Skilirium

Recognises contradicting data rules

K-301 · Skill knobit · Activity: Document data rules as SBVR fact types and rule statements · Competence: Data modelling

Two rules on one fact type cannot both hold. Almost always a missing condition: one rule applies to a subtype and nobody wrote that down.

Can AI do this?

AI does this well Most of the tested AI models master this. 7 of 10 models master it.

ModelTierProbability of masteryStatus
gemini-4-argonFlagship 100%Mastered
gemini-3.1-pro-previewFlagship 84%Not shown
gpt-6-astraFlagship 100%Mastered
claude-fable-5-1Flagship 100%Mastered
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 30%Not shown
gpt-6-lunaLow cost 34%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 rule pair and the missing condition

How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: BR-1: each account has exactly one interest rate and BR-2: it is prohibited that an account has an interest rate Acceptable: BR-1: each savings account has exactly one interest rate; BR-2: it is prohibited that a current account has an interest rate — the condition is in the rule, not in somebody's memory (ANO-001)

Also known as: Contradiction (data rule)

Related knobits

Builds on

Usually followed by

All 28 knobits of Document data rules as SBVR fact types and rule statements.

Source: Review checklist 03-data-rules, row 1