Graph

Graph exports retain payment and event identities while separating observable evidence from oracle-only campaign truth. PyTorch Geometric conversion is an optional dependency.

fraudtwin.GraphDataset	One immutable graph view and its structural descriptors.
fraudtwin.GraphNode	Versioned entity node in an observable or oracle graph view.
fraudtwin.GraphEdge	Time-bounded relationship with provenance back to source events.
fraudtwin.GraphCampaign	Oracle descriptor for one deterministic scenario instance.
fraudtwin.GraphEvidence	Normalized lineage for a derived relationship.
fraudtwin.GraphHyperedge	Optional higher-order campaign incidence record.
fraudtwin.GraphHyperedgeMembership	Membership of an entity in a higher-order graph relationship.
fraudtwin.build_graph	Build a deterministic temporal graph without generating source data.
fraudtwin.validate_graph	Validate IDs, temporal closure, and edge references for one graph view.
fraudtwin.validate_graph_scenarios	Validate campaign closure and higher-order incidence records.
fraudtwin.write_graph	Write one append-only graph artifact containing the requested views.
fraudtwin.to_pyg	Convert a graph to torch_geometric.data.HeteroData when installed.