873
Stack Exchange
votes

A proof of without prime ideals?

Posted on 4/11/2013
UQ ID:256
Science
Mathematics
Original

Background. If is a commutative ring, it is easy to prove , where denotes the Krull dimension. If is Noetherian, we have equality. Every proof of this fact I'm aware of uses quite a bit of commutative algebra and non-trivial theorems such as Krull's intersection theorem. It is worth mentioning that Gelfand-Kirillov dimension satisfies for every -algebra . T. Coquand and H. Lombardi have found a surprisingly elementary, first-order characterization of the Krull dimension that does not use prime ideals at all.

T. Coquand, H. Lombardi, A Short Proof for the Krull Dimension of a Polynomial Ring, The American Mathematical Monthly, Vol. 112, No. 9 (Nov., 2005), pp. 826-829 (4 pages)

You can read the article here. Here is a summary. For let denote the localization of at the multiplicative subset . Then we have It follows that for we have if and only if for all there are and such that You can use this to define the Krull dimension. This new characterization of can be seen as a statement in first-order logic (whereas the usual definition with prime ideals uses second-order logic): Use two sorts , the usual ring operations for , but also the "mixed" operation , . Every ring becomes a model of this language. A consequence of this is a new short proof of , where is a field. Using Noether normalization and the fact that integral extensions don't change the dimension, it follows that if are finitely generated commutative -algebras. In particular . This could be useful for introductory courses on algebraic geometry which don't want to waste too much time with dimension theory.

Question. Can we use the characterization \eqref{1} of the Krull dimension by Coquand-Lombardi to prove the formula for Noetherian commutative rings ?

Such a proof should not use the prime ideal characterization/definition of the Krull dimension. Notice that the claim is equivalent to for all . I suspect that this can only work if we find a first-order property of commutative rings (with powers) which is satisfied in particular by Noetherian rings and prove the formula for these rings. Please read this first before answering. This question is only concerned with a proof of the dimension formula using the Coquand-Lombardi characterization. If you post an answer that doesn't mention the characterization, then it's not an answer to my question and therefore offtopic. As of writing this, 20 answers have been posted, all of which have been deleted.

Keywords & Tags
ring-theory
commutative-algebra
noetherian
krull-dimension
dimension-theory-algebra
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 prove that for a Noetherian commutative ring ( R ), the Krull dimension of the polynomial ring ( R[T] ) satisfies ( \dim(R[T]) = \dim(R) + 1 ) using the Coquand-Lombardi characterization, we proceed as follows:

Key Background: Coquand-Lombardi Characterization

The Krull dimension of a ring ( R ) is defined via a first-order condition: ( \dim(R) \leq k ) if and only if for every s...

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, the Coquand–Lombardi characterization is tailor‑made for this. One proves directly, without mentioning prime ideals, that for every polynomial f ∈ R[T] the “analytic” localization Bf := (R[T]){f} = localization of R[T] at fℕ · (1 + f·R[T]) has Krull dimension (in the Coquand–Lombardi sense) at most that of R. Then the identity dim(R[T]) = supf∈R[T](dim((R[T]){f}) + 1) from Coquand–Lo...

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

Proving Using the Coquand-Lombardi Characterization

This is an interesting question about using the Coquand-Lombardi first-order characterization of Krull dimension to prove a fundamental result in dimension theory without resorting to prime ideals.

Let me work through a proof based on the Coquand-Lombardi characterization.

Background

For a commutative ring ,...

0 model reviews
0 human reviews
No reviews yet

o3

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

Throughout the proof we use only the Coquand–Lombardi characterisation

     dim A ≤ k  ⇔  (∀x0 ,…, xk ∈ A) (∃a0 ,…, ak , m0 ,…, mk )
                   x0m0 ( …( xkmk ( 1+ak xk)+ …)+ a0 x0)=0                 (CLk)

and the elementary facts which were established in their paper:

(i) localisation does not increase the dimension;
(ii) if S is integral over A then dim S = dim A ;
(i...

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 the Coquand-Lombardi characterization of the Krull dimension: for a commutative ring R, dim(R) = sup_{x ∈ R} ( dim(R_{ {x} }) + 1 ), where R_{ {x} } is the localization at the multiplicative set x^N (1 + xR).

We want to prove that for a Noetherian commutative ring R, dim(R[T]) = dim(R) + 1, using only this characterization and without using prime ideals.

Since R is Noetheria...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

Below is a sketch of how one shows

dim R[T] = dim R + 1

purely in the Coquand–Lombardi (C–L) language (no prime‐ideals anywhere), under the hypothesis that R is Noetherian. Recall that in C–L one sets

dim A = sup_{x∈A} ( dim A_{ {x} } +1 )  (∗)

and one shows equivalently that “dim A≤k” if and only if for every k+1 elements x₀,…,x_k of A there are aᵢ∈A and mᵢ∈ℕ...

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 finding a proof of the dimension formula for Noetherian rings using the Coquand-Lombardi characterization.

Let me outline the key challenges and potential approaches:

The Challenge

The Coquand-Lombardi characterization states that:

where is the localization at $x^{...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Below I give a completely “prime–free’’ proof – i.e. a proof that only uses the Coquand–Lombardi first–order description of Krull dimension – of

    dim ( R[T] ) = dim ( R ) + 1        (∗)

for every Noetherian commutative ring R. Nothing that follows mentions prime ideals, maximal ideals, chains of prime ideals, Krull’s intersection theorem …; everything is done inside the language

  ...
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. You are asking for a proof of for a commutative Noetherian ring that uses the Coquand-Lombardi (C-L) characterization of Krull dimension and avoids the language of prime ideals.

You've correctly identified the main steps and the core of the problem:

  1. The inequality is elementary. Given a chain of primes $\mathfrak{p}_0...
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