Recognises a mapping ignoring a meaning change
One transformation across a cut-over the profile recorded.
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 | 83% | Not shown |
| gemini-3.5-flash-lite | Low cost | 38% | Not shown |
| gpt-6-luna | Low cost | 82% | Not shown |
| claude-haiku-5-5 | Low cost | 82% | 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 mapping split at the cut-over
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: MP-003 copies LN_RATE as is; it was a percentage before 2018 Acceptable: Split at the cut-over: divide by 100 before 2018-01-01
Also known as: Mapping ignoring a meaning change
Related knobits
Builds on
- N-152 Explains field semantics and their change over time
- N-251 Explains the source-to-target mapping contract
- N-1902 Explains a percent-to-fraction scale change of a field
- Q-1804 Explains the concept of a percentage
All 18 knobits of Map sources to targets.
Source: Review checklist 02-source-to-target-mapping, row 7 (DMBOK)