Ugly Duckling Theorem
Version 1.0.0 · Updated 2026-07-28
CORE DEFINITION
The ugly duckling theorem shows that, for finitely many objects, counting all extensional properties obtainable through logical combinations equally gives different object pairs the same number of shared properties. Discriminating classifications therefore require selecting or weighting properties. Inductive bias here means modeling assumptions, not necessarily personal prejudice or values.
SCAFFOLDING EFFECT
Reduce cognitive load
Make features, weights, and task objectives explicit, then test sensitivity to those choices. The theorem does not establish that every classification is arbitrary or that data and domain knowledge cannot support a classification.
Anchor fast decisions
Treating every subset of a finite set of distinguishable objects as an equally counted extensional predicate creates symmetry across all distinct pairs. It cannot favor one pair. Feature selection or nonuniform weighting breaks that symmetry and permits discriminating similarity judgments.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Ugly_duckling_theoremverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS