Four tiers.
Every engagement produces the same four artefacts. The tier defines scope and price, not rigour.
The four artefacts
Versioned dataset
Lance-native format with fragment-level copy-on-write versioning and schema-enforced annotations against a defined taxonomy. For training, evaluation, and downstream pipelines.
Merkle integrity proof
A cryptographic tree over dataset fragments, with proof generation for any individual sample. Verify the bytes have not changed.
Provenance bundle
Four layers: SHA-256 content hashes, Merkle root, C2PA content credentials carried as a sidecar manifest referencing the dataset by hash, SLSA v1.2 attestation. Verified independently with external reference tools.
EU AI Act evidence pack
Articles 10, 11 and 12 mapped artefacts with coverage classification: fully populated, requires human input, or not applicable. Articles 9, 14 and 15 (risk management, human oversight, and system accuracy) stay with the provider deploying the system.
Each deliverable ships with verification recipes: commands that run against your copy of the dataset using tools Static Signal does not maintain. Acceptance requires you to run at least one successfully.
The tiers
Published rangesStandard
Single defined taxonomy — yours, or a Static Signal template — with modality-appropriate validation and train, validation, and test splits.
Production
Adds a taxonomy iteration cycle, custom schema authoring, stratified splits with a verification report, and branch-aware versioning.
Enterprise
Adds hierarchical taxonomies, a reference set curated with your domain experts, and a workshop day.
Bespoke
Greenfield taxonomy design, a pilot dataset to validate it, then full production construction. Begins with a paid discovery engagement.
Modality coverage
Images
In production useSix-tier validation: structural checks, subject gate, data quality, perceptual quality, categorical assessment, consistency. Four of the six gate; advisory findings are recorded as advisory.
Text · tabular · multimodal
Available on engagementValidation stacks are scoped per engagement; the provenance and compliance artefacts are identical to image deliverables.
Out of scope
- Software licensingthe instrument is the production line, not the product
- Continuous SaaS hostingcustody is bounded, not permanent
- Model training and deploymentwe hand over the dataset; what you train on it stays with you, or becomes an applied engagement
- Annotation labour at scaleyou or your domain experts provide labels; we verify, structure, and sign them
- Generic consultingaudit and regulator support is a published add-on; open-ended advisory is not something we sell
Applied systems — capture rig to operator interface — are scoped separately.
Applied workNegotiate scope and timeline. We do not negotiate evidence quality or the price floor.
Start an engagement