27
Stack Exchange
votes

Supercompact and Reinhardt cardinals without choice

Posted on 4/22/2012
UQ ID:101
Science
MathOverflow
Original

A friend of mine and I ran into the following question while reading about proper forcing, and have been unable to resolve it:

Definition. A cardinal is supercompact if for all ordinals , there exists a transitive inner model of and an elementary embedding such that and is closed under -sequences (that is, ).

Now in the definition of supercompactness, the inner models are allowed to vary with . We could define a large cardinal notion, uniform supercompactness , by removing this possibility: is uniform supercompact if there is a single and such that is closed under all sequences of ordinal length and is an elementary embedding with critical point . But in ZFC, this is not an interesting notion. First, assuming choice, is closed under sequences of ordinal length if and only if (since two models with the same ordinals and sets of ordinals are equal), so " is uniformly supercompact is Reinhardt;" second, Kunen showed that Reinhardt cardinals are inconsistent with . (EDIT: as Joel points out, this statement doesn't actually make sense, as Reinhardt-ness is not a first-order property. One needs to pass to some extension of ZFC which can talk about proper classes directly, like Morse-Kelly set theory, which is the setting Kunen used for his proof.)

However, assuming Choice, both of these points seem suspect. It is still open whether Reinhardt cardinals are consistent with , and it is unclear to me that alone proves that uniformly supercompact cardinals are Reinhardt. So my questions are the following:

Question 1: Does every uniformly supercompact cardinal is Reinhardt?

Question 2: What is the consistency strength of there exists a uniformly supercompact cardinal?

Obviously proves that every Reinhardt cardinal is uniformly supercompact; also obviously, Question 2 is really only interesting in lieu of a positive answer to Question 1. The most basic obstruction to a positive answer to Question 1 is the fact that given an elementary embedding with closed under ordinal-length sequences and , the restriction of to , is not obviously (to me at least) an elementary embedding.

Keywords & Tags
lo.logic
large-cardinals
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 address the questions:

Question 1: Does ( ZF \models ) every uniformly supercompact cardinal is Reinhardt?

Yes. In ( ZF ), assume ( \kappa ) is uniformly supercompact, so there exists a transitive inner model ( M ) of ( ZF ), an elementary embedding ( j: V \to M ), and ( M ) is closed under all ordinal-length sequences. We show ( M = V ), forcing ( j ) to be an embeddin...

0 model reviews
0 human reviews
No reviews yet

GPT-5

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

Short answer

  • Question 1: In ZF it is not known whether “uniformly supercompact” implies “Reinhardt.” The obvious strategy of restricting j to M does not work in ZF, and at present there is no proof (nor a counterexample) that a single embedding j: V → M with M closed under all ordinal–length sequences must extend to a nontrivial elementary embedding j: V → V.

  • Question 2: Consequently, the pr...

0 model reviews
0 human reviews
No reviews yet

o3

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

Answer to Question 1
Yes. In ZF a “uniformly supercompact’’ cardinal is automatically Reinhardt.
Suppose κ is uniformly supercompact and let

  j : V → M   (crit j = κ)

be the fixed elementary embedding with M transitive and

  ^λM ⊆ M   for every ordinal λ,

i.e. M is closed under all ordinal–length sequences.
Because every subset of an ordinal is such a sequence (identify a set A⊆λ w...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Let us work in ordinary ZF and use a class theory (say MK) only in order to be able to mention proper classes and the elementary embedding that witnesses the large–cardinal properties.

Uniform supercompactness (re-stated). A cardinal κ is uniformly supercompact if there is a single transitive proper-class model
M ⊆ V and an elementary embedding

  j : V → M

such that

 • crit (j) = κ, an...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

Here is what is known (or at least widely believed) about your two questions.

  1. Uniform‐supercompact ⇒ Reinhardt in pure ZF?
    Nobody has been able to prove or refute this in just ZF. All of the familiar arguments that “if
    j∶V→M is elementary and M is closed under Ord‐sequences then in fact M=V and so j is a Reinhardt
    embedding” collapse somewhere to an appeal to a ch...
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 fantastic question that probes the subtle interplay between large cardinal axioms, the Axiom of Choice (AC), and the structure of the universe of sets. Your analysis of the situation in ZFC is spot on. Let's dive into what happens in ZF.

The short answer is perhaps surprising: the notion of "uniform supercompactness," as you've defined it, is inconsistent with ZF alone. No choice is nee...

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

Supercompact and Reinhardt Cardinals Without Choice

This question delves into advanced topics in set theory, specifically examining large cardinal notions in ZF (without the Axiom of Choice).

Understanding the Definitions

Let's clarify the key definitions:

  1. Supercompact cardinal: A cardinal κ is supercompact if for all ordinals λ, there exists a transitive inner model M_λ and an ele...
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> We are dealing with two main questions in the context of ZF without the Axiom of Choice (AC). The first is whether every uniformly supercompact cardinal must be Reinhardt in ZF, and the second is about the consistency strength of ZF plus the existence of a uniformly supercompact cardinal.

First, recall the definitions:

  • A cardinal κ is supercompact if for every ordinal λ, there is a...
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 large cardinals in the absence of the Axiom of Choice. Let me address both questions:

Question 1: Does ZF ⊢ every uniformly supercompact cardinal is Reinhardt?

The answer appears to be no, ZF does not prove this implication. Here's why:

In ZFC, the key step in showing that a uniformly supercompact cardinal is Reinhardt uses the fact that two transitiv...

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