A temporal context graph is a time-aware map of sources, entities, claims, signals, briefs, streams, and stable identifiers that lets AI systems reason with fresh context instead of isolated chunks.
Context changes, so edges carry observed windows, recency, and freshness state.
People, organizations, places, topics, data tags, and sources are stable graph nodes.
Atomic claims and derived signals make the graph explainable without exposing raw retrieval.
Public panels expose enough aggregate shape for citation while keeping item-level retrieval in Synorb.
The source, stream, and tag pages on HC are public examples of this definition: static aggregate panels with JSON twins for citation. Detailed retrieval and delivery live in Synorb.