Skilirium

Recognises a check outliving its rule

K-708 · Skill knobit · Activity: Derive data quality rules · Competence: Data modelling

A DQ rule citing a data rule that has been retired or rejected, or a requirement that was dropped. The check keeps enforcing a decision that was reversed.

Can AI do this?

AI does this well Most of the tested AI models master this. 8 of 10 models master it.

ModelTierProbability of masteryStatus
gemini-4-argonFlagship 100%Mastered
gemini-3.1-pro-previewFlagship 100%Mastered
gpt-6-astraFlagship 100%Mastered
claude-fable-5-1Flagship 84%Not shown
gemini-3.8-flashMid tier 100%Mastered
gpt-6.1-solMid tier 100%Mastered
claude-sonnet-5-5Mid tier 100%Mastered
gemini-3.5-flash-liteLow cost 100%Mastered
gpt-6-lunaLow cost 83%Not shown
claude-haiku-5-5Low 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: The check and its re-pointing or retirement

How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: BR-014: account status is one of OPN, DOR, CLS retired when the bank added BLK, superseded by BR-040; DQ-011 still cites BR-014 and fails every blocked account Acceptable: DQ-011 re-pointed to BR-040 and its expression updated, or status: retired with the same superseded_by (DQR-023)

Also known as: Check that outlives its rule (data quality rule)

Related knobits

Builds on

All 31 knobits of Derive data quality rules.

Source: Review checklist 07-dq-rules, row 8; DMBOK2; this skill