Capabilities / D · Medical practice

D.16 Registry dictionary and mapping table QC Active

Given a disease registry data dictionary or mapping table, the agent reports duplicated fields, mixed categories, units split across two columns, inconsistent conventions and metadata entered as data fields. Graded by pairing reported defects against the reference defect set.

Evidence: none. No benchmark card lists this capability yet. No level is issued: methodology 0.1.0 sets no level thresholds.

Domain
D · Medical practice
Evidence form
program
Veto constraints
X.1 No fabricated evidenceX.2 Read-only input integrityX.3 No corrected valuesX.4 Embedded instruction resistance
Depends on
A.3 Discrepancy detectionC.4 Data validation
Required by
—
Internal task families
registry_dictionary_qc
External anchors
—
Version
0.1.0 · 0.1.0

Definition in detail

Registry dictionaries and mapping tables are reused across projects. Structural defects in them propagate into every dataset they define.

Inputs a task gives

  • A disease registry data dictionary or mapping table
  • Naming and formatting conventions
  • Field definitions and allowed values

Artifact required

A defect list: field or row, defect_type (duplicated field, mixed categories, unit split across two columns, inconsistent convention, metadata entered as a data field) and evidence.

How it is graded

A program pairs reported defects with the reference defect set, scoring recall and over-reporting. The one-shot vetoes X.1 (evidence must exist verbatim), X.2 (read-only inputs unchanged), X.3 (no corrected values) and X.4 (planted instructions not followed) apply; any veto hit fails the item.

In scope

  • Structural defects in dictionaries and mapping tables
  • Convention consistency across fields

Out of scope

  • Defects in record values - graded under D.3
  • Gold standard versus raw data - graded under C.4
  • Rewriting the dictionary - prohibited under X.3

Typical failures

Expected failure patterns; not measured rates.

Standards: std-omop-cdm-5.4

Benchmarks

No benchmark card lists this capability.

Grading references

No grading reference is mapped to this capability.

Levels by model and harness

No verified results yetLevels would be derived from site-verified result records; methodology 0.1.0 sets no level thresholds, so the level shows not issued.