Doug Lenat, the Cyc Project, and Permion Inc.

[John F Sowa]

Doug Lenat had presented a talk at the 2022 Ontology Summit before he died in 2023,  Over the years, he and I had interacted in many ways.  We had different methods and different goals, but we agreed on the fundamental issues.   

Since 2000, Arun Majumdar and I have been working on AI systems that put more emphasis on deriving knowledge from various sources rather than hand-coding the knowledge as in the Cyc project.  From 2000 to 2010, we developed symbolic methods for automatically deriving, encoding, and reasoning about knowledge in conceptual graphs.  For the current Permion Inc. company, the addition of LLM technology supports neurosymbolic methods for improved integration of natural language processing with the symbolic reasoning methods. 

Since Lenat can't speak at the current summit, I recommend his Wikipedia page for a summary of his work and references to his publications: https://en.wikipedia.org/wiki/Douglas_Lenat 

For a brief comparison about our different approaches, I asked Google:  How did Doug Lenat and John Sowa use ontology for artificial intelligence?

Reply by Google AI:  

Lenat’s primary contribution was the Cyc Project, started in 1984. His goal was to build a massive ontology of "common sense" knowledge—things a human knows but rarely says out loud, like "you can't be in two places at once". 

• Knowledge Representation: He developed CycL, a formal language based on predicate calculus, to hand-code millions of assertions and rules.
• The "Knowledge Pump": Lenat believed that once the system reached a "crossover point" of basic common sense, it could begin learning on its own by reading textbooks and reasoning through new information.
• Addressing Brittleness: By building a deep upper ontology (high-level concepts like space, time, and causality), he aimed to prevent AI from failing when faced with novel situations that lacked specific pre-programmed rules.

John Sowa focused on the formal structures and mathematical logic required to represent natural language semantics. 

• Conceptual Graphs (CGs): Sowa introduced Conceptual Graphs as a graphic notation for logic. These were designed to be both human-readable and computationally precise, serving as an intermediate language between natural language and machine-readable data.
• Interoperability: While Lenat focused on building one massive, unified knowledge base, Sowa championed a "lattice of theories"—a framework that could reconcile and map different, even inconsistent, ontologies to one another.
• Natural Language Processing (NLP): Sowa’s work emphasized using ontologies to capture the "implicit ontology" in human speech, allowing machines to map NL words and phrases directly to logical structures.

Key Comparison

Feature	Doug Lenat (Cyc)	John Sowa (Conceptual Graphs)
Primary Goal	Encoding "consensus reality" (common sense)	Representing natural language semantics
Method	Hand-coding millions of axioms in CycL	Using graphic notations for logic
Ontology Scope	Single, massive, unified knowledge base	A flexible net/lattice of multiple theories

Both researchers aimed to move AI from mere data processing to systems capable of reasoning and understanding, but they approached the problem from different, albeit complementary, angles within the symbolic AI paradigm.

Google's answer above emphasizes the relationships within the symbolic paradigm.  Since then the work at Permion combines the symbolic methods with LLMs to support neuro-symbolic methods.  I'll discuss the issues involved in that transition, and Arun will present examples that illustrate the methods and results.

In effect, the goals for Permion are similar to the goals for Cyc.  But instead of hand-coding the knowledge, we are using LLMs and various resources derived from the WWW to provide the massive amount of knowledge that Lenat had hoped to encode in Cyc.  For reasoning, Permion software uses neurosymbolic methods to derive conceptual graphs for symbolic reasoning with guaranteed precision -- no hallucinations or approximations.

John

[Dan Brickley]

Hi John,

Thanks for this. One point I am curious about,

Cyc and “Single, massive, unified knowledge base”

Whatever became of “microtheories”?

https://web.archive.org/web/19970630114849/http://www.cyc.com/tech-reports/cyc-050-92/cyc-050-92.html

That 1992 document doesn’t have a particularly compelling answer to the question of how to deal with conflicting answers from different levels of abstraction, but at least it engaged with the issue, unlike 

https://cyc.com/archives/glossary/microtheory/

The older material doesn’t sound so far from your “A flexible net/lattice of multiple theories”…

Best,

Dan

--
All contributions to this forum are covered by an open-source license.
For information about the wiki, the license, and how to subscribe or
unsubscribe to the forum, see http://ontologforum.org/info
---
You received this message because you are subscribed to the Google Groups "ontolog-forum" group.
To unsubscribe from this group and stop receiving emails from it, send an email to ontolog-foru...@googlegroups.com.
To view this discussion visit https://groups.google.com/d/msgid/ontolog-forum/19dadb6457fb40c8845297843abc985f%40d1d89cccad814b11b1deb40ea943d42b.

[Alex Shkotin]

Hi Dan,

My question is: do they take into account existing theories in science and technology?

Then one could say that microtheory is a small part of a substantive theory.

Best,

Alex

пт, 13 мар. 2026 г. в 12:24, 'Dan Brickley' via ontolog-forum <ontolo...@googlegroups.com>:

To view this discussion visit https://groups.google.com/d/msgid/ontolog-forum/CAFfrAFr47jxLvCa797-V2JiFM1EKnEwHzY0Mk%2Bq1h%2BV%2BK91kAQ%40mail.gmail.com.