Explains the kinds of data change and their reach
Rename, type change, semantic change, removal and population change; a semantic change keeps name and type, passes every schema check and changes every number downstream.
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 | 90% | Not shown |
| gpt-6-luna | Low cost | 50% | Not shown |
| claude-haiku-5-5 | Low cost | 90% | 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: Rename, type change, semantic change, removal and population change; a semantic change keeps name and type, passes every schema check and changes every number downstream.
How it is assessed: Answers a written question on the data change type correctly
Related knobits
Builds on
Needed for
All 9 knobits of Analyse the impact of a change.
Source: Practice the stage 6 reference and review checklist rest on