61
Stack Exchange
votes

Grothendieck's Period Conjecture and the missing p-adic Hodge Theories

Posted on 3/15/2015
UQ ID:57
Science
MathOverflow
Original

Singular cohomology and algebraic de Rham cohomology are both functors from the category of smooth projective algebraic varieties over to -vectors spaces. They come with the extra structure of Weil cohomology theories - grading, cup product, orientation map, and cycle class map. We can consider the space of all invertible natural transformations from singular cohomology to algebraic de Rham cohomology that respect this structure. For purely formal reasons, this is an affine scheme. The coordinates are the matrix coefficients of the natural transformation for each algebraic variety, and the relations are given by the various commutative diagrams that must hold. Conjecturally, this scheme is a torsor for the motivic Galois group of .

de Rham's theorem, together with GAGA, gives us an isomorphism between these two functors when tensored with . In other words, it gives us a -point of this affine scheme.

Grothendieck's period conjecture says that this point is a generic point - so the ring of periods in is equal to the whole ring of functions on this scheme.


On the other hand, consider the -adic analogue. -adic etale cohomology and algebraic De Rham cohomology are both functors from the category of smooth projective algebraic varieties over to -vector spaces. They are Weil cohomology theories.

We can consider the space of all isomorphisms between these two functors as an affine scheme over .

-adic Hodge theory gives a -valued point of this scheme.

However, it is not the generic point. The reason is that the isomorphism described by -adic Hodge theory naturally factors through the category of -representations. Hence it lies in a closed subscheme that is a torsor under, not the full motivic Galois group, but the Zariski closure of inside it. This group is much smaller because the Tate conjecture fails over , and a map of Tannakian categories that is not a full functor corresponds to a map of Tannakian groups that is not surjective.


So the analogue of the period conjecture fails badly over . This leads me to my question: Grothendieck's period conjecture essentially gives us a description of the scheme of isomorphisms betweeen singular and de Rham cohomology - it's the spectrum of the period ring. However, we do not have a similar picture of the scheme of isomorphisms between -adic etale cohomology and de Rham cohomology. The period ring only gives us one point.

Can we explicitly describe any other points of this scheme of isomorphisms?

Keywords & Tags
nt.number-theory
tannakian-category
p-adic-hodge-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

The scheme parametrizing natural isomorphisms between ( p )-adic étale cohomology and algebraic de Rham cohomology, respecting their Weil cohomology structures, is deeply tied to the motivic Galois group and the formalism of Tannakian categories. Here's a structured answer:

Key Background:

  • Weil Cohomology Theories: Both ( p )-adic étale cohomology (( H^{\text{et}} )) and de Rham c...
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

  • On the “Galois” sub-Tannakian category generated by the p-adic étale cohomology of smooth proper varieties over Qp, the scheme of tensor isomorphisms between the forgetful fiber functor (étale) and the de Rham fiber functor is, in a precise Tannakian sense, represented by Spec BdR. In particular, there are no points over any smaller Qp–algebra: any R–valued point necessarily factor...
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 that touches on deep aspects of p-adic Hodge theory and the motivic formalism. Let me address several key points:

The Structure of the Problem

You've correctly identified that the scheme of isomorphisms between p-adic étale cohomology and algebraic de Rham cohomology over is much richer than what classical p-adic Hodge theory reveals. The comparis...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Let

• H = Hét(–, ℚp) : Var/ℚp → Vecℚp
• HdR = Hdr(–/ℚp) : Var/ℚp → Vecℚp

be the two Weil co-homology theories on smooth projective ℚp–varieties that you fixed. Put

Perp := Isom⊗(H, HdR)

(the affine ℚp-scheme whose R-valued points are the tensor-compatible, graded, cup–product–, orientation– and cycle–class-preserving natural isomorphisms
H⊗ℚpR ≃ HdR⊗ℚpR).

  1. What is already ...
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, in my view, what one can and cannot say about “other” points on the p-adic comparison torsor

 Iso⊗(H_et, H_dR) over ℚₚ.

1) What we know: Fontaine’s p-adic Hodge theory produces a single distinguished point

 s_{dR} ∈ Iso⊗(H_et, H_dR)(B_{dR})

namely the usual B_{dR}-comparison isomorphism
H_et^(X)⊗{ℚₚ}B{dR} ≃ H_{dR}^(X)⊗{ℚₚ}B{dR}.
Because this factors through Galois r...

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 and deeply insightful question that touches upon the foundational differences between archimedean and non-archimedean Hodge theory, and it leads directly to some of the most exciting recent developments in arithmetic geometry.

You have perfectly summarized the situation. Let's formalize it slightly to set the stage.

The Formal Setup

Let be the Tannakian ...

0 model reviews
0 human reviews
No reviews yet

o3

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

Let

ω ₑₜ : Var / ℚ_p → Vec_{ℚ_p}, X ↦ ⊕i H^{i}{et}(X_{\bar{ℚ}p},ℚ_p)
ω
{dR} : Var / ℚ_p → Vec_{ℚ_p}, X ↦ ⊕i H^{i}{dR}(X/ℚ_p)

denote the two standard Weil co-homology functors (with all usual extra structures).
Write

P := Isom^{⊗}(ω ₑₜ , ω_{dR})

for the fpqc sheaf that assigns to a ℚ_p–algebra R the set of invertible tensor-compatible natural transformations

ω ₑₜ ⊗_{ℚ_p...

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 a highly technical question about Grothendieck's period conjecture and p-adic Hodge theory. They want to know if there are explicit descriptions of points in the scheme of isomorphisms between p-adic étale cohomology and de Rham cohomology beyond the one provided by the period ring.

Hmm, this is deep arithmetic geometry territory. Let me unpack the context first....

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

Grothendieck's Period Conjecture and p-adic Cohomology Isomorphisms

This is an excellent question about a deep topic in arithmetic geometry. Let me provide some insights on the scheme of isomorphisms between p-adic étale cohomology and de Rham cohomology.

The Current Situation

As you correctly note, p-adic Hodge theory gives us a B_dR-valued point on the scheme of isomorphisms Isom(H_ét, H...

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