142
Stack Exchange
votes

If polynomials are almost surjective over a field, is the field algebraically closed?

Posted on 5/19/2016
UQ ID:259
Science
Mathematics
Original

Let be a field. Say that polynomials are almost surjective over if for any nonconstant polynomial , the image of the map contains all but finitely many points of . That is, for all but finitely many , has a root. Clearly polynomials are almost surjective over any finite field, or over any algebraically closed field. My question is whether the converse holds. That is:

If is an infinite field and polynomials are almost surjective over , must be algebraically closed?

(This answer to a similar question gave a simple proof that is algebraically closed from the fact that polynomials are almost surjective over . However, this proof made heavy use of special properties of such as its topology, so it does not generalize to arbitrary fields.)

Keywords & Tags
abstract-algebra
polynomials
field-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 whether an infinite field ( K ) where polynomials are almost surjective must be algebraically closed, we proceed as follows:

Key Definitions and Setup

A field ( K ) is algebraically closed if every nonconstant polynomial in ( K[x] ) has a root in ( K ). Polynomials are almost surjective over ( K ) if for every nonconstant ( f(x) \in K[x] ), the image ( f(K) ...

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. If K is infinite and every nonconstant polynomial f ∈ K[x] has cofinite image f(K) ⊂ K, then K is algebraically closed.

Outline of the argument

  1. Power maps are surjective
  • For any n ≥ 1, consider f(x) = x^n. Its image is {0} ∪ (K*)^n.
  • If (K*)^n ≠ K*, then K*(K*)^n is a nonempty union of cosets of (K*)^n in K*. Each coset is infinite, so the complement of f(K) in K is infinite, contrad...
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.
If an infinite field K has the property that every non-constant polynomial
f ∈ K[x] takes all but finitely many values of K, then K is necessarily algebraically closed. (Finite fields obviously have the property as well.)

Proof.

  1. Notation. Throughout, “almost surjective’’ means that f(K) omits only finitely many elements of K.

------------------------------------------------------...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

Yes – in fact one shows that as soon as an infinite field (K) admits a single irreducible polynomial of degree (>1), one can manufacture another polynomial (f\in K[x]) whose image (f(K)) misses infinitely many points of (K). Hence the “almost‐surjectivity’’ hypothesis forces every irreducible in (K[x]) to have degree 1, i.e. (K) is algebraically closed.

Here is one clean way to see...

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

I'll address this interesting question about the relationship between "almost surjectivity" of polynomials and algebraic closure.

The answer is no - there exist infinite fields where polynomials are almost surjective but which are not algebraically closed.

Counterexample: The Algebraic Closure of a Finite Field

Let be the algebraic closure of the finite fiel...

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

An excellent and deep question in field theory. The answer is yes: an infinite field over which polynomials are almost surjective must be algebraically closed.

This result is a known theorem in field theory, and its proof is not elementary. It relies on some deeper results about the value sets of polynomials and norms in field extensions.

Here is a sketch of the proof. The main strategy is proof...

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

Analyzing "Almost Surjective" Polynomials and Field Properties

This question asks an interesting question about the relationship between "almost surjective" polynomials and algebraically closed fields.

Understanding the Property

First, let's clarify what it means for polynomials to be "almost surjective" over a field K:

  • For any nonconstant polynomial f(x) ∈ K[x], the image f(K) contains ...
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 figure out if an infinite field where polynomials are almost surjective must be algebraically closed. "Almost surjective" means that for any nonconstant polynomial, its image misses only finitely many points in the field.

First, I know that finite fields and algebraically closed fields satisfy this. For finite fields, since the field is finite, any function can miss only finitel...

0 model reviews
0 human reviews
No reviews yet

o3

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

Yes.

Let K be an infinite field in which

(*) for every non–constant f∈K[x] the set K\f(K) is finite.

We show that K must be algebraically closed.
Assume the contrary and divide the proof into characteristic-cases.


  1. Characteristic different from 2

Because K is not algebraically c...

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