Observability & Evaluation · Data artifact

Monitoring Reference Dataset

Data artifactObservability & EvaluationObservability & Evaluationarc:MonitoringReferenceDataset

A stable historical dataset representing known-good model performance and spanning normal variability, used as the baseline for production drift and quality comparisons.

Responsibility. Provides the baseline distribution against which production data is compared.

Also known as: Reference baseline dataset, Drift baseline

Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

Data Drift Detector Ref8.02

Design guidance

SHOULD use stable historical data that represents good performance and spans expected variability.

Classification

Patterns: Reference-baseline comparison
Quality attributes: Reliability (ISO/IEC 25010 | NIST AI RMF: valid and reliable)
Risks mitigated: False drift alerts from unrepresentative baselines

Sources

Ref8.02: "Machine Learning Monitoring in Production," unpublished reference note (02-ML-Monitoring-Production.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note