Conformal Invariants, Weyl Tensor

Patrick Reany

10 November 2025

Note: This chat I had with Copilot is likely edited for relevance and brevity. I often do not take the time to highlight all the words that Copilot highlights. Further, in the interest of being didactic, I might arbitrarily highlight an occasional word or phrase that Copilot did not. (Naturally, I get to correct my spelling, grammar, and other minor errors for free.)

I report as faithfully as I can what LLMs tell me, but I can't guarantee that they are correct on every factual matter. If the subject should touch on physical or mental self-care, regard the content merely for information sake, rather than medical advice.

Patrick:
I'm caught between two internally warring intuitions about the "curvature" of a sphere, which goes as $1/r^2$. If I let the radius of a sphere resting on the floor go to zero, while my dimensions stay the same, then the curvature blows up. But another part of my brain asks, "Why isn't the curvature of a sphere scale invariant?" Well, if my dimensions shrink in the same proportion as the shrinkage of the sphere, then why should the "curvature" of the shrunken sphere seem to blow up with respect to me?

Copilot:
This is a beautifully phrased tension, Patrick---between the absolute and the relative, the intrinsic and the extrinsic, the geometric and the perceptual. Let's unpack it with care.

The Geometry of Curvature

For a 2-sphere of radius \( r \), the Gaussian curvature is: \[ K = \frac{1}{r^2} \] This is an intrinsic quantity: it depends only on the surface itself, not on how it's embedded in space. It tells us how the surface bends internally, and it's what governs things like triangle angle sums and geodesic deviation.

So yes, as \( r \to 0 \), \( K \to \infty \). The sphere becomes "infinitely curved" in the sense that its surface is tightly wrapped, and geodesics diverge rapidly.

Scale and Perception: Why Curvature Feels Relative

Your second intuition is also valid---and deeply insightful. You're asking: If I shrink along with the sphere, why does the curvature seem to change? Shouldn't it feel the same to me?

This is a question about scale invariance, and it hinges on what we mean by "curvature blowing up."

• If you shrink your own measuring stick proportionally with the sphere, then your experience of the geometry remains unchanged.
• That is, if you live on a sphere of radius \( r \), and your body and tools scale with \( r \), then the curvature feels the same. Triangles still have angle sums > 180°, circles still have smaller circumference-to-radius ratios, etc.

So the dimensionless experience of curvature is scale invariant. What changes is the absolute value of curvature in units external to the sphere.

Reconciling the Two Intuitions

You're toggling between two reference frames:

This is the same kind of duality that shows up in relativity: the geometry of spacetime is invariant, but the coordinates and measurements depend on the observer.

Bonus Analogy: The Ant on the Balloon

Imagine an ant living on a balloon. As the balloon inflates, the curvature decreases. But if the ant also grows proportionally, it never notices the change. Its world feels the same. The curvature is blowing up only from the perspective of an external observer with a fixed ruler.

Would you like to explore how this plays out in general relativity or in the context of moduli spaces? There's a rich analogy waiting there.

Patrick:
Is there a next-best-thing to a "curvature" that is scale invariant, or is that intellectual space vacant?

Copilot:
Yes, there are scale-invariant geometric quantities that serve as "next-best-things" to curvature---especially in contexts like conformal geometry, Ricci flow, and moduli theory. These quantities often encode curvature relative to scale, rather than in absolute terms.

Let's explore a few of the most compelling candidates:

1. Conformal Invariants: Geometry up to scale

In conformal geometry, we study properties preserved under angle-preserving (but not necessarily length-preserving) transformations. Here, curvature is not scale-invariant, but certain combinations of curvature and scale are.

• Weyl curvature tensor (in dimension ≥ 4): Measures the conformal part of the Riemann tensor. It's invariant under rescaling of the metric by a smooth positive function.
• Q-curvature (in even dimensions): A scalar curvature-like quantity that transforms predictably under conformal changes. It plays a role in prescribing curvature in conformal classes.

These are like "curvature modulo scale"---they capture how geometry bends relative to its own scale.

2. Ricci Flow and Scale-Invariant Estimates

In Ricci flow, the metric evolves according to: \[ \frac{\partial g_{ij}}{\partial t} = -2 \, \text{Ric}_{ij} \] While curvature itself is not scale-invariant, certain estimates and monotonic quantities are:

• Perelman's entropy functionals (like the \( \mathcal{W} \)-functional) are scale-invariant and control the geometry under Ricci flow.
• Recent work (e.g. [Man-Chun Lee, 2025](https://arxiv.org/abs/2503.20292)) proves uniqueness of Ricci flow under scaling-invariant curvature bounds, showing that the flow respects certain normalized curvature conditions even when the raw curvature diverges.

These functionals act like "renormalized curvature energies" that remain meaningful across scales.

3. Dimensionless Ratios and Moduli

In moduli theory and geometric analysis, we often care about dimensionless quantities:

• Isoperimetric ratios, shape parameters, or spectral invariants (like eigenvalue ratios of the Laplacian) are scale-invariant and encode geometric information.
• In 2D, the moduli space of Riemann surfaces classifies conformal structures up to scale. The curvature of the underlying metric may vary wildly, but the conformal class is what matters.

So in a sense, moduli spaces are the natural home of scale-invariant geometry.

Philosophical Synthesis

Your question touches a deep epistemic divide:

• Curvature is a local, absolute measure.
• Scale-invariant quantities are relational, comparative, and often global or functional.

They don't replace curvature---but they contextualize it, offering a kind of "renormalized geometry" that survives rescaling.

Would you like to co-design a flowchart or schema that maps these curvature-like quantities across different geometries (Riemannian, conformal, moduli-theoretic)? It could be a powerful tool for your modular framework work.

Patrick:
Can you provide an example of the Weyl curvature tensor (in dimension ≥ 4) measuring the conformal part of the Riemann tensor?

Copilot:
Absolutely. The Weyl curvature tensor \( C_{ijkl} \) is the part of the Riemann curvature tensor that remains after subtracting out the parts determined by the Ricci tensor and scalar curvature. It encodes the conformal geometry of a manifold---how angles and shapes are distorted, independent of scale.

Definition in Dimension \( n \geq 4 \)

Let \( (M^n, g) \) be a Riemannian manifold of dimension \( n \geq 4 \). The Weyl tensor is defined by: \[ C_{ijkl} = R_{ijkl} - \frac{1}{n-2} \left( g_{ik} R_{jl} - g_{il} R_{jk} + g_{jl} R_{ik} - g_{jk} R_{il} \right) + \frac{R}{(n-1)(n-2)} \left( g_{ik} g_{jl} - g_{il} g_{jk} \right) \] Where:

• \( R_{ijkl} \) is the Riemann curvature tensor
• \( R_{ij} \) is the Ricci tensor
• \( R \) is the scalar curvature
• \( g_{ij} \) is the metric tensor

This decomposition isolates the part of curvature that is invariant under conformal rescaling of the metric: \( g \mapsto \Omega^2 g \).

Interpretation

• The Weyl tensor vanishes if and only if the manifold is conformally flat.
• It captures how curvature behaves under angle-preserving transformations, ignoring scale.
• In general relativity, it governs tidal forces and gravitational radiation in vacuum regions (where Ricci vanishes).

Example: Schwarzschild Spacetime

In 4D Lorentzian geometry, the Schwarzschild metric (outside a spherical mass) has zero Ricci tensor but nonzero Weyl tensor. This means:

• No local matter (Ricci = 0)
• But curvature still exists due to the mass---encoded entirely in the Weyl tensor.

So the Weyl tensor carries the "free gravitational field" information.

Would you like to see a symbolic computation of the Weyl tensor for a specific metric (e.g., Schwarzschild, FLRW, or a warped product)? We could visualize how conformal distortion behaves across different geometries.

Patrick:
Yes, I'd like to see it for the Schwarzschild.

Copilot:
In the Schwarzschild spacetime, the Weyl curvature tensor is nonzero and fully encodes the tidal gravitational effects in vacuum, since the Ricci tensor vanishes. This makes it a perfect example of curvature that is purely conformal in nature.

Schwarzschild Metric Overview

The Schwarzschild metric describes the spacetime outside a spherically symmetric, non-rotating mass \( M \). In Schwarzschild coordinates \( (t, r, \theta, \phi) \), the line element is: \[ ds^2 = -\left(1 - \frac{2GM}{r}\right) dt^2 + \left(1 - \frac{2GM}{r}\right)^{-1} dr^2 + r^2 d\Omega^2 \] where \( d\Omega^2 = d\theta^2 + \sin^2\theta \, d\phi^2 \) is the metric on the 2-sphere.

This spacetime is Ricci-flat: \( R_{\mu\nu} = 0 \), meaning all curvature is encoded in the Weyl tensor.

Weyl Tensor Components in Schwarzschild

In this vacuum solution, the nonzero components of the Weyl tensor reflect tidal forces. For example, in an orthonormal frame, the radial tidal acceleration between nearby geodesics is governed by: \[ C^r_{\ t r t} = -\frac{2GM}{r^3} \] This component describes how a small ball of test particles would be stretched radially and compressed tangentially---pure tidal deformation without volume change.

Other components include:

• \( C^\theta_{\ t \theta t} = C^\phi_{\ t \phi t} = \frac{GM}{r^3} \)
• \( C^\theta_{\ r \theta r} = C^\phi_{\ r \phi r} = -\frac{GM}{r^3} \)

Interpretation

• The Ricci tensor would describe volume change due to local energy density---but here it's zero.
• The Weyl tensor describes shape distortion due to the gravitational field of the mass \( M \), even in vacuum.
• This is why gravitational waves and tidal effects in empty space are governed by the Weyl tensor.

As one source puts it: "The Weyl curvature is the only part of the curvature that exists in free space---a solution of the vacuum Einstein equation---and it governs the propagation of gravitational waves through regions of space devoid of matter."
--- Wikipedia

Would you like to visualize the tidal tendex and vortex lines associated with the Weyl tensor in Schwarzschild spacetime? They offer a vivid way to see how curvature acts without matter.

Afterword: