Recognises an undocumented code value in use
A value observed that the documentation does not list.
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 | 66% | Not shown |
| gemini-3.5-flash-lite | Low cost | 67% | Not shown |
| gpt-6-luna | Low cost | 66% | Not shown |
| claude-haiku-5-5 | Low cost | 67% | 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 value, its count and the question for the owner
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: FP-002 LN_STAT observes RST (412 rows); documented: ACT, ARR, CLS Acceptable: RST documented by the owner (restructured)
Also known as: Undocumented code value in use
Related knobits
Builds on
All 13 knobits of Analyse and profile the sources.
Source: Review checklist 01-source-analysis, row 1 (DMBOK ch. 13; 25024 validity)