Domain 5 · Lesson 3 · Context & Reliability (15%)

Human Review, Confidence & Provenance

Task Statements 5.5 & 5.6 — calibrating who reviews what, and not losing the sources.

Course progress: Domain 5 ▸ lesson 3 of ~3

Human review & confidence calibration (5.5)

Aggregate metrics lie "97% overall accuracy" can mask poor performance on a specific document type or field. Before automating high-confidence extractions, segment accuracy by document type and field — a great average can hide a 60%-accurate segment.

Note the contrast with Domain 5.2: self-reported confidence for escalation is unreliable, but field-level confidence calibrated against labeled data is a legitimate routing signal for extraction review. Calibration against ground truth is the difference.

Provenance & uncertainty in synthesis (5.6)

Preserve claim→source mappings Attribution is lost when findings are summarized without preserving the claim-source mapping. Require subagents to output structured mappings (source URL, doc name, relevant excerpt) that downstream agents preserve and merge through synthesis — don't compress them away.

Check yourself

Your extraction system reports 97% aggregate accuracy and you want to reduce human review. Before automating, you should:
Correct: option 2. Aggregate accuracy can hide a poorly-performing segment; analyze by document type and field first. Automating on the average (1) risks that hidden segment; a uniform threshold (3) ignores segmentation; self-reported confidence (4) isn't calibrated.
Two credible sources report different statistics for the same metric. The synthesis output should:
Correct: option 3. Preserve both with attribution rather than arbitrarily selecting or averaging; also check publication dates in case it's a temporal difference, not a true contradiction. Dropping the data loses real information.
Decision rules Before automating → segment accuracy by type+field (aggregate hides gaps). Route review → field-level confidence calibrated on labeled data + stratified sampling. Synthesis → preserve claim-source mappings; conflicts annotated w/ attribution; dates for temporal data; render by content type.
Ask your teacher. Ready for the Domain 5 quiz, then the final mixed practice exam. Ask if the calibrated-vs-self-reported confidence distinction is fuzzy — it's a favorite trap.