Recognises a check outliving its rule
A DQ rule citing a data rule that has been retired or rejected, or a requirement that was dropped. The check keeps enforcing a decision that was reversed.
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 | 81% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 100% | Mastered |
| gpt-6-astra* | Flagship | 100% | Mastered |
| claude-fable-5-1* | Flagship | 84% | Not shown |
| gemini-3.8-flash* | Mid tier | 100% | Mastered |
| gpt-6.1-sol* | Mid tier | 100% | Mastered |
| claude-sonnet-5-5* | Mid tier | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 50% | Not shown |
| gpt-6-luna | Low cost | 81% | Not shown |
| claude-haiku-5-5 | Low cost | 82% | 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 check and its re-pointing or retirement
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: BR-014: account status is one of OPN, DOR, CLS retired when the bank added BLK, superseded by BR-040; DQ-011 still cites BR-014 and fails every blocked account Acceptable: DQ-011 re-pointed to BR-040 and its expression updated, or status: retired with the same superseded_by (DQR-023)
Also known as: Check that outlives its rule (data quality rule)
Related knobits
Builds on
All 30 knobits of Derive data quality rules.
Source: Review checklist 03-dq-rules (data-quality), row 8; DMBOK2; this skill; formerly data-modelling K-708