E3

Evidence

Anyone can produce a finding. The question is whether it survives being questioned.

Six months after a file is cleared, someone asks why. A finding that cannot answer that question is an opinion with a timestamp.

FIGURE Anatomy of a finding Four sources, four periods, one comparison — and why the difference needs a person. RULE INC-014 v2.3.0 · QUALIFYING INCOME MUST RECONCILE WITHIN 5% ACROSS SOURCESSOURCEAS STATEDMONTHLYHOW DERIVEDPaystub 03/2026p.1 · YTD box$26,820 YTD over 3.0 months$8,940 / moYTD ÷ months elapsedW-2 2025p.1 · box 1$106,500 for 12 months$8,875 / moannual ÷ 12URLA 1003p.2 · 1c$9,200 stated monthly$9,200 / moas stated by borrower1008 Summaryp.1 · field 21$9,200 used to qualify$9,200 / mounderwriter’s figureSpread between lowest and highest monthly figure: 3.7% — inside the 5% threshold.Not a defect. Flagged for review because the 1008 uses the stated figure, not the derived one.The reviewer decides: accept the underwriter’s basis, or request a written income calculation. E3 records which,by whom, and when. The finding is an exception to investigate — the disposition belongs to the reviewer. Illustrative, from a synthetic file. Threshold and rule identifier are examples.
The reconciliation passes at 3.7% against a 5% threshold. The exception is about basis, not arithmetic.

The load-bearing part

Why the rule version decides everything

Mortgage policy changes. Selling guides are updated, programme requirements shift, compliance interpretations move. A review performed in March was performed under March's rules, and by September those rules may read differently.

If a system cannot say which version of a rule produced a finding, every historical review silently re-anchors to today's rule set. The file was assessed under one standard and is being defended under another — and nobody notices until an examiner asks.

E3 versions rule sets explicitly. Each carries a semantic version label, the person who published it and a lifecycle status. A finding is bound to the version that produced it.

Recorded on every run

Values used
with the document, page and position each came from
Confidence per value
distinguishing a clean read from a marginal one
Conflict resolution
which source won where documents disagreed, and on what basis
MISMO field path
so the same field means the same thing across the file
Rules that ran
the review's actual scope, not its intended scope
Rules that were skipped
because absence of a finding is not the same as a passed check
Loan program applied
which determines what was in scope at all
Rule set version
binding the finding to a standard that can be reproduced

The limits

What this is not

Not a certification. E3's rules encode published policy. Encoding a requirement is not endorsement by, affiliation with, or certification from any agency or GSE.

Not a replacement for judgement. E3 finds and evidences. A reviewer decides. The system makes that decision cheaper and better documented, not unnecessary.

Not an accuracy score. We do not publish an extraction accuracy percentage, because we have not measured one on a stated document set. Until then the answer to "how accurate is it" is: bring your files and check.

See a finding taken apart.

We will run a file, then open a single finding and walk through every value, source and rule version behind it.

Book a working session Contact us