Recognises stale control evidence
last_seen older than the control's frequency allows: the control has stopped running, or nobody looks.
Can AI do this?
Not settled yet The benchmark tested this, but the models' answers do not settle yet whether they master it. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 90% | Not shown |
| gemini-3.5-flash-lite | Low cost | 38% | Not shown |
| gpt-6-luna | Low cost | 35% | Not shown |
| claude-haiku-5-5 | Low cost | 88% | Not shown |
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 control, the evidence and the lapse
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: CT-009 annual, EV-009 last_seen: 2024-03-15 Acceptable: last_seen within the last period, or a finding that the control lapsed
Also known as: Stale evidence
Related knobits
Builds on
All 21 knobits of Map BCBS 239 to controls.
Source: Review checklist 04-regulatory-mapping, row 5 (DCAM; ECB)