Explains traceability from data rule to check
Every check cites the rule or requirement it implements, and the check follows the rule's lifecycle.
Can AI do this?
AI does this well Most of the tested AI models master this. 10 of 10 models master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.1-pro-preview | Flagship | 100% | Mastered |
| gpt-6-astra | Flagship | 100% | Mastered |
| claude-fable-5-1 | Flagship | 100% | Mastered |
| 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 | 100% | Mastered |
| 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: Every check cites the rule or requirement it implements, and the check follows the rule's lifecycle
How it is assessed: Traces sample checks to their rules and finds the untraced ones
Related knobits
Needed for
- K-707 Recognises a check with no rule behind it
- K-708 Recognises a check outliving its rule
- K-710 Recognises a check on the wrong object
- K-711 Recognises a check weaker than its rule
- K-712 Recognises a check stronger than its rule
- K-719 Recognises duplicate checks for one rule
All 31 knobits of Derive data quality rules.
Source: Data-management practice used by the stage 7 reference and review checklist