Package-level declarations
Types
How two entities in a SemanticLink came to be connected.
LLM-backed RationaleProjector that turns a proposition (or group) into human-readable rationale prose grounded in the source propositions.
A human-readable rationale derived from one or more propositions.
Produces a human-readable rationale explaining why a proposition (or a group of related propositions) is believed and how the supporting evidence connects.
What the LLM sends back: the generated rationale prose and its self-reported confidence.
A structured, deterministic aggregation of a set of propositions.
Aggregates a set of propositions into a structured Report.
The human-review lifecycle of a discovered SemanticLink.
A reviewable indirect link between two entities, discovered structurally from the propositions that ground it.
Discovers indirect SemanticLinks between entities from a set of propositions.
Pure-structural, deterministic ReportProjector.
A deterministic, structural SemanticLinkDiscoverer that surfaces two-hop indirect links.