Skip to main content
Core ConceptsGovernance Spec

Evidence Classification (Tiers 1–5) & Provenance Verification

Hierarchical evidence taxonomy from Tier 1 observed cryptographic facts down to Tier 5 merchant assumptions.

NNellie (AI Automation)
Published:
Updated:
5 min read

Every fact ingested by MeritSKU is tagged with an evidence tier and a SHA-256 cryptographic provenance digest. This provenance tracking guarantees auditability and prevents speculative LLM hallucinations from poisoning financial ledgers.

Cited Claim IDs:PUB-CLM-002PUB-CLM-006

1. The 5-Tier Evidence Hierarchy

Our architecture strictly partitions evidence into five discrete tiers with decreasing confidence weights:

TierClassificationExamplesConfidence Weight
Tier 1Observed FactPro-forma factory invoice, carrier API tracking, audited bank receipt1.0 (Highest)
Tier 2Platform AnalyticsDirect Shopify order history, Google Search Console telemetry0.85
Tier 3Market AggregationAggregated 3PL rate sheets, commercial freight index, HTS tariff book0.70
Tier 4Heuristic ModelsCompetitor review velocity trends, category return rate regression0.50
Tier 5Merchant AssumptionUnverified user estimates, verbal supplier promises0.20 (Lowest)

2. Cryptographic Payload Digests (SHA-256)

Whenever an external quotation or document is ingested, MeritSKU computes the raw SHA-256 hash of the payload and records it in the evidence ledger.

This establishes a permanent, immutable chain of custody: any alteration to supplier terms or pricing immediately invalidates the upstream evaluation.

3. Zero-Hallucination Policy & Missing Data Rules

If a critical attribute (such as package height or tariff code) is absent from the source document, MeritSKU strictly fails closed to typed null.

The AI extraction engine is prohibited from guessing or fabricating realistic-sounding defaults. Missing attributes are surfaced as explicit blocker warnings in the decision report.

Was this guide helpful?

Your feedback trains our editorial documentation standards.