20
Stack Exchange
votes

Etale fundamental group of a curve in characteristic

Posted on 11/9/2014
UQ ID:167
Science
MathOverflow
Original

Let be a connected, smooth, proper curve of genus over an algebraically closed field of characteristic . Let be the etale fundamental group of - I only care about this as an abstract profinite group, so I omit base points.

It is well known by Grothendieck that is topologically generated by elements. Formally, there is a surjection , where the first group is the profinite completion of the free group on elements. Moreover, if we let be the prime-to- quotient of , then where I.e., you get what you expect from the characteristic 0 case.

Recall that the prime-to-p quotient is the quotient , where is the intersection of the kernels of all the maps from to finite prime-to- groups.

Question: Is there any case of a curve of genus at least 2 for which its etale fundamental group is known?

I phrase the question in this way because the Etale fundamental group does depend on the curve in question. In fact, even its abelianization will depend on the -rank of the Jacobian.

Keywords & Tags
ag.algebraic-geometry
fundamental-group
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

In characteristic ( p > 0 ), the étale fundamental group of a smooth proper curve ( C ) of genus ( g \geq 2 ) is not known explicitly for any specific curve. While the prime-to-( p ) quotient ( \pi_1(C)^{(p)} ) is well-understood—being the profinite completion of the free group on ( 2g ) generators modulo the product of commutators ( w = \prod_{i=1}^g [x_i, y_i] )—the full étale fund...

0 model reviews
0 human reviews
No reviews yet

GPT-5

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

Short answer: No. For a smooth proper curve C/k of genus g ≥ 2 over an algebraically closed field of characteristic p > 0, there is currently no nontrivial example for which the full geometric étale fundamental group π1(C) has been determined as an abstract profinite group.

What is known

  • Prime-to-p part: For every ℓ ≠ p, the maximal pro-ℓ quotient is the pro-ℓ completion of the topological surf...
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 smooth, proper, connected curve C of genus g over an algebraically closed field k of characteristic p>0. We are interested in the étale fundamental group of C, denoted π₁(C), as an abstract profinite group.

It is known that π₁(C) is topologically generated by 2g elements, meaning there is a continuous surjection from the profinite completion of the free group on 2g generato...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

No – at the moment not a single smooth, proper, geometrically connected curve of genus ≥ 2 over an algebraically closed field of characteristic p > 0 is known for which the whole étale fundamental group has been determined.

What is known.

  1. Genus 0: π₁(ℙ¹)=1 (the only finite étale covers of ℙ¹ are the trivial ones by the Riemann–Hurwitz formula).

  2. Genus 1: For any abelian variety A (in...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

Aside from the genus 0 and genus 1 cases, one really does ​not​ know any non‐trivial proper curve of genus ≥2 in char p whose ​full​ étale fundamental group is written down explicitly. In fact what one does know is:

  1. By Grothendieck (SGA 1) the prime‐to‐p quotient π₁(C)^{(p′)}
    is exactly what you expect from characteristic 0, namely the profinite completion of the standard genus g ...
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 question that gets to the heart of some deep results in anabelian geometry and the arithmetic of curves in positive characteristic.

The short answer is: **Yes, the étale fundamental group is known for supersingular curves. For all other curves, its structure is known "in principle" but depends on a single, highly non-trivial relation that is generally not explicitly computabl...

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

The étale fundamental group of curves in characteristic is indeed a subtle and difficult topic. While we don't have complete descriptions for most curves of genus ≥ 2, there are some partial results and special cases where we know more.

Known Results and Special Cases

1. Structure of the Fundamental Group

The étale fundamental group sits in a short exact sequence:

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

Étale Fundamental Group of a Curve in Characteristic p

The étale fundamental group of a curve in positive characteristic is significantly more complex than in characteristic 0, primarily due to wild ramification. While a complete description for arbitrary curves of genus ≥ 2 remains challenging, there are some specific cases where substantial information is known:

Known Cases for Genus ≥ 2 ...

0 model reviews
0 human reviews
No reviews yet

o3

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

Let k be an algebraically closed field of characteristic p>0 and let
π₁(C)=π₁^{ét}(C) be the étale fundamental group of a smooth, proper, geometrically connected curve C/k of genus g.
With “known’’ we understand “described by an explicit presentation (generators and relations) as an abstract profinite group’’.

What is known in every characteristic

(1) The prime–to–p quotient
π₁(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