Explains managing reference values over time
Each value with code, label, definition, effective dates and status; owners and versions; retire rather than delete; never overwrite a code's meaning (ISO/IEC 11179-3; ISO 8000-115).
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 99% | Not shown |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | Mastered |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: Each value with code, label, definition, effective dates and status; owners and versions; retire rather than delete; never overwrite a code's meaning (ISO/IEC 11179-3; ISO 8000-115).
How it is assessed: Answers a written question on the reference value lifecycle correctly
Related knobits
Needed for
- R-203 Recognises reference values with no effective dates
- R-204 Recognises a retired code still issued
- R-205 Recognises a code reused with a new meaning
- R-206 Recognises a reference value with no definition
- R-207 Recognises a reference data set with no owner
- R-231 Splits a reused code by effective date
- R-506 Recognises a reference data change without effective dates
All 17 knobits of Manage the reference data sets.
Source: Practice the stage 2 reference and review checklist rest on