17
Stack Exchange
votes

Are there two non-equivalent exotic structures on coming from topologically slice, non-slice knots?

Posted on 7/27/2017
UQ ID:232
Science
MathOverflow
Original

For a knot , which is topologically slice but not slice (in a smooth way), there's a four manifold , homeomorphic but not diffeomorphic to standard euclidean .

There are ways to find such knots, particularly knots with the Alexander polynomial equal to 1, are topologically slice (Freedman). Among these knots one can find non-slice knots using obstructions like -invariant (coming from Knot Floer Homology) or Rasmussen -invariant (coming from Khovanov Homology). Knots with non-zero - or - invariant are not slice.

The negative Whitehead double of left trefoil is an example of these knots.

Question. The above argument proves the existence of an exotic structure on , but this method proves the existence of only one exotic structure on . Can you show if there are two different knots, and (both topologically slice, non-slice knots), which they give us two non-equivalent exotic s? Or if all of coming from these knots are the same, i.e. you can get to only one exotic structure through this method.

Keywords & Tags
differential-topology
knot-theory
4-manifolds
heegaard-floer-homology
khovanov-homology
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 address whether there exist two non-equivalent exotic structures on (\mathbb{R}^4) constructed from distinct topologically slice, non-smoothly slice knots (K) and (K'), we proceed as follows:

Key Background:

A knot (K \subset S^3) is topologically slice if it bounds a topologically embedded 2-disk in (B^4), and non-smoothly slice if no such disk is smoothly embedded. Free...

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: This is open for the specific “topologically slice but not smoothly slice knot” construction. We do not currently know whether two different knots K and K′ of that type can produce nondiffeomorphic exotic R^4’s via the standard construction. It is conceivable (and consistent with present knowledge) that all such R^4_K could even be diffeomorphic.

Context and references:

  • The constr...
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

Excellent question. This gets to the heart of how modern invariants in low-dimensional topology can be used to distinguish subtle structures.

The short answer is yes, you can find two such knots, and , that give rise to non-diffeomorphic exotic s. In fact, this method can produce an infinite family of pairwise non-diffeomorphic exotic s.

Here is a cons...

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, I need to tackle this question about exotic structures on ℝ⁴ coming from topologically slice but non-slice knots. The user is asking whether there are two different knots that give non-equivalent exotic ℝ⁴s or if all such constructions yield the same exotic structure.

First, I recall the setup: For a knot K in S³ that's topologically slice but not smoothly slice, we can construct a ...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Let us denote by

  C (K)=B⁴∪(0–framed 2–handle attached along K)

and

  R⁴_K = int C (K).

If K is topologically slice, Freedman showed that ∂C (K)=S³ bounds a topological 2–disk, so C (K) is topologically B⁴ and therefore R⁴_K is homeomorphic to the standard ℝ⁴.
If, in addition, K is not smoothly slice, the slice disc has to be replaced by a Casson handle; the resulting smooth structure...

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 an excellent question about exotic smooth structures on arising from topologically slice knots.

The answer is yes - there are indeed infinitely many distinct exotic 's that can be constructed from topologically slice but not smoothly slice knots.

Here's the key insight: The exotic constructed from a topologically slice knot can be dis...

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

Exotic Structures from Topologically Slice Knots

This is a fascinating question in 4-manifold theory that deals with distinguishing exotic smooth structures on .

The Construction

Let me clarify the construction first: For a knot that is topologically slice but not smoothly slice, we can construct an exotic as follows:

  1. Take a...
0 model reviews
0 human reviews
No reviews yet

o3

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

Yes – in fact the recipe you quote produces infinitely many mutually non-diffeomorphic exotic (\mathbb {R}^{4})’s.

How the construction works again
Let (K\subset S^{3}) be a knot.

  1. Attach a (0)-framed 2–handle to (B^{4}) along (K); call the result
    (X_{K}=B^{4}\cup_{K}h^{2}).
    (\partial X_{K}=S^{3}_{0}(K)).

  2. If (K) is topologically slice, its meridian bounds a loca...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

No. In fact nobody knows how to tell two of these “knot‐exotics” apart, and it is quite possible that they are all diffeomorphic. Here is roughly what is known:

  1. Construction via a Casson–handle.
    Given a topologically slice but smoothly non-slice knot K one builds a Casson–handle CH(K) in B^4 whose attaching circle is K. Freedman’s theorem says CH(K) is homeomorphic to the standard o...
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