Cognition · Software component

Coreset Exemplar Pre-selector

Software componentCognitionCognition & Memoryarc:CoresetExemplarPreselector

An exemplar selector that pre-selects a compact core subset of highly informative demonstrations, keeping examples that are sufficient to solve tasks and discarding redundant ones.

Responsibility. Prunes the demonstration pool to an informative core subset.

Also known as: Demonstration pre-selection

Variant of Exemplar Selector abstract

When to choose. Choose when the demonstration pool is large or noisy and a compact core subset satisfying sufficiency and necessity is needed.

Direct neighbourhood (hover for relationship types)

Relationships

writes dependency

Prompt Exemplar Set Ch3.5

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Pre-selection reduced demonstration dataset size by ~50% while maintaining or improving performance (Ch3.5).

Classification

Patterns: Sufficiency-and-necessity demonstration pre-selection
Technologies: FEEDER
Quality attributes: Performance efficiency (ISO/IEC 25010)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)

Sources

Ch3.5: T. Nguyen, "Prompt Optimization, Few-Shot Learning, Fine-Tuning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.5. ISBN: 9798244538229.