Convolutions Revisited

On the 12th October 2025, I created a post titled A Practical Example of a Convolution which began as follows:

Over the past decade, for some reason, I've chosen to ignore convolutions. Whenever they were mentioned in an OEIS sequence, I simply skipped over the reference. However, I'm now attempting to redress that neglect and to that end I was lucky to find two excellent YouTube videos about convolutions made by 3Blue1Brown (this guy has 7.76 million subscribers and for good reason).

I finished the post by saying:

This post is simply the first in what I hope will be a series of posts relating to convolutions. As I've already discovered, convolutions linked to Fourier transforms and Laplace transformations so it's a big topic to investigate but at least I've finally made a start.

Unfortunately there was no future series of posts relating to convolutions but I was reminded of them once again thanks to the number associated with my diurnal age today: \( \textbf{28152}\). It is a member of OEIS A014342:

 A014342: Convolution of primes with themselves.

 The initial members are:

4, 12, 29, 58, 111, 188, 305, 462, 679, 968, 1337, 1806, 2391, 3104, 3953, 4978, 6175, 7568, 9185, 11030, 13143, 15516, 18177, 21150, 24471, \( \textbf{28152}\), 32197, 36678, 41543, 46828, 52621, 58874, 65659, 73000, 80949, 89462, 98631, 108396, 118869, 130102, 142071

This time around I got Gemini to explain how the convolution was calculated:

In the context of integer sequences like those found in the OEIS, a convolution (specifically, a discrete Cauchy convolution) is a mathematical way of combining two sequences to create a third. When a sequence is convolved with itself, you are multiplying its terms together in a symmetrical, sliding window and summing the results.

Here is the full breakdown of how this works for OEIS A014342.

The Formula

First, let's establish our base sequence, which is the sequence of prime numbers, denoted as p_n:

• p₁ = 2
• p₂ = 3
• p₃ = 5
• p₄ = 7
• p₅ = 11
• ...and so on.

The n-th term of the convolved sequence, let's call it c_n, is calculated by taking the sum of the products of two primes whose indices add up to n + 1.

The formal equation looks like this:

c_n = Σ (p_i × p_n-i+1)

(summed from i = 1 to n)

In simpler terms: to find the n-th number in your sequence, you line up the first n primes going forward, line up the exact same n primes going backward, multiply the overlapping pairs, and add those products together.

Step-by-Step Calculation

Here is how the first few members of the sequence are calculated using this method.

1st Term (n = 1):

We only use the first prime (p₁ = 2).

c₁ = (p₁ × p₁)

c₁ = (2 × 2)

c₁ = 4

2nd Term (n = 2):

We use the first two primes (2 and 3). We pair the first with the second, and the second with the first.

c₂ = (p₁ × p₂) + (p₂ × p₁)

c₂ = (2 × 3) + (3 × 2)

c₂ = 6 + 6

c₂ = 12

3rd Term (n = 3):

We use the first three primes (2, 3, and 5). Notice how the indices always add up to 4 (n + 1).

c₃ = (p₁ × p₃) + (p₂ × p₂) + (p₃ × p₁)

c₃ = (2 × 5) + (3 × 3) + (5 × 2)

c₃ = 10 + 9 + 10

c₃ = 29

4th Term (n = 4):

We use the first four primes (2, 3, 5, and 7).

c₄ = (p₁ × p₄) + (p₂ × p₃) + (p₃ × p₂) + (p₄ × p₁)

c₄ = (2 × 7) + (3 × 5) + (5 × 3) + (7 × 2)

c₄ = 14 + 15 + 15 + 14

c₄ = 58

5th Term (n = 5):

We use the first five primes (2, 3, 5, 7, and 11).

c₅ = (p₁ × p₅) + (p₂ × p₄) + (p₃ × p₃) + (p₄ × p₂) + (p₅ × p₁)

c₅ = (2 × 11) + (3 × 7) + (5 × 5) + (7 × 3) + (11 × 2)

c₅ = 22 + 21 + 25 + 21 + 22

c₅ = 111

The Pattern

As you calculate further into the sequence, this symmetrical "folding" action continues. You are always starting at the outer edges of your chosen set of primes and working your way inward to the middle, multiplying the pairs and summing them up. This specific operation is incredibly common in polynomials, probability theory, and signal processing, but when applied purely to integer sequences like the primes, it yields the exact sequence you provided.

Remember that SageMath makes it very easy to determine self-convolutions due to its formula convolutions(A, A) where A is any given set.