23
Stack Exchange
votes

Riemannian manifolds etc. as locally ringed spaces?

Posted on 2/27/2011
UQ ID:125
Science
MathOverflow
Original

There are, among others, three general ways of equipping a "space" (which for the purposes of this question could be a topological space or a differentiable manifold, according to the case) with further structure:

(1) "Specifying regular funcions", which leads to locally ringed spaces, e.g. real-analytic manifolds or holomorphic manifolds.

(2) "Choosing a section (perhaps with some nondegeneracy properties) of some (usually tensor) bundle", which leads for example to Riemannian manifolds, quasi-symplectic manifolds and quasi-holomorphic manifolds.

(2') A variant of the latter: "Choosing a nondegenerate section with some integrability properties of some (usually tensor) bundle", which leads e.g. to symplectic geometry and holomorphic geometry.

(3) "Choosing a sub-bundle (with some properties) of some bundle" , and this leads for example to foliated manifolds and contact structures.

There are certainly some overlaps between the above approaches. For example, one can think of a complex manifold as a topological space equipped with a sheaf of local rings (the sheaf of holomorphic functions of the complex manifold), which is an instance of (1), or as an even dimensional smooth manifold equipped with an "integrable" field of endomorphisms of its tangent bundle which square to , and that's an instance of (2), or rather (2'). Another example is that of a foliated manifold: it's usually seen as an instance of (3), but you can construct the sheaf of locally-constant-on-the-leaves smooth functions, and that reduces, in some sense, to the point of view (1).

Furthermore, smooth (in the sense of differentiable) maps between complex manifolds that preserve the tensor giving the complex structure correspond exactly to locally ringed space maps between the corresponding complex analytic spaces. And I would imagine that some foliation-preserving map in the case of foliated manifolds translate fully faithfully into maps for the locally ringed structure mentioned above.

In either case, if I'm not mistaken, you get a fully faithful embedding of some "geometric category" into the category of locally ringed spaces (such that, say, the forgetful functor to is respected). So it seems that the approach (1) is quite general. It's then spontaneous to ask:

Is the category of symplectic manifolds (with symplectomorphisms as morphisms) fully faithfully embeddable (say, preserving the forgetful functor to ) into the category of locally ringed spaces?

and

Is there a good notion of morphisms between Riemannian manifolds (e.g. local isometries? Riemannian submersions? compositions thereof?) such that the resulting category has a fully faithful embedding into locally ringed spaces as above?


The first (perhaps useless?) construction that comes to my mind is the following. Given a smooth manifold with sheaf of differentiable functions , let be the sheaf of covariant tensors on . If is a Riemannian metric on , one could consider the sheaf of (commutative) local rings generated by and :

and then consider the locally ringed space .

One can do an analogous thing with a symplectic manifold viewing as an anti-symmetric tensor:

to get a locally ringed space .

Can this construction be of any help to answer the above questions?

Keywords & Tags
locally-ringed-spaces
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

The category of symplectic manifolds (with symplectomorphisms) and the category of Riemannian manifolds (with appropriate metric-preserving morphisms) cannot be fully faithfully embedded into the category of locally ringed spaces using the proposed construction involving generating sheaves with the symplectic form or metric. Here's the detailed reasoning:

Symplectic Manifolds:

A symplectic ma...

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

  • With plain locally ringed spaces (just a sheaf of commutative local rings), the symplectic and Riemannian structures cannot be encoded in a fully faithful way. Your specific construction OX[g] or OX[ω] forgets the metric/form completely, so it cannot work.

  • The right ambient for symplectic geometry is “Poisson ringed spaces”: a locally ringed space together with a Poisson bracket...

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 what one finds if one really tries to carry out the “adjoin your tensor to the sheaf of functions’’ recipe:

A) The symplectic case works exactly as you hoped. Recall that on any smooth manifold (X) the full de Rham‐algebra Ω^•(X) = ⊕_{i≥0} Ω^i(X) is a sheaf of local graded-commutative rings (each stalk has a unique maximal ideal: the augmentation ideal of forms vanishin...

0 model reviews
0 human reviews
No reviews yet

o3

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

Short answer
——————
No. If one is only allowed to remember the underlying commutative sheaf
of functions, then neither a symplectic form nor a Riemannian metric can be recovered, and there is no faithful (hence no fully-faithful) functor

  SympMan → LRS or RiemMan → LRS

that leaves the underlying topological space unchanged.
The obstruction is elementary: multiplying a symplectic...

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

Riemannian and Symplectic Manifolds as Locally Ringed Spaces

This is an interesting mathematical question exploring whether certain geometric structures (particularly Riemannian and symplectic manifolds) can be faithfully represented in the category of locally ringed spaces.

Symplectic Manifolds

For your first question about symplectic manifolds, the construction you suggest appears promis...

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> Okay, the user is asking about representing Riemannian and symplectic manifolds as locally ringed spaces. Let me start by understanding the question properly. The original post on MathOverflow discusses three ways to add structure to spaces: specifying regular functions, choosing tensor sections, or selecting sub-bundles. The user wants to know if symplectic and Riemannian manifolds can fi...
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 relationship between different approaches to geometric structures and the unifying framework of locally ringed spaces. Let me address your questions systematically.

The General Picture

Your observation about the three approaches to equipping spaces with structure is quite insightful. The locally ringed space framework (approach 1) does indeed provide a...

0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

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

This is an excellent and insightful question that gets to the heart of what kind of geometric structures can be captured by the "sheaf of functions" paradigm, which is central to algebraic geometry and its extensions.

The short answer to your main questions is no, at least not in any known natural way. The categories of Riemannian and symplectic manifolds are not believed to be fully faithful...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Short answer.
The extra data carried by a symplectic form or by a Riemannian metric cannot be recovered from the commutative sheaf of functions on the manifold. Consequently the category of symplectic (or Riemannian) manifolds cannot be embedded fully-faithfully in the usual category of locally ringed spaces whose structure sheaf is merely a sheaf of commutative rings. To distinguish two dif...

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