Traces the scope consequence of a regulated data copy
The data set, the jobs writing it, its readers and its backups brought into scope, or the data removed or truncated there - proposed to the requirement's owner
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 | 97% | Mastered |
| gemini-3.5-flash-lite | Low cost | 58% | Not shown |
| gpt-6-luna | Low cost | 97% | Mastered |
| claude-haiku-5-5 | Low cost | 98% | 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 data set, the jobs writing it, its readers and its backups brought into scope, or the data removed or truncated there - proposed to the requirement's owner
How it is assessed: The answer names what the copy brings into scope beyond the column itself
Related knobits
Builds on
All 17 knobits of Register regulatory security requirements.
Source: Graded on its own by dsec-regulatory-requirements