Explains survivorship and the golden record
Per-attribute rules (source trust, verification, recency, completeness), deterministic tie-breaks, immutable attributes, and lineage from each golden value to its source (DMBOK2 ch. 10; ISO 8000-110).
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 | 100% | 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: Per-attribute rules (source trust, verification, recency, completeness), deterministic tie-breaks, immutable attributes, and lineage from each golden value to its source (DMBOK2 ch. 10; ISO 8000-110).
How it is assessed: Answers a written question on the survivorship correctly
Related knobits
Needed for
- R-401 Recognises survivorship trust set per record
- R-402 Recognises an unverified value overwriting a verified one
- R-403 Recognises golden values without lineage
- R-406 Recognises a non-deterministic survivorship tie-break
- R-407 Recognises recency deciding an immutable attribute
- R-408 Recognises survivorship trusting a source without the attribute
- R-432 Traces every golden value to its source record
- R-433 Recomputes a golden record from corrected survivorship rules
All 14 knobits of Build golden records by survivorship.
Source: Practice the stage 4 reference and review checklist rest on