Skilirium

Recognises content filed under the wrong requirement

K-114 · Skill knobit · Activity: Capture data requirements · Competence: Data modelling

A rule, note or value in the source belongs to a different requirement than the one it is filed under. Typical in spreadsheets where rows were inserted or sorted.

Can AI do this?

AI does this partly Some of the tested AI models master this; others do not show it. 3 of 10 models master it.

ModelTierProbability of masteryStatus
gemini-4-argonFlagship 100%Mastered
gemini-3.1-pro-previewFlagship 32%Not shown
gpt-6-astraFlagship 100%Mastered
claude-fable-5-1Flagship 84%Not shown
gemini-3.8-flashMid tier 37%Not shown
gpt-6.1-solMid tier 37%Not shown
claude-sonnet-5-5Mid tier 36%Not shown
gemini-3.5-flash-liteLow cost 30%Not shown
gpt-6-lunaLow cost 37%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 content and the requirement it belongs to

How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: Spreadsheet row Account type carries the rule "Must be a valid ISO 4217 code", which is about Account currency in the next row Acceptable: The ISO 4217 rule moved to the Account currency requirement; Account type gets its own candidate rule (its value comes from the product catalogue) or none.

Also known as: Content attached to the wrong requirement (data requirement)

Related knobits

Builds on

All 47 knobits of Capture data requirements.

Source: Review checklist 01-requirements, row 14; 29148 5.2.5 (correct)