Skip to content

Latest commit

 

History

History
33 lines (23 loc) · 1.84 KB

File metadata and controls

33 lines (23 loc) · 1.84 KB

Extraction eval report

Fixture set: extraction. Generated by reconcile eval-extraction. This file is committed and regenerated when the extractor or the labeled fixtures change. The fixtures are deterministic synthetic intake forms with hand-written ground-truth labels; there is no real personal data in them.

What is measured

Field-level precision and recall of the offline PDF extractor. A predicted field is correct when its field name and normalized value match a labeled field in the same document, using the same normalizers the matching pipeline applies, so formatting differences do not count as errors. Unmatched predictions are false positives; unmatched labels are false negatives. This is a REVIEW metric in the metrics ledger, read by a person, and a test also holds the committed fixture at or above the ledger targets so the numbers cannot drift silently.

Results

Metric Value 95% CI
Documents 4
Labeled fields (ground truth) 17
Predicted fields 16
Precision 100.0% (16/16) [80.6%, 100.0%]
Recall 94.1% (16/17) [73.0%, 99.0%]

Per-field breakdown

Field TP FP FN Precision Recall
dob 2 0 1 100.0% 66.7%
email 3 0 0 100.0% 100.0%
first_name 4 0 0 100.0% 100.0%
last_name 4 0 0 100.0% 100.0%
phone 3 0 0 100.0% 100.0%

Targets

Ledger targets: precision at least 95.0%, recall at least 90.0%. Observed: precision 100.0%, recall 94.1%. MET.

False negatives (1 here) are shown, not hidden: the fixture set deliberately includes at least one field the deterministic extractor is known not to parse (see the fixture README), so the measurement demonstrably catches a real miss rather than scoring a set the extractor is guaranteed to ace.