Systems
At N=13, Context Graph yields up to 91 structured signals per input as a constructive upper bound pending mutual-information audit.
Figure 1.Context Graph is the text-side DDA witness: N=13, up to 91 signals per input as a constructive upper bound.
The figure represents Context Graph as a text-side DDA witness with 13 frozen embedders. The direct projections contribute 13 signals per input and the pairwise interactions contribute up to 78 more, for up to 91 structured signals per input as a constructive upper bound pending mutual-information audit.
Context Graph embeds stored text through 13 frozen embedders and persists the panel output into durable storage.
The DDA count at N=13 is up to 91 structured signals per input as a constructive upper bound: 13 direct projections plus 78 pairwise interactions.
The research claim is not that the product UI is impressive. The relevant evidence is that panel outputs, topic profiles, and retrieval records are stored and can be independently inspected.
The videos explain the system in public talk-track form while this page keeps the count qualified.
00:11:34 / oHLZggLYgBI
Text-side production witness showing the 13-embedder panel used for memory, retrieval, and DDA signals.
Counts are system-at-date figures; the up to 91 signal count is a constructive upper bound pending mutual-information audit.
Open video page00:08:10 / ke9cyFbFYWM
Technical walkthrough for the 13-embedder memory architecture and single-GPU operating posture.
Open video page00:11:34 / oHLZggLYgBI
Text-side production witness showing the 13-embedder panel used for memory, retrieval, and DDA signals.
Counts are system-at-date figures; the up to 91 signal count is a constructive upper bound pending mutual-information audit.
00:08:10 / ke9cyFbFYWM
Technical walkthrough for the 13-embedder memory architecture and single-GPU operating posture.