Clause extraction & the 41-category pack
Pull structured clause facts — type, verbatim text, and typed attributes — with the same grounding discipline as review.
Extraction runs over a controlled clause vocabulary (the 41 standard categories) to produce structured clause facts. It mirrors the CitationGate: the model may only nominate a span, and a span that can't be located verbatim in the source is dropped and counted — never stored.
- A stored clause fact is always provable: clause type, the verbatim text, and its character offsets.
- Typed attributes — amounts, currencies, percentages, dates, parties — are parsed deterministically by rule from the grounded span, not guessed by the model.
Related technical documentation
Document comparison & the review grid
Compare versions or compare a contract against a standard, in a tabular grid you can export to Excel.
CitationGate: grounding every finding
The trust core. A finding with no verifiable quote is rejected; a quote that doesn't match the source is dropped. This is why LexCore's output is traceable.
Authority-grounded legal research
Answers grounded in Nigerian authority, with every citation verified, currency flagged, and coverage disclosed honestly.