Recognises a null counted as missing where the element does not apply
Completeness counting nulls on rows where the element does not apply.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 1 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 90% | Not shown |
| gemini-3.5-flash-lite | Low cost | 9% | Not shown |
| gpt-6-luna | Low cost | 10% | Not shown |
| claude-haiku-5-5 | Low cost | 90% | 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: Completeness over the applicable population
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: QM-001 maturity_date 91.0% complete; all 5,512 nulls are revolving credit lines (open-ended) Acceptable: Population: term loans only; completeness 100%
Also known as: Null read as missing where it means "not applicable"
Related knobits
Builds on
- K-655 Explains null semantics and three-valued logic
- Q-453 Explains ISO/IEC 25024 data quality measures
All 10 knobits of Profile and assess data quality.
Source: Review checklist 04-profiling-assessment, row 1 (25024 (completeness over the applicable population); DMBOK)