Recognises a broken lineage hop
An edge to or from an object that is not catalogued, so the path breaks.
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 | 83% | Not shown |
| gemini-3.5-flash-lite | Low cost | 83% | Not shown |
| gpt-6-luna | Low cost | 83% | Not shown |
| claude-haiku-5-5 | Low cost | 83% | 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 edge and the catalogued object it should point at
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: LG-004 from CE-014; staging column is CE-011 Acceptable: from: CE-011
Also known as: Broken hop
Related knobits
Builds on
All 11 knobits of Trace column-level lineage.
Source: Review checklist 05-lineage, row 1 (BCBS 239 P3; DMBOK)