Published April 20, 2025 | Version 1.0

NMCA Original Blueprint (46 pages, April 20, 2025)

Authors/Creators

Description

This page documents the multimodal cognitive architecture I first published as the original 46-page NMCA blueprint on April 20, 2025.

A copy was sent to the USPTO as prior art. No patent was pursued.

I chose to release that version — and all subsequent versions — freely to the public.

I did this because the implications of proprietary, corporate-controlled systems built on visual thought / internal 3D simulation as a core of cognition are too large to leave exclusively in private hands.

The work is therefore placed in the public record so that the chronological priority and the original architectural claims remain visible.

The final specification is the 471-page NMCA blueprint published in 2026. Earlier versions remain preserved as separate historical records.

 

Publication Chronology

Date Publication Record
April 20, 2025 Original 46-page NMCA blueprint Zenodo DOI 10.5281/zenodo.21972901
2026 Expanded NMCA architecture Zenodo DOI 10.5281/zenodo.20212241
2026 NMCA Architectural Addendum Zenodo DOI 10.5281/zenodo.22352561
 
 

What was disclosed on April 20, 2025

  • Internal 3D Scene Builder used to simulate tasks visually and model interactions
  • Persistent internal visual/3D scene representation for reasoning
  • Memory encoding that stores visual scenes for future recall
  • Internal visual simulation synchronized with observation
  • Symbolic scene representations tied to memory and belief structures
  • Contradiction detection and belief updating
  • Planning inside the 3D spatial model
  • Simulation of routes and actions before execution
  • Feedback from real observation that triggers replanning
  • Multiple simulation branches
  • Explicit computational loop: Input → Internal Simulation → Action → Reflective Update
 
Concrete example given in the original disclosure:

An agent is told to get a banana from the refrigerator. It loads the refrigerator location from prior visual memory, internally simulates the full route and object interaction, executes the plan, discovers the refrigerator is empty, and generates a new subgoal.
 

Human thought can keep a scene. Current LLMs keep text and files. Those are not the same thing.

Thought requires a persistent, re-enterable internal space.

It is the first public specification of the same claim later expanded to the 128-module NMCA document:

This first version was publicly disclosed by Derek Van Derven on April 20, 2025. No earlier public document containing this same unified combination as a single architecture has been identified.

 

Site
https://visualthoughtagi.com

 

Demo
https://derekv123.itch.io/visual-thought-agi

 

---

 

Alternative Research Download Sites

 

OSF

Academia

 

---

 

Original 46-page blueprint IPFS CID


bafybeifjiyzm6tmk2jj27tjvbpqgdqpjm5loeon6y6ikxzeek3ff2vbdey

 

Original 46-page blueprint IPFS Download

 

---

 

Final 471-page blueprint IPFS CID

bafybeiedxfq5wsvuayjcxcxwmtto6ptelznkj6arb4mrscshwhcc2selfm

 

Final 471-page blueprint IPFS Download

 

---

Addendum to the 471-page blueprint CID

bafkreibse76prz3wypp3tcveczq4iuoifmk6sp5e73cbqiz2sry6b3hmvy

 

Addendum to the 471-page IPFS Download

 

---

 

Attribution of the 2026 NMCA

 

License: CC BY-NC-SA 4.0

Cite both DOIs, 2025 first

 

22352561 (addendum)

Companion to 20212241; cite 20212241 and 21972901

 

All derivatives must prominently cite:

 

“Neurosymbolic Multimodal Cognitive Architecture (NMCA) - by Derek Van Derven (2026).”

 

This requirement applies to derivatives of the 2026 work. Earlier publications may have different licensing terms; the license attached to the specific version should be consulted.

 

 

Files

Multimodal_Cognitive_System_Patent_April_20_2025.pdf

Files (1.3 MB)