Proof Models
Burden Standard Labels
Burden and standard labels should stay ordered without invented probabilities. Honesty note: simplified evidence and proof model; jurisdictions and rules vary; the pinned first step states the as-of date; not legal advice.
Structured Visual
Jurisdiction: US; as of 2026-06-24; not legal advice; Code encodes the stated structural model, not the law itself.
RENDER STRUCTURE · REFUSE INTERPRETATION · CITE · ABSTAIN · HAND-OFF: render structure, refuse interpretation, cite provenance, abstain when unsupported, and hand off to human review.
Evidence model honesty note
Honesty note: simplified evidence and proof model; jurisdictions and rules vary; as of June 24, 2026; not legal advice; code encodes a stated structural model, not the law itself.
Burden fields are labels
The stated process stores production, persuasion, and standard labels as ordered review fields. It does not turn them into percentages.
Example proof packet
The toy packet starts with a claim record, then moves through production label, persuasion label, standard label, and human review.
The flow recomputes the label order
The procedure flow recomputes 5 nodes and 4 edges from the authored label sequence.
Diagram note
The diagram is an ordering map. It does not score proof, weigh testimony, or predict a result.
Jurisdiction: US; as of 2026-06-24; not legal advice; Code encodes the stated structural model, not the law itself.
RENDER STRUCTURE · REFUSE INTERPRETATION · CITE · ABSTAIN · HAND-OFF: render structure, refuse interpretation, cite provenance, abstain when unsupported, and hand off to human review.
Summary
Burden and standard data are useful when labels remain visible and any application question goes to human review.