92
Stack Exchange
votes

Complete, Finitely Axiomatizable, Theory with 3 Countable Models

Posted on 8/29/2014
UQ ID:264
Science
Mathematics
Original

Does there exist a complete, finitely axiomatizable, first-order theory with exactly 3 countable non-isomorphic models? A few relevant comments: There is a classical example of a complete theory with exacly models. This theory is not finitely axiomatizable (For the trivial reason that the language is infinite). In this post, Javier Moreno explains how to rephrase this example in a finite language. Still, the theory is not finitely axiomatizable. Some less relevant comments: I would like to know if finite axiomability has ever be asked in this context. There have been research in connection with stability. Lachlan has proved that a superstable theory with finitely many countable models is -categorical. And it is still open if this can be extended to all stable theories.

Keywords & Tags
logic
model-theory
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

To determine if there exists a complete, finitely axiomatizable first-order theory ( T ) with exactly 3 countable non-isomorphic models, we can rely on key results in model theory, specifically the Engeler-Sacks-Procopescu theorem.

Key Theorem:

The Engeler-Sacks-Procopescu theorem states that a complete, finitely axiomatizable first-order theory ( T ) is either ω-categorical (i.e., h...

0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Yes. A very classical way to get exactly three nonisomorphic countable models (the Ehrenfeucht phenomenon) can be carried out in a finite language, and in fact by a single first-order sentence.

Here is one explicit construction.

Language

  • One binary relation symbol < (intended as a linear order).
  • One unary function symbol f (intended as an order automorphism).

Axioms (a finite list)

  • < is a...
0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Complete, Finitely Axiomatizable Theory with Exactly 3 Countable Models

This is an interesting question at the intersection of model theory, finite axiomatizability, and Vaught's conjecture. Let me provide what's known about this situation:

Short Answer

No such theory exists. A complete, finitely axiomatizable first-order theory cannot have exactly 3 countable models up to isomorphism. ...

0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

This is an excellent question about the intersection of finite axiomatizability and the spectrum problem in model theory.

Answer: No, such a theory cannot exist.

Here's why:

Theorem (Ryll-Nardzewski): A complete theory in a countable language is -categorical (has exactly one countable model up to isomorphism) if and only if for each , there are only finitely many -type...

0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

No such example is known at present, and it is not known whether one can exist.
In fact the problem is open already for the weaker requirement “finite language’’ – nobody has yet produced a complete theory in a finite language that has a finite number > 1 of non-isomorphic countable models, and nobody has been able to prove that such a theory is impossible.

Background

  1. Let I(T,ℵ₀) be the n...
0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

No. In fact, all of the “classical’’ constructions of complete theories with exactly three (or, more generally, finitely many >1) countable models use an infinite axiom‐schema (or an infinite language) and one does not know how to collapse them to a single finite axiom in a finite relational language. To this day no one has produced a complete, finitely axiomatizable first‐order T with exactly t...

0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> I need to determine if there exists a complete, finitely axiomatizable, first-order theory with exactly three countable non-isomorphic models. The question mentions that there's a classical example with exactly three models, but it's not finitely axiomatizable because it uses an infinite language. Javier Moreno showed how to do it in a finite language, but still not finitely axiomatizable....
0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

Failed UQ Validation
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

Excellent question. This delves into a classical and very important part of model theory concerning the number of countable models of a theory.

The answer to your question is no, such a theory does not exist.

The key result that resolves this is a cornerstone of model theory related to Vaught's Conjecture.

The Main Theorem

A complete, finitely axiomatizable theory in a countable first-...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Nobody knows.

More precisely, the following two questions are still open.

  1. Does there exist a complete first–order theory in a countable language that has a finite number > 1 of countable, pairwise non-isomorphic models (in particular, 2 or 3)?
  2. Does there exist such a theory that can in addition be axiomatized by finitely many sentences (equivalently, by a single sentence)?

Your questi...

0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer