Build log, March 26, 2025
Build log: table extraction when the table spans four pages
The problem
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
What makes this hard is that the signal is distributed. A single clause read in isolation looks fine. Read against the definitions section and two schedules, the same clause does something different.
What we do about it
We score against a human baseline drawn from executed matters rather than a synthetic set, because synthetic contracts do not contain the drafting scars that cause real misses.
In the current build this runs as part of the standard pass, so it applies to every document in the set rather than only the ones someone thought to check.
Where it breaks
Scanned originals with poor image quality remain the weakest input. So do agreements that were assembled from three precedents and never reconciled, which is common in long-lived supplier relationships.
If you take one thing from this, make it the habit of checking the adjacent provision before you sign off the clause in front of you.
Working notes from the Lawrs team. General information about legal technology and practice, not legal advice.