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?
AI does this well Most of the tested AI models master this. 7 of 10 models master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| 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 | 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: 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 31 knobits of Derive data quality rules.
Source: Review checklist 07-dq-rules, row 13; DAMA UK 2013; Olson 2003