Bongard Problem
Updated 2026-08-02
INTRODUCTION
English translation pending.
CORE DEFINITION
Introduced by the Russian computer scientist Mikhail Bongard, each problem shows six figures on the left and six on the right, with a rule that holds for one group and fails for the other. Human solvers usually find the rule quickly, while pattern-matching systems struggle because the relevant distinction is abstract and often depends on context. The puzzles became a benchmark for testing concept learning rather than statistical fitting.
SCAFFOLDING EFFECT
Reduce cognitive load
- Test abstraction: ask what single rule explains the whole split rather than fitting individual examples - Generate and discard: propose several candidate rules and check each against every figure - Judge real understanding: treat the ability to find the rule as a test of comprehension, not recall
Anchor fast decisions
The rule is not attached to any single figure, so memorizing features does not help. A solver must form hypotheses, apply them to all twelve cases, and revise when one case contradicts. That loop of proposing and testing is what separates genuine concept formation from surface pattern matching.
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/Bongard_problemverified
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