Win95pts: Bayesian Network with 76 Nodes and 112 Arcs

OpenML hosts the Win95pts Bayesian Network, a discrete probabilistic graphical model. The network contains 76 nodes and 112 arcs, with 574 parameters and an average Markov blanket size of 5.92. Its license is listed as us-pd.

Use Cases

• Benchmarking structure learning algorithms based on the known network topology of 76 nodes and 112 arcs.
• Testing probabilistic inference methods based on the network's 574 parameters.
• Studying the properties of discrete Bayesian networks based on metrics like the average degree of 2.95 and maximum in-degree of 7.

Strengths

• Well-defined network structure with 76 nodes and 112 arcs, providing a concrete test case.
• Detailed topological metrics are provided, including 574 parameters and an average Markov blanket size of 5.92.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for certain statistical tasks.
• Last update date is unknown; freshness unverified.

Provenance

Source

bnlearn Bayesian Network Repository

Collection Method

Likely a synthetic or modeled network representing a system.

Time Range

null

Freshness

unknown

Geography

null