Data provenance is the recorded origin and lineage of a datapoint — where it came from, when it was captured, and how it was transformed — so any value can be traced back to its primary source and verified.
Provenance answers "how do you know that?" for every figure. It records the source (which filing, which feed), the timestamp, and each transformation along the way, producing an auditable chain from raw source to served value.
For AI, provenance is what upgrades retrieval into trustworthy grounding: an agent can not only fetch a number but show the user the exact origin, making the claim independently checkable.
A holding figure annotated with "from CIK 0001067983, accession 0001193125-24-000123, parsed 2026-05-15" is fully provenance-tracked.
Provenance is built into Arkolith at the datapoint level — the moat (acquisition + resolution + lineage) and the anti-hallucination feature are the same thing.
Arkolith turns this into live, sourced data your agent can query — SEC filings, insider activity, and market data behind one key, every datapoint traceable to its origin.