Universal law of generalization¶

Shepard's cognitive hypothesis that generalization probability decreases approximately exponentially with distance between stimuli in an appropriately constructed psychological space.

Version: v1 · 2026-09-08 · History
Domain-specific #: 7356
Origin domain: cognitive psychology
Subdomain: stimulus generalization

Core Idea¶

The universal law of generalization proposes a monotonic, characteristically exponential decline in response transfer as psychological distance between a trained and test stimulus increases. Experience and evolutionary pressure organize stimuli in a similarity space; uncertainty about consequence regions makes nearby points more likely than distant points to share the learned consequence. The abstraction is therefore identified by a declared carrier, a transformation or constraint over that carrier, and an invariant that tells an analyst whether the named structure is genuinely present.

Scope of Application¶

Universal law of generalization belongs to cognitive psychology and is useful where the analyst can specify stimuli, learned responses or consequences, an empirically fitted psychological space and metric, pairwise distances, generalization probabilities, task context, organisms, and observations, then evaluate distance is defined in a task-relevant psychological representation and generalization probability is evaluated as a function of that distance rather than raw physical difference alone. The scope is broad within that domain but bounded by the need for distance is defined in a task-relevant psychological representation and generalization probability is evaluated as a function of that distance rather than raw physical difference alone. The entry records a descriptive analytical identity; practical use requires the governing domain's evidence, standards, and safety obligations.

Clarity¶

The abstraction clarifies a crowded vocabulary by making distance is defined in a task-relevant psychological representation and generalization probability is evaluated as a function of that distance rather than raw physical difference alone the center of the account. A claim should name the carrier, the governing operation or relation, the applicable assumptions, and the recognition test. A bare label is insufficient because the name Universal law of generalization can be used for a formal identity, an implementation, or a neighboring result unless carrier and convention are stated.

Manages Complexity¶

Without the abstraction, an analyst must reason directly over many local details: the carrier roles, admissibility assumptions, competing conventions, derived invariants, boundary cases, and proof or validation obligations specific to Universal law of generalization. Universal law of generalization compresses them into the roles in the structural signature. That compression permits comparison across instances without erasing the variables that determine validity. It also exposes which details may be varied safely and which are constitutive.

Abstract Reasoning¶

Identify the carrier. State what the elements, states, objects, or observations are: stimuli, learned responses or consequences, an empirically fitted psychological space and metric, pairwise distances, generalization probabilities, task context, organisms, and observations. Reject examples whose alleged carrier belongs to a different problem. 2. Lock the constitutive rule. Express distance is defined in a task-relevant psychological representation and generalization probability is evaluated as a function of that distance rather than raw physical difference alone independently of one notation or implementation.

Knowledge Transfer¶

Knowledge transfers strongly among subfields of cognitive psychology because they reuse stimuli, learned responses or consequences, an empirically fitted psychological space and metric, pairwise distances, generalization probabilities, task context, organisms, and observations, Experience and evolutionary pressure organize stimuli in a similarity space; uncertainty about consequence regions makes nearby points more likely than distant points to share the learned consequence., and type the carrier, state every parameter and convention in the definition, test that distance is defined in a task-relevant psychological representation and generalization probability is evaluated as a function of that distance rather than raw physical difference alone, compare the nearest accepted identity, and report counterexamples, uncertainty, and limiting cases.

Relationships to Other Abstractions¶

Current abstraction Universal law of generalization Domain-specific

Parents (1) — more general patterns this builds on

Universal law of generalization is a kind of Learning Prime

The proposed strict upward parent is prime:learning.

Hierarchy paths (2) — routes to 2 parentless roots

Universal law of generalization → Learning → Adaptation

Show alternative path (1)

Neighborhood in Abstraction Space¶

Universal law of generalization sits in a moderately populated region (49^th percentile for distinctiveness): it has near-neighbors but no dense thicket of look-alikes.

Family — Magnitude, Timing & Numerical Cognition (5 abstractions)

Nearest neighbors

Computed from structural-signature embeddings · 2026-09-08