Source Explorer
Query Token Match
Search rows use exact token matches over pinned snippets. Honesty note: simplified toy source-explorer model, corpus-light with no neochart dependency; the pinned first step carries the full honesty note.
Structured Visual
Jurisdiction: US; as of 2026-06-24; not legal advice; Code encodes a stated review workflow, 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.
Source explorer honesty note
Honesty note: simplified toy source-explorer model; corpus-light and no neochart dependency; jurisdictions and authority treatment vary; as of June 24, 2026; not legal advice; code encodes a stated review workflow, not the law itself.
Use exact query tokens
The stated process tokenizes the query and compares exact token overlap with pinned source snippets.
Example query packet
The query is normalized into 3 tokens.
The table recomputes exact matches
The FRCP row has 3 exact token matches and the table has 5 support rows.
Diagram note
The diagram is an exact token-match table. It does not perform semantic ranking or provide answers.
Jurisdiction: US; as of 2026-06-24; not legal advice; Code encodes a stated review workflow, 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
Search rows should expose query tokens, match counts, source snippets, and review handoff without answer generation.