Causal Structural Priors

Menu path: Hellixia > Causal Structural Priors

What it does

Elicits proposed causal directions, explanations, and structural priors for use in learning workflows.

Treat Hellixia output as a structured starting point for analyst review, expert refinement, learning, inference, or communication. Generated causal directions and quantification should be checked before they are used operationally.

When to use it

• Constrained structure learning
• Causal orientation review
• Expert prior elicitation

Inputs

• Selected arcs or nodes
• Optional General Context

Outputs

• Structural priors
• Causal direction explanations
• Review material

Step-by-Step Workflow

1. Prepare the network, source material, selected nodes, selected arcs, or Knowledge Files required by the function.
2. Confirm that Hellixia provider settings and model access are configured.
3. Open Hellixia > Causal Structural Priors.
4. Review the available options and add General Context when the model needs domain-specific guidance.
5. Run the function and inspect the generated graph, comments, priors, embeddings, translations, or images.
6. Edit the output in BayesiaLab before using it for analysis, publication, or decision support.

Review Guidance

Check whether the generated labels, relationships, comments, classes, probabilities, or causal effects match the source material and expert understanding. For causal outputs, verify that the proposed direction and mechanism are plausible and that no important confounder or alternative explanation has been hidden by the generated structure.

Related Functions

• Causal Relationship Finder
• Pairwise Causal Link
• Root Priors Elicitor

Examples

• Causality — Causal Semantic Diagram, Causal Bayesian Network, or Risk-Centric Causal Network