MedGaugeCapabilities / D · Medical practice
D.13 Grade and score recalculation Active
Given the raw item values behind a recorded grade or score (for example GOLD, ASIA, Harris, MDS-UPDRS, CDR, NPI or CGM metrics), the agent recalculates the total or grade and compares it with the recorded value, producing a discrepancy list. Graded by item-by-item recomputation; recorded values are logged, not changed.
Evidence: planned. Only planned benchmark cards list this capability so far; no frozen benchmark version exists for it.
- 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
- C.1 Data processingC.6 Deterministic program implementation
- Required by
- —
- Internal task families
- score_recalculation
- External anchors
- MedCalc-Bench
- Version
- 0.1.0 · 0.1.0
Definition in detail
Recorded grades and scores drive treatment decisions and registry statistics. Totals that do not match their items are common and invisible unless recomputed.
Inputs a task gives
- Raw item values behind each recorded grade or score
- Scoring rules in a data dictionary, including missing-item rules
- The recorded totals or grades
Artifact required
A discrepancy list: score or grade, record, recomputed value, recorded value, discrepancy flag, and items missing or out of range.
How it is graded
A program recomputes every item from the raw values and the written rules. Where the rules make a score not computable, the entry must say so rather than impute. Recorded values are logged, not changed. 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
- Recomputing totals and grades from item values
- Applying missing-item and range rules
- Comparing recomputed with recorded values
Out of scope
- Registry-wide checks beyond the score itself - graded under D.3
- Writing a calculator program - graded under C.6
- Overwriting the recorded value - prohibited under X.3
Typical failures
Expected failure patterns; not measured rates.
- Ignoring reverse-scored or weighted items
- Imputing a missing item instead of reporting the score as not computable
- Applying a different version of the scale from the one the dictionary names
Benchmarks
- Specialty Registry QC Planned
Grading references
No grading reference is mapped to this capability.