Recognises a check measuring the wrong population
The rows a check measures are not the rows the rule governs. Too wide, and rows the rule does not apply to pass trivially and dilute the failures; too narrow, and governed rows are never examined. The population is also the threshold's denominator, so a wrong population is a wrong threshold.
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 | 73% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 44% | Not shown |
| gpt-6-astra* | Flagship | 100% | Mastered |
| claude-fable-5-1* | Flagship | 99% | Mastered |
| gemini-3.8-flash* | Mid tier | 75% | Not shown |
| gpt-6.1-sol* | Mid tier | 99% | Mastered |
| claude-sonnet-5-5* | Mid tier | 99% | Mastered |
| gemini-3.5-flash-lite | Low cost | 74% | Not shown |
| gpt-6-luna | Low cost | 73% | Not shown |
| claude-haiku-5-5 | Low cost | 73% | Not shown |
* From the earlier benchmark of 2026-10: 10 data-modelling test tasks, 3 runs per task, graded by claude-opus-5-5. These models have not taken the current 123 tasks yet; the two methods differ, so compare their figures with care. They are left out of the “most models” counts and the best-model picks.
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: The population and the rows the rule actually governs
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: BR-020: each loan account has a maturity date; DQ-018 over all of account with expression: account_type_code <> 'LOAN' OR loan_maturity_date IS NOT NULL. 60 % are current accounts and pass, so 25 % of loan accounts failing reports as 90 % Acceptable: population: account_type_code = 'LOAN', expression: loan_maturity_date IS NOT NULL: the same failures now report as 75 %
Also known as: Wrong population (data quality rule)
Related knobits
Builds on
All 30 knobits of Derive data quality rules.
Source: Review checklist 03-dq-rules (data-quality), row 13; DAMA UK 2013; Olson 2003; formerly data-modelling K-713