Hive research paper

Evidence Graphs for Agent Runs

Order, state links, roots, counts, and declared gaps

Published
September 3, 2026
Scope
4 typed receipt profiles
Format
HTML, Markdown, JSON index
Quick answer. An evidence graph turns a run into canonical leaves and ordered links. The verifier rebuilds roots, counts, transitions, and durations. A valid graph proves internal consistency of the supplied record, not the correctness of OCR or the truth of raw inputs.

The problem

Agent runs cross document extraction, object storage, event streams, and origin records. A flat list loses the relation between one state and the next. A graph preserves those relations in a form that can be rebuilt by an independent verifier.

The useful boundary is strict. Canonicalization can prove that two parties evaluated the same bytes in the same order. It cannot prove that the bytes described reality or that an omitted event never happened.

Primitive map

ReceiptBound inputsDerived relationClaim boundary
afir.ocr.docproofDocument commitment, page leaves, OCR output commitment, and ordered linksRoot and page count recomputeOCR accuracy or human authorship
afir.s3Object versions, canonical leaves, and state transitionsVersion links and object root recomputeCloud account control
afir.streamOrdered event leaves and timestampsCount, duration, links, and stream root recomputeComplete event capture
origin.proofOrigin observations and canonical transitionsSupplied origin chain is internally consistentPhysical origin or source honesty

Verifier gates

The verifier rebuilds derived values. It does not trust a caller supplied outcome, count, root, total, or relation.

  • CANONICAL_LEAVES
  • ORDERED_LINKS
  • ROOT_RECOMPUTATION
  • COUNT_RECOMPUTATION
  • DURATION_RECOMPUTATION
  • OUTCOME_DERIVATION

Failure cases

Reordered events

Changed order produces different transitions and a different root.

Broken state link

A transition that does not reference the prior state fails its named gate.

Invented count

The verifier counts canonical leaves instead of trusting a total.

Invented duration

The verifier derives duration from ordered timestamps.

Inflated outcome

A favorable label fails when graph relations do not support it.

Claim boundary

  • OCR receipts do not claim extraction correctness.
  • Graph roots do not prove raw payload truth.
  • A graph cannot prove that an unobserved event did not occur.
  • A valid object graph does not prove that a host or account was uncompromised.

Standards context

These sources describe related transparency, authorization, or evidence patterns. They do not endorse Hive or establish that a Hive receipt was present in any third party system.

Related research