hinton_number
ABOUT

What is a
Hinton number?

The Erdős number, rebuilt for the deep-learning era. Paul Erdős wrote 1,500+ papers; mathematicians measure their distance to him in co-authorship hops. We do the same with Geoffrey E. Hinton as the origin.

scroll ↓
THE_IDEA
  1. Geoffrey E. Hinton← the origin, distance 0
  2. co-authored a paper together
  3. his co-authorhinton_number = 1
  4. co-authored with a 1
  5. their co-authorhinton_number = 2
  6. …the shortest co-authorship path…
  7. youhinton_number = ?

Co-author a paper with Hinton and your number is 1; co-author with a 1 and yours is 2 — your Hinton number is the length of the shortest co-authorship path from you back to Hinton.

THE_DATA
0M
papers
0M
people
0M
co-author edges

Everything comes from the full dblp.org dump (CC0 1.0) — the computer-science bibliography. We rebuild the co-author graph and re-run the computation monthly; the verified date on every badge is that build date. Your number and the path behind it are precomputed, not computed on request.

one BFS from Hinton's node
HOW_ITS_COMPUTED
  1. 01Parse every paper in DBLP; two people share an edge if they co-authored at least one paper — every paper counts, from a two-author note to a 450-author consortium report.
  2. 02Run one breadth-first search from Hinton's node over that graph. Every author gets a distance and a parent pointer — that pointer chain is the shortest path shown on your page.
  3. 03Count the distinct shortest paths of that length (the "via N paths" line) and rank your collaboration strength among the authors with the same Hinton number.
THE_STATISTICS

Almost everyone
is connected.

Of the 4.2M people in DBLP, 0% have a finite path to Hinton. Each square below is ~21,000 people — the gray ones have published, but never within reach of the giant connected component.

connected: ~3.9M people∞: ~0.3M people
THE_INNER_CIRCLE

Distance 1 is a club of 365.

Only 365 people share a paper byline with Hinton — the top 0.009% of connected people. Not all of those are close collaborations; some share only a large consortium byline. Being a 1 is about as rare, among CS authors, as being struck by lightning in your lifetime.

HALL_OF_FAME — famous hinton_numbers
1
Yoshua Bengio
1
Yann LeCun
1
Ilya Sutskever
1
Alex Krizhevsky
THE_ANCESTORS

The man the metric is named
after is 3 hops away.

The Hinton number is measured in a unit invented for Paul Erdős — and Erdős himself has a Hinton number of 3. So does everyone below: some helped invent computing, some spent a career arguing the field was on the wrong track, some never went near it. Publish anywhere near the field's ancestry and the graph finds you.

HALL_OF_LEGENDS — hinton_numbers across a century
3
Paul Erdős
3
Claude Shannon
3
Donald Knuth
4
John von Neumann
3
Noam Chomsky
3
Terence Tao
2
Marvin Minsky
2
Judea Pearl
3
Tim Berners-Lee
Alan Turing is in DBLP — but has no path. He published alone, or with people the connected graph never absorbed. Not even the father of the field is guaranteed a number.
DISTANCE_DISTRIBUTION

The whole field sits at 4.

The most common distance is 4 — 53% of connected people sit there, and 96% land between 3 and 5. Distances above 7 are vanishingly rare.

<1%
1.2%
28.2%
52.8%
15.1%
2.2%
<1%
<1%
<1%
<1%
mean 3.90
1
2
3
4
5
6
7
8
9
10+
3.90
mean distance
4
median
4
mode (53%)
11
max observed
DEGREES_OF_SEPARATION

ML is a tighter web
than mathematics.

Mean distance to the center of each famous small world. The average Hinton number beats the average Erdős number — deep learning collaborates harder.

Kevin Bacon — actors (Bacon number)3.14
Geoffrey Hinton — CS authors3.90
random Facebook users, any two4.6
Paul Erdős — mathematicians4.65
shorter bar = smaller world · Bacon/Erdős/Facebook figures from published studies · every bar is hops, so Facebook's "3.57 degrees" (people in between) is 4.57 hops here
COLLABORATION_STRENGTH

Hops aren't the whole story.

Hop count treats a one-off workshop paper the same as a decade of collaboration. Collaboration strength doesn't. We use the standard co-authorship tie strength from network science — Newman's collaboration weight (M. E. J. Newman, 2001) — where each shared paper adds 1 / (co-authors − 1) to an edge: many small-team papers make a strong edge; a 450-author consortium paper adds almost nothing.

ONE 3-HOP ROUTE — fragile
you1 paper each — fragilehinton
ANOTHER 3-HOP ROUTE — heavy ← the one we score
you12 · 23 · 5 shared papers — thickness = weighthinton

Among your shortest paths — all the same number of hops — we take the one whose co-authorship is tightest, and use its weight to place your square inside your own band on the grid on your page: everyone with your Hinton number, strongest chains first. A 3 is only ever ordered against other 3s. Hops stay primary — no amount of collaboration weight turns a 4 into a 3. One honest caveat: much of that ordering is inherited from which of Hinton's direct co-authors — the distance-1 author your best chain runs through — rather than from your own collaborations, so read it as a curiosity more than a verdict. For example:

your square, near the strong end of the №3 band (example — the real grid on your page holds every band)
FAQ

Why is my number ∞? You have no path to Hinton in DBLP yet — usually meaning no indexed publication. Your first paper is your ticket in.

I can't find myself / that isn't me. Names collide; pick yourself by the paper titles shown in search. You can also type a venue or a word from one of your titles after your name — wei wang vldb — since search covers your two most recent papers too. Author identity follows DBLP's disambiguation.

Non-CS papers? Not yet — DBLP covers computer science. Broader sources are on the roadmap.

your_hinton_number = ?
find_your_number()
hintonnumber.orgdata: dblp.org (CC0 1.0) · graph verified 2026-08-29
privacy · contact · find your number
not affiliated with, endorsed by, or sponsored by Geoffrey Hinton