators
• last_reviewed — explicit date stamp; pre-deploy pipeline blocks any IG record older than 180 days

Correction-velocity SLA

Material errors corrected within seven business days. Non-material corrections (typos, formatting, version stamps) within thirty business days. Every correction is logged at /audit-log/ with: what changed, why, the source of the authoritative correction, version marker incremented, regression check, editorial sign-off.

The Audit Log is published, not internal. A correction that has not been logged is not complete.

Pre-deploy gate discipline

Every deploy is gated by an automated pre-deploy pipeline that blocks publication on any of the following findings:

A CRITICAL or SIGNIFICANT finding blocks deploy. The pipeline runs at every build; the script is in the bundle at scripts/audit/pre-deploy-audit.js.

AI provenance contract

Afrimintel's AI feature (ASK Afrimintel) is governed by a published Provenance Contract embedded in the system prompt before every query. The contract instructs the model to:

1. Answer only from the Afrimintel database injected into the system prompt — not training-data inference
2. Cite the tier (Sourced / Derived / Absent) for every numeric or factual claim
3. Refuse fabrication of operator names, reserve tonnages, grades, transaction values, or counterparty relationships
4. Refuse to claim Afrimintel partnerships, customers, or commercial relationships unless explicitly stated in the data
5. Respond "Afrimintel's current dataset does not include verified information on [topic]" when no relevant record exists

Compliance with the contract is measured by a 20-query test battery (in-database / absent / adversarial / tier-mix categories). A defence-in-depth runtime audit runs after every model response, surfacing inline flags if the response contains counterparty-relationship language, forward-looking partnership claims, or permanent-exclusion terms.

What this Standard does not claim

Specific things the Standard does not promise:

• That every dossier is exhaustively current — operational events outpace dossier refresh; the last_reviewed field shows the floor of staleness, the 180-day threshold the ceiling
• That every Sourced citation has been independently re-walked by Afrimintel against the underlying primary document — the Sourced tier requires that a named, dated, citable primary or institutional document exists and is recorded in the platform's data layer; it does not require that Afrimintel has opened the source PDF and verified each cited field. Verification depth varies by record and is highest on the worked dossier-grade and intelligence-grade dossiers (where field-level provenance is documented and quarterly deep audits are scheduled) and lower on the spatial-reference tier (where the citation chain is recorded but per-claim re-walks are not routine). When Afrimintel does perform an independent re-walk, the work is documented in the audit log under a specific record-level audit entry. The hedge text on intelligence-grade dossiers explicitly flags claims that have been cited but not independently re-walked, distinguishing citation hygiene from independent verification
• That tier classification is governed by the published tier definitions, with the platform's data layer as the single source of truth; the public methodology page surfaces the intelligence-grade count (6), and the full per-tier inventory is maintained and reconciled internally. The contract suite (check-44 and check-45) verifies that tier counts reconcile to the feed and that no record carries a tier its fields do not support; it does not verify per-record classification judgement. The judgement that a specific record meets the intelligence-grade criterion (resource statement + named operator + primary-source citation) sits with editorial discipline at ingestion time and with the quarterly deep audit cycle on rotating provinces, not with an automated classification check. Where a deep audit reclassifies a record, the audit log entry records the reclassification
• That a model-written answer is verification — Ask Afrimintel answers only from the records supplied and every figure is traced to them, but an answer is a reading of the record, not a substitute for the cited primary source. The platform's other AI tools were retired on 11 Sep 2026.
• That the Standard substitutes for accreditation — it is a published editorial framework, not a peer-reviewed industry standard backed by a governing body

Editorial responsibility

The Standard is signed and operated by a single named editorial responsibility: Nikesh Patel, geochemist (nikesh@afrimintel.com). Distribution of editorial capacity across additional named reviewers is on the build roadmap, sequenced to the point a commercial event requires it. Until then, every record carries one editorial signature, and that signature is accountable.

Versioning and changes to this Standard

Changes to the Standard itself are logged at /audit-log/ under "Standard amendment." Material changes (e.g. addition or removal of a state, change to the correction SLA, change to the AI contract clauses) require explicit Audit Log entry with reasoning and effective date. Non-material editorial revisions (typos, formatting, link maintenance) are versioned but do not require a separate entry.

Adopted 25 April 2026. Version identifier ruled 7 September 2026: the Standard is v1.1 on every surface and in the manifest quality_contract; the changelog reference to "v1.2" on 8 July 2026 was drift and is superseded by this line. Last amendment: 17 August 2026 (absence_basis discriminator on every Absent cell, enforced by check-49; see the manifest quality_contract changelog). Earlier: 2 May 2026 (v1.0.18 schema fields added, pre-deploy gate checks expanded). Companion documents: Methodology · Bankability Record · Audit Log · Privacy Policy · Terms of Service.