Proof and Deployments

What we have put to work.

Kettle has been used with institutional records and paid document-processing work. The verification tools are at an earlier stage.

Any published benchmark needs a collection, date, and method. A number without that context is not useful.

Current work

Four things we can point to.

Institutional deployment · current

Work inside an archive

The system has handled institutional records, researcher requests, collection restrictions, and human review.

Commercial work · current

Paid pipeline development

An outside customer has paid Kettle to build document-processing infrastructure for a specific problem.

Processing · current

Three input paths

We process professional scans, phone photos, and existing digital collections.

Research · current

Claims with citations

The research system keeps the source passage and document reference with extracted claims.

Status

Current, internal, or still to build.

CapabilityStatusPublic description
Document and graph processingCurrentDeployed collection workflows produce clean text, records, citations, and graph data.
Research retrievalCurrentSearch results carry supporting claims and source references.
Deterministic addressingInternalStable object IDs are used inside the research system.
Public verification standardIn developmentThe specification, test vectors, and outside verifier still need to be published.
Institution-held source pilotNext testRun a pilot where signed IDs and approved data move between systems while the institution keeps the master source files.
What counts

A node count is not proof.

A useful test starts with the source material, shows what the pipeline produced, checks the citations, and states what still failed.

See how we process a collection or send a representative sample.