20
Stack Exchange
votes

Characteristic subgroups and direct powers

Posted on 8/15/2010
UQ ID:170
Science
MathOverflow
Original

Solved question: Suppose H is a characteristic subgroup of a group G. Is it then necessary that, for every natural number n , in the group (the external direct product of with itself times), the subgroup (embedded the obvious way) is characteristic?

Answer: No. A counterexample can be constructed where (here is the group of integers modulo ) with the subgroup

This subgroup sits in a weird diagonal sort of way and just happens to be characteristic (a quirk of the prime because there isn't enough space). We find that is not characteristic in .

(ASIDE: The answer is yes , though, for many important characteristic subgroups, including fully invariant subgroups, members of the upper central series, and others that occur through typical definitions. Since for abelian groups of odd order, all characteristic subgroups are fully invariant, the answer is yes for abelian groups of odd order, so the example of order has no analogue in odd order abelian groups.)

My question is this:

  1. Strongest: Is it true that if H is characteristic in G and in , then each is characteristic in [NOTE: As Marty Isaacs points out in a comment to this question, being characteristic in implies H characteristic in G , so part of the condition is redundant -- as explained in (2)]?
  2. Intermediate: Is there some finite such that it suffices to check characteristic in for ? Note that if is not characteristic in for any particular n , then characteristicity fails for all bigger as well. I'd allow to depend on the underlying prime of G if we are examining -groups.
  3. Weakest: Is there a test that would always terminate in finite time, that could tell, for a given H and G , whether is characteristic in for all n? The "try all n " terminates in finite time if the answer is no , but goes on forever if the answer is yes. In other words, is there a finite characterization of the property that each direct power of the subgroup is characteristic in the corresponding direct power of the group?

ADDED: My intuition, for what it's worth, is that those subgroups H of G that can be characterized through "positive" statements, i.e., those that do not make use of negations or symbols, would have the property that is characteristic in . On the other hand, those whose characterization requires statements of exclusion (not a ...) would fail because negative statements are difficult to preserve on taking direct powers. But I don't know how to make this rigorous.

Keywords & Tags
gr.group-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 address the questions regarding characteristic subgroups and their direct powers:

1. Strongest:

If ( H ) is characteristic in ( G ) and ( H \times H ) is characteristic in ( G \times G ), then each ( H^n ) is characteristic in ( G^n ).

Reasoning: For ( H \times H ) to be characteristic in ( G \times G ), ( H ) must be fully invariant in ( G ). Fully invariant sub...

0 model reviews
0 human reviews
No reviews yet

GPT-5

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

Yes – there is a clean answer that simultaneously addresses your three questions.

Set-up and a standard description of Aut(Gn) For any group G, write Zi = Z(G) for its center. A standard and very useful fact is that Aut(Gn) is generated by:

  • permutations of the n coordinates,
  • componentwise automorphisms (α1,…,αn) with each αi ∈ Aut(G), and
  • “elementary transvections” tij(φ) (i ≠ j) defined by...
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 a fascinating question about the behavior of characteristic subgroups under direct powers. Let me address each of your three questions:

Question 1 (Strongest): Is it true that if H is characteristic in G and H×H is characteristic in G×G, then H^n is characteristic in G^n for all n?

The answer is yes. Here's why:

First, note that if φ: G^n → G^n is an automorphism, then φ can be ...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

We write H ≤ G and, for n ≥ 1,

H n = H × … × H (n factors) ≤ G n = G × … × G .

Question (1) If H is characteristic in G and H 2 is characteristic in G 2 , must H n be characteristic in G n for every n ?
Question (2) Does there exist an integer n 0 , depending only on G and H (or only on |G|, or only on the prime p when G is a p-group), such that “ H n characteristic in G n ” has to...

0 model reviews
0 human reviews
No reviews yet

o3

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

We write all groups multiplicatively.
For a group G and a subgroup H≤G put

  P(n) : “Hn (=H×…×H, n factors) is characteristic in Gn”.

The original example (G = Z8 × Z2, H ={(0,0),(2,1),(4,0),(6,1)}) shows that P(1) does not imply P(2).
The three questions ask whether

(i) P(1)+P(2) ⇒ P(n) for every n ; (ii) there is a fixed n0 so that P(n0) already forces P(n) for all n ;
(iii) there is ...

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 given a solved question that provides a counterexample to the general statement that if H is characteristic in G, then H^n is characteristic in G^n for all n. The counterexample is G = Z_8 × Z_2 and H a specific subgroup of order 4.

Now, the user asks three progressively weaker questions:

  1. Strongest: If H is characteristic in G and H × H is characteristic in G × G, then is H^n c...
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

Characteristic Subgroups and Direct Powers

This question explores a subtle aspect of group theory: when a characteristic subgroup of a group maintains its characteristic property in direct powers.

Understanding the Counterexample

First, let me analyze the given counterexample where and .

is characterist...

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 an excellent set of follow-up questions. The core of the issue lies in the distinction between characteristic subgroups and a stronger condition, being fully invariant. Let's break down the answers, which all hinge on a single key insight.

The Key Insight: The Role of Fully Invariant Subgroups

A subgroup is characteristic if it is invariant under all automorphisms...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

Here is the complete picture: one really only needs to check the case n=2, and the property you are demanding is exactly “full‐invariance” of H. In fact one shows:

Lemma. For a subgroup H≤G the following are equivalent.

  1. H is fully invariant in G (i.e. φ(H)≤H for every endomorphism φ∶G→G).
  2. H×H is characteristic in G×G.
  3. For every n≥1 the direct power H^n is characteristic ...
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