Explains crosswalks and their cardinality
Mappings between code sets: 1:1, N:1, 1:N, N:M read from the pairs; only 1:1 reverses; every active source code mapped.
Can AI do this?
AI does this well Most of the tested AI models master this. 4 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 98% | Mastered |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | 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: Mappings between code sets: 1:1, N:1, 1:N, N:M read from the pairs; only 1:1 reverses; every active source code mapped.
How it is assessed: Answers a written question on the crosswalks correctly
Related knobits
Builds on
Needed for
- R-202 Recognises a crosswalk not 1:1 treated as 1:1
- R-209 Recognises a crosswalk missing source values
- R-232 Restricts a many-to-one crosswalk to forward use
All 17 knobits of Manage the reference data sets.
Source: Practice the stage 2 reference and review checklist rest on