Recognises a data quality issue severity set by the reporter
A rating justified by who raised it or how often, not by the policy's impact levels.
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 91% | Mastered |
| gemini-3.5-flash-lite | Low cost | 10% | Not shown |
| gpt-6-luna | Low cost | 90% | Mastered |
| 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: The severity from the policy's impact levels
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: IS-003 employer "-" critical: "raised four times by Credit Risk"; impact: affordability notes incomplete Acceptable: medium (operational); IS-001 (NPL misstated) is the critical one
Also known as: Severity set by the reporter, not the impact
Related knobits
Builds on
All 9 knobits of Manage data quality issues.
Source: Review checklist 06-issue-management, row 1 (DMBOK §2.6)