Four tiers.
Every engagement produces the same five artefacts. The tier defines scope and price, not rigour.
The Five Artefacts
Lance-native format with fragment-level copy-on-write versioning and schema-enforced annotations against a defined taxonomy. For training, evaluation, and downstream pipelines.
A cryptographic tree over dataset fragments, with proof generation for any individual sample. Verify the bytes have not changed.
Four layers: SHA-256 content hashes, Merkle root, C2PA v2.3 content credentials, SLSA v1.2 attestation. Verified independently with external reference tools.
Sigstore keyless or Static Signal PKI, with rotation and revocation. An authenticated chain of custody.
Articles 9–15 mapped artefacts with coverage classification: fully populated, requires human input, or not applicable. Conformity assessment preparation.
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
100–500 samples. Single defined taxonomy — yours, or a Static Signal template — with modality-appropriate validation and train, validation, and test splits.
500–2,000 samples. Adds a taxonomy iteration cycle, custom schema authoring, stratified splits with a verification report, and branch-aware versioning.
2,000–10,000 samples. Adds hierarchical taxonomies, a reference set curated with your domain experts, and a workshop day.
Scoped volume. Greenfield taxonomy design, a pilot dataset to validate it, then full production construction. Begins with a paid discovery engagement.
Modality Coverage
Six-tier validation: structural checks, subject gate, data quality, perceptual quality, categorical assessment, consistency.
Validation stacks are scoped per engagement; the provenance, signing, and compliance artefacts are identical to image deliverables.
Out of Scope
- Software licensing — the instrument is the production line, not the product
- Continuous SaaS hosting — custody is bounded, not permanent
- Model training and deployment
- Annotation labour at scale — you or your domain experts provide labels; we verify, structure, and sign them
- Generic consulting
Negotiate scope and timeline. We do not negotiate evidence quality or the price floor.