Retrieval Models
Lexical Match
Token overlap can be counted with exact integer counts. Honesty note: simplified toy corpus; jurisdictions vary; the pinned first step states the as-of date; not legal advice; retrieval points to sources and does not answer the legal question.
Structured Visual
Jurisdiction: US; as of 2026-06-24; not legal advice; Code encodes a stated structural model, not the law itself. RENDER STRUCTURE · REFUSE INTERPRETATION · CITE · ABSTAIN · HAND-OFF.
RENDER STRUCTURE · REFUSE INTERPRETATION · CITE · ABSTAIN · HAND-OFF: render structure, refuse interpretation, cite provenance, abstain when unsupported, and hand off to human review.
Retrieval honesty note
Honesty note: simplified toy corpus; jurisdictions vary; as of June 24, 2026; not legal advice; retrieval points to sources and does not answer the legal question.
Match by token overlap
The stated retrieval model uses exact token overlap. It counts shared tokens between the query and each corpus row.
Example query and source row
The example query is diversity amount citizenship. The matching row is the record for 28 U.S.C. sec. 1332.
The count governs rank order
Record id diversity has 3 of 3 matching tokens and rank 1 in this toy table.
Diagram note
The diagram displays integer overlap and deterministic rank. It does not claim legal relevance or source weight.
Jurisdiction: US; as of 2026-06-24; not legal advice; Code encodes a stated structural model, not the law itself. RENDER STRUCTURE · REFUSE INTERPRETATION · CITE · ABSTAIN · HAND-OFF.
RENDER STRUCTURE · REFUSE INTERPRETATION · CITE · ABSTAIN · HAND-OFF: render structure, refuse interpretation, cite provenance, abstain when unsupported, and hand off to human review.
Summary
Lexical matching is useful because each displayed number can be recomputed from the query and corpus text.