CitationGate: grounding every finding
A finding with no verifiable quote is rejected, and a quote that doesn't match the source is dropped. This is what makes LexCore's output traceable.
CitationGate is what makes LexCore verification-first. When an agent proposes a finding, it has to attach the exact clause that supports it. That quote is then located verbatim in your document before the finding is allowed to surface.
The rules
- A finding with no citation is rejected outright.
- Each quote is matched against the source: a whitespace-flexible exact match first, then, for long spans on first verification, a fuzzy word-shingle fallback. A match returns real character offsets and a match type (
exactorfuzzy). - Quotes shorter than 10 characters are rejected. A finding passes only if at least one of its citations verifies.
- Re-verification after an edit is strict (exact matches only). If you change an amount or a term, the finding that cited the old text is flagged stale instead of being quietly re-matched.
- Every decision (verified, failed, passed, rejected) writes an audit entry.
Page-level anchoring
Parsing records the page (and passage) for each chunk, so a citation badge jumps to the exact page in the source PDF. That meets passage-level citation granularity, which is the bar procurement checklists set.
The one exception: absence
Some of the most useful findings are about what a contract doesn't say, such as a missing indemnity or an absent liability cap. There is no quote to check. Absence findings carry a non-quote evidence type ("the playbook requires this and extraction found no matching provision"), skip the quote gate by design, and default to high supervision, because a false "missing" claim is expensive.
Related documentation
Multi-agent debate (DyTopo)
A tiered bench of specialist agents proposes and challenges findings in parallel rounds, in an order set by a learning loop. A claim has to survive scrutiny before you see it.
Review Level (LAM): sufficient supervision, made auditable
How much human review is enough for a task? LexCore turns that judgment into an explicit setting, recorded for audit, that decides how many findings escalate to you.
Clause extraction and the 41-category pack
Pull structured clause facts (type, verbatim text and typed attributes) under the same grounding rules as review.