Win95pts: A 76-Node Bayesian Network for Probabilistic Inference

76 nodes and 112 arcs define this discrete Bayesian network from the bnlearn repository. The network contains 574 parameters and has an average Markov blanket size of 5.92. It is a sample from the Win95pts model, used as a benchmark for probabilistic reasoning and structure learning algorithms.

Use Cases

• Benchmarking probabilistic inference algorithms based on the network's 76-node structure.
• Testing structure learning methods based on the 112 defined arcs and connectivity.
• Evaluating parameter estimation techniques based on the 574 parameters.
• Studying the properties of graphical models based on metrics like the average degree of 2.95.

Strengths

• Well-defined structure with 76 nodes and 112 arcs, providing a concrete test case.
• Network metrics are quantified, including 574 parameters and a maximum in-degree of 7.
• Sourced from the authoritative bnlearn Bayesian Network Repository.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and sample data are unavailable, which may limit suitability assessment.

Provenance

Source

bnlearn Bayesian Network Repository

Collection Method

Likely a synthetic or modeled network representing a system.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null