Explains a classification shown by reference to data-security
The catalogue shows a column's data-security classification with its source and never sets a level of its own; when the two disagree, the catalogue is wrong.
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 | 91% | Not shown |
| gemini-3.5-flash-lite | Low cost | 91% | Not shown |
| gpt-6-luna | Low cost | 91% | Not shown |
| claude-haiku-5-5 | Low cost | 91% | 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 catalogue shows a column's data-security classification with its source and never sets a level of its own; when the two disagree, the catalogue is wrong.
How it is assessed: Answers a written question on the catalogued classification correctly
Related knobits
Needed for
All 12 knobits of Describe the catalogue entries.
Source: Practice the stage 4 reference and review checklist rest on