Recognises a check failure with no capable owner
A check with no owner, or an owner who cannot fix the cause — a team name for a mailbox nobody reads, the data platform team for a defect in the source system's entry screen. The alert fires and everybody assumes someone else saw it.
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 | 82% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 25% | Not shown |
| gpt-6-astra* | Flagship | 99% | Mastered |
| claude-fable-5-1* | Flagship | 99% | Mastered |
| gemini-3.8-flash* | Mid tier | 99% | Mastered |
| gpt-6.1-sol* | Mid tier | 99% | Mastered |
| claude-sonnet-5-5* | Mid tier | 26% | Not shown |
| gemini-3.5-flash-lite | Low cost | 58% | Not shown |
| gpt-6-luna | Low cost | 58% | 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 owner able to fix the cause
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: owner: absent; the check has failed every night for four months Acceptable: owner: "Payments data steward", the person who can get the source corrected, named in the rule (DQR-027)
Also known as: Failure nobody owns (data quality rule)
Related knobits
Builds on
All 30 knobits of Derive data quality rules.
Source: Review checklist 03-dq-rules (data-quality), row 23; Loshin 2011; DMBOK2; formerly data-modelling K-723