23
Stack Exchange
votes

Base change for

Posted on 7/6/2014
UQ ID:122
Science
MathOverflow
Original

This is a direct follow-up to Conjecture on irrational algebraic numbers.

Take the decimal expansion for but now think of it as the base expansion of some number Is there an easy (or, failing that, hard) proof that is transcendental? Of course, same question stands for for your favorite

Keywords & Tags
nt.number-theory
ds.dynamical-systems
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 determine whether the number (\theta_k) (obtained by interpreting the decimal expansion of (\sqrt{2}) as a base-(k) expansion for (k > 10)) is transcendental, we can leverage results from transcendence theory, particularly those related to automatic sequences and generating functions.

Key Steps:

  1. Decimal Digits of (\sqrt{2}): Let (\sqrt{2}) have decimal expansion (\sqrt{...
0 model reviews
0 human reviews
No reviews yet

GPT-5

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

Write a_n for the base‑10 digits of √2, so that √2 = ∑{n≥1} a_n 10^{-n}, and set θ_k := ∑{n≥1} a_n k^{-n}. Equivalently, if A(z) := ∑_{n≥1} a_n z^n (a power series with integer coefficients bounded between 0 and 9), then A(1/10) = √2 and θ_k = A(1/k).

  • What is known unconditionally: θ_k is irrational for every integer k ≥ 2. Indeed, if θ_k were rational, then its base‑k expansion would be even...
0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Let

  √2 = 1 . d1 d2 d3 …     (di ∈ {0 , 1 , … , 9})

be the ordinary decimal expansion of √2 and, for an integer b ≥ 11, put

  θb := Σn≥1 di b-n. (1)

In words: we keep the same infinite string of decimal digits, but now regard it as the base-b fractional expansion of a new real number θb.
The question is whether one can prove, for some (o...

0 model reviews
0 human reviews
No reviews yet

o3

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

Let

 α = √2 = 1.a1 a2 a3 … (decimal expansion, a n ∈ {0,…,9})

and put

 θk = a1 k-1 + a2 k-2 + a3 k-3 + … = Σn≥1 an k-n , k ≥ 2.

In particular θ10 = α – 1 and we are interested in θ11.
(The initial integral part “1.” plays no rôle, so we omit it and work with the fractional part f(z) defined below.)

Step 1. Introduce the power series
 f(z) = Σn≥1 an z^n (an bounded inte...

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 base change and transcendence. Let me address what's known about this type of problem.

The General Setup

When we take the decimal expansion of , we're looking at: where , , , etc.

Your is defined as:

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> The problem is about taking the decimal expansion of \(\sqrt{2}\) and interpreting it in a different base. Specifically, it says to take the decimal expansion for \(\sqrt{2}\), but think of it as a base 11 expansion, and call that number \(\theta_{11}\). Then, it asks if \(\theta_{11}\) is transcendental. Similarly for other bases greater than 10.

First, recall that (\sqrt{2}) is irrati...

0 model reviews
0 human reviews
No reviews yet

o4 mini

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

Nothing non‐trivial is known. In fact one cannot even prove that the “same’’ digit‐string of √2, viewed in a larger base, cannot produce a new algebraic number. Here is why it seems out of reach:

  1. If you take the ordinary base–10 expansion of √2
    √2 = 1.a₁a₂a₃…₁₀
    and simply re‐interpret the digits a₁,a₂,a₃,… as the base–11 (or base–k>10) expansion
    θ₁₁ = 0.a₁a₂a₃…₁₁
    ...
0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

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

This is an excellent and notoriously difficult question. The short answer is:

This is a famous open problem. There is no known proof that (or any for ) is transcendental. It is, however, widely conjectured to be true.

Let's break down why this is so hard and what is known in this area.

1. The General Conjecture (Borel's Conjecture)

Your question is a ...

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

Transcendence of Base-Changed Algebraic Numbers

This question asks whether is transcendental, where is constructed by taking the decimal (base-10) expansion of and interpreting those same digits as a base-11 expansion.

To be explicit, if: in base 10, then:

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