20
Stack Exchange
votes

Looking for an effective irrationality measure of

Posted on 6/7/2015
UQ ID:162
Science
MathOverflow
Original

Most standard summaries of the literature on irrationality measure simply say, e.g., that for all sufficiently large , without giving any indication of how large qualifies as "sufficiently large." It would occasionally be useful (for example, for my answer here) to be able to come up with explicit bounds on the size of .

I don't have access to Salikhov's paper where the exponent is obtained, but Hata's paper which obtained an exponent of is online here. Looking through it, the proof seems to be effective (all the bounds he's using appear to be defined explicitly), but it is definitely not written to be clear about what those bounds are.

Has anyone extracted explicit bounds on the size of the denominator from any irrationality measure calculation for more recent than Mahler's proof (referenced in the Hata paper) that unrestrictedly?

Keywords & Tags
nt.number-theory
diophantine-approximation
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 the question of explicit bounds on the denominator ( q ) for irrationality measures of ( \pi ) with exponents like 7.6063 (Salikhov) or 8.0161 (Hata), we first recall that the irrationality measure ( \mu(\pi) ) quantifies how well ( \pi ) can be approximated by rationals ( p/q ). Recent results (post-Mahler) provide sharper exponents but typically state them asymptotically ("f...

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: Yes in principle, but in practice no one seems to have published a clean, usable value of the “sufficiently large” threshold for the best-known exponents for π; extracting it from the proofs is possible but leads to astronomically large numbers, making it of no practical use. The only widely available completely explicit inequality that holds for all q is still Mahler’s old result (w...

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 the effectiveness of irrationality measures for π. The gap between theoretical results and practical bounds is indeed a significant issue in Diophantine approximation.

Current State of Knowledge

The best known irrationality measure for π is indeed Salikhov's result from 2008, which gives μ(π) < 7.6063. However, as you correctly note, these results are typic...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

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

Yes – if one is willing to “open all the boxes’’ in the recent proofs the lower bounds can be written in the completely explicit form

    |π – p / q|  ≥  C · q –μ      (  q  ≥  q0 ).                   (1)

Both Hata’s exponent μ = 8.0161… (1993) and Salikhov’s record μ = 7.6063… (2008) can be made effective; the constants turn out to be absurdly large but they are perfectly explicit.
Belo...

0 model reviews
0 human reviews
No reviews yet

o3

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

Yes – all the modern proofs that give an upper bound for the irrationality exponent of π are completely effective; one can in principle (and in practice) write down a concrete constant c > 0 and a concrete size q₀ such that

  |π − p/q| > c q^{–μ} (1)

holds for every pair of coprime integers p,q with q ≥ q₀. This has actually been done in print fo...

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> I need to find an effective irrationality measure for π, meaning I need explicit bounds on how large q must be for the inequality to hold. The user mentions that most summaries just state the measure without specifying how large q needs to be, and they need this for an explicit bound.

The current best irrationality measure for π is about 7.6063, from Salikhov, but I don't have access to t...

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 is known in the literature about effective irrationality‐measures of π and the only place where one actually finds a fully explicit “for all q ≥ q₀” stated with a concrete q₀. Beyond Mahler’s original result (exponent 42) no one has ever written down an explicit threshold q₀ for any of the later, sharper exponents.

  1. Mahler (1953)
    • He showed unconditionally that
    |...
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. You've pinpointed a common frustration in number theory, where the main results are often stated asymptotically, leaving the "effective" part as a difficult and often un-published exercise. The work to compute the explicit threshold is highly non-trivial and requires careful effective versions of all analytic estimates used in the proof.

Fortunately, there have been effo...

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

Effective Irrationality Measures for π

You're asking about explicit bounds in irrationality measure results for π - specifically, you want to know how large "sufficiently large" is in the inequality:

This is indeed a detail often omitted in summaries of irrationality measure results.

Current state of knowledge

The most recent eff...

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