18
Stack Exchange
votes

Čech functions and the axiom of choice

Posted on 5/20/2020
UQ ID:197
Science
MathOverflow
Original

A Čech closure function on is a function such that (i) for all , (ii) , and (iii) for all ; in other words, it obeys the Kuratowski closure axioms except possibly the idempotent law .

In 1947 E. Čech asked if there exists such a closure function (on any set, not necessarily ) which is also surjective and nontrivial (not the identity map). Čech's question has been answered in the affirmative under various set-theoretic assumptions, including ZFC. The ZFC example is rather complicated and makes heavy use of the axiom of choice; it seems unlikely that one could construct such a thing without choice.

Question. Is it consistent with ZF that there is no nontrivial surjective Čech closure function ?

That is, there is no function satisfying the conditions (i)-(iii) above and also (iv) for every there exists such that , and (v) for some . (Condition (ii) is now redundant, as it follows from (i) and (iv) that if is finite.)

Keywords & Tags
gn.general-topology
set-theory
axiom-of-choice
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 it is consistent with ZF that there is no nontrivial surjective Čech closure function on ω, we analyze the properties of such functions. A Čech closure function φ must satisfy: (i) X ⊆ φ(X) for all X ⊆ ω; (iii) φ(X ∪ Y) = φ(X) ∪ φ(Y); and be surjective (iv) and nontrivial (v).

Key Observations:

  1. Finite Sets Are Fixed: For any finite X, φ(X) must equal X. This follows be...
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. In fact it is consistent with ZF that there is no nontrivial surjective Čech closure function on P(ω).

Here is a way to see why. Work in a model of ZF in which there is a countable family of pairs of reals with no choice function. Such models are standard; for example, in the basic Cohen–Halpern–Levy symmetric model (obtained by the usual symmetric submodel of adding countably many Cohen rea...

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

Analysis of Čech Functions and the Axiom of Choice

To determine whether it's consistent with ZF (without the Axiom of Choice) that no nontrivial surjective Čech closure function exists on , I'll analyze the constraints such a function must satisfy.

Understanding the Problem

A Čech closure function must satisfy:

  1. $X ...
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 interesting question about the relationship between Čech closure functions and the axiom of choice. Let me analyze what we're looking for and discuss the consistency question.

First, let's clarify what we need: a function that satisfies:

  1. for all (extensivity)
  2. $\varphi(\emptyset) =...
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 tackle this question about Čech closure functions and the axiom of choice. The question is whether it's consistent with ZF (without choice) that there is no nontrivial surjective Čech closure function on the power set of ω.

First, recall that a Čech closure function satisfies three properties:

(i) ( X \subseteq \varphi(X) ) for all ( X \subseteq \omega )

(ii) ( \varphi(\e...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

All of the “hard” examples of non‐trivial surjective Čech‐closure‐operators that one finds in the literature live in ZFC and, indeed, use the axiom of choice in a crucial way. No one has ever exhibited a model of ZF + ¬AC in which one can prove that every Čech‐closure‐map [ \varphi!: \mathcal P(\omega)\to\mathcal P(\omega) ] which satisfies

  1. (X\subseteq\varphi(X)),
  2. (\varphi(...
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

This is a fascinating question that lies at the intersection of general topology, set theory, and descriptive set theory. The answer to your question is yes, it is consistent with ZF that there is no nontrivial surjective Čech closure function on .

The proof of this consistency result relies on showing that the existence of such a function is impossible in certain models ...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Yes. One can build a model of ZF in which every Čech‐type closure operator on P(ω) is the identity, so that in particular there is no non–trivial surjective one. A convenient way to obtain such a model is to use the classical Fraenkel–Mostowski (permutation-) technique.

  1. A quick reminder of Čech closure operators

A map φ : P(ω) → P(ω) is a Čech closure operator iff

(1) X ⊆ φ(X) (...

0 model reviews
0 human reviews
No reviews yet

o3

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

No additional set–theoretic assumptions are needed – ZF itself already proves that a non–trivial surjective Čech closure function on ω exists. Hence there is no model of ZF in which every Čech closure function on ω is either the identity or non-surjective.

Construction of a Čech closure function in ZF

Write σ(n)=n+1 and for X⊆ω put
 σ[X]={σ(n)...

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