Recognises a critical data element chosen above element level
A table, report or system chosen instead of an element.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 74% | Not shown |
| gemini-3.5-flash-lite | Low cost | 18% | Not shown |
| gpt-6-luna | Low cost | 73% | Not shown |
| claude-haiku-5-5 | Low cost | 74% | Not shown |
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: One CDE per column the uses read
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: CD-007 element: PT-010 (the loan table) Acceptable: The loan columns the returns read, one CDE each
Also known as: CDE at the wrong level
Related knobits
Builds on
All 10 knobits of Select the critical data elements.
Source: Review checklist 01-cdes, row 4 (DMBOK §2.2)