Lean is a language for mathematical statements and proofs that a computer can verify. This page shows one statement file from OpenAI’s release, possible paper matches and independent reports. The code-like names below identify the definitions or theorems selected by the proof-verification settings.
Theorem selected for verification:OAI.PlanarFalconer.mainTarget_proved
The lines of the Lean statement that state the theorem, then the definitions in the file that it uses.
defMainTarget : Prop := ∀ E : Set Plane, IsCompact E → 1 < dimH E → 0 < volume (distanceSet E)⋮theoremmainTarget_proved : MainTarget := bysorry
A Lean statement states the theorem and leaves its proof as sorry on purpose. OpenAI’s proof is in a separate solution module, and a program called Comparator checks that proof against this statement.
Definitions needed to read it
Local definitions the statement names, followed through the definitions they name in turn. The match is by name in the source text, so a name reached only through notation can be missed; the full file is below.
defdistanceSet (E : Set Plane) : Set ℝ := {r | ∃ x ∈ E, ∃ y ∈ E, dist x y = r}
Possible paper match, with no recorded review
Atlas selected this possible match by comparing words in the Lean statement with every statement in the family. No review of whether the statements mean the same thing is recorded.
Words of the Lean statement, its names split into words, that also appear in the theorem: proves, plane, compact, dim and distance.
Proposition 5.10 of The Falconer distance conjecture in all dimensions
Proposition(Starting pair measures)
Let E\subset\R^d be compact, d\ge2, and \dim_HE>S=d/2. Either Lemma prep:classical-plane already proves that its distance set has positive Lebesgue measure, or the following construction is possible.
After a similarity there are compact separated sets E_1,E_2\subset E and probabilities \mu_i supported on them, each satisfying
\mu_i(B(x,u))\le C u^{S+\chi}
for a fixed \chi>0. Their cross directions lie in a fixed arbitrarily small spherical patch. For every sufficiently small fixed \omega>0, there are decreasing Borel pair sets \Gamma_N\subset E_1\times E_2 such that
1.
(\mu_1\otimes\mu_2)(\bigcap_N\Gamma_N)>0;
2.
\Gamma_N is a disjoint union of at most C2^{2d\omega N} products of spatial Borel sets;
3.
for every e>0, there are c(e)>0, C_e<\infty and Borel B_N\subset\Gamma_N with (\mu_1\otimes\mu_2)(B_N)\le C_e2^{-c(e)N}, such that for G_N=\Gamma_N\setminus B_N, all 2^{-N}\le u\le1, and all spherical caps B(w,u),
The last bounds integrate the original opposite marginal, without normalizing its individual fibers. The B_N need not have a product partition or be nested. All constants are independent of N, but may depend on the fixed measures, \omega, and e.
Let $E\subset\R^d$ be compact, $d\ge2$, and
$\dim_HE>S=d/2$. Either Lemma~\ref{prep:classical-plane} already
proves that its distance set has positive Lebesgue measure, or the
following construction is possible.
After a similarity there are compact separated sets $E_1,E_2\subset E$
and probabilities $\mu_i$ supported on them, each satisfying
\[
\mu_i(B(x,u))\le C u^{S+\chi}
\]
for a fixed $\chi>0$. Their cross directions lie in a fixed
arbitrarily small spherical patch. For every sufficiently small fixed
$\omega>0$, there are decreasing Borel pair sets
$\Gamma_N\subset E_1\times E_2$ such that
\begin{enumerate}
\item $(\mu_1\otimes\mu_2)(\bigcap_N\Gamma_N)>0$;
\item $\Gamma_N$ is a disjoint union of at most $C2^{2d\omega N}$
products of spatial Borel sets;
\item for every $e>0$, there are $c(e)>0$, $C_e<\infty$ and
Borel $B_N\subset\Gamma_N$ with
$(\mu_1\otimes\mu_2)(B_N)\le C_e2^{-c(e)N}$, such that for
$G_N=\Gamma_N\setminus B_N$, all $2^{-N}\le u\le1$, and
all spherical caps $B(w,u)$,
\begin{align*}
\mu_2\{y:(x,y)\in G_N,\ \pi_x(y)\in B(w,u)\}
&\le2^{eN}u^S,\\
\mu_1\{x:(x,y)\in G_N,\ \pi_y(x)\in B(w,u)\}
&\le2^{eN}u^S.
\end{align*}
\end{enumerate}
The last bounds integrate the original opposite marginal, without
normalizing its individual fibers. The $B_N$ need not have a product
partition or be nested. All constants are independent of $N$, but
may depend on the fixed measures, $\omega$, and $e$.
Other possible paper matches, closest wording first
Theorem 1.1 of The Falconer distance conjecture in all dimensions. Words of the Lean statement, its names split into words, that also appear in the theorem: dim and compact. Found in the paper’s title, which its main theorem states: distance.
Theorem 4.1 of The Falconer distance conjecture in all dimensions. Words of the Lean statement, its names split into words, that also appear in the theorem: dist. Shared only with the release’s name for the Lean statement or OpenAI’s note on it: case.
Proposition 11.5 of The Falconer distance conjecture in all dimensions. Words of the Lean statement, its names split into words, that also appear in the theorem: distance.
Proposition 11.3 of The Falconer distance conjecture in all dimensions. Words of the Lean statement, its names split into words, that also appear in the theorem: distance.
Theorem 4.2 of The Falconer distance conjecture in all dimensions. Shared only with the release’s name for the Lean statement or OpenAI’s note on it: planar.
Proposition 7.4 of The Falconer distance conjecture in all dimensions. Words of the Lean statement, its names split into words, that also appear in the theorem: distance.
How Atlas selects possible matches: it compares words in the Lean statement with every statement in the family. It also splits Lean names into words. The release’s label and note receive less weight; a main theorem wins a close match. If the Lean wording yields no clear match, Atlas uses the catalogue description. This selects passages to compare; it does not establish that they mean the same thing.
Reported Comparator runs
two independent groups report that Comparator accepted runs for this Lean statement file: Carlos Toledo’s cert-machine; MathVet. Each group reports its own Comparator run for this statement file. Atlas has not repeated the runs.
For a configured theorem, Comparator tests whether OpenAI’s proof proves the exact Lean statement. Some files instead configure definitions for comparison by name and type. Acceptance does not establish that the statement means the same thing as the paper’s theorem.
Every Comparator challenge re-run on Linux with nanoda switched on, decided by a preregistered rule; every family’s challenge statements read against OpenAI’s headline, clause by clause. Decider: Comparator (leanprover/comparator d03acab1 = tag v4.34.0, built with the release’s toolchain v4.34.1), lean4export 076e8e57, landrun 811cfff5, nanoda_lib 3a240721 — on GitHub’s Linux runners (.github/workflows/openai-math-kernel.yml), one j…
AcceptedTheir term: “CERTIFIED”.
Re-run through Comparator with the independent nanoda kernel switched on: Lean’s kernel and nanoda both accept OpenAI’s solution.
An independent, model-assisted, pre-referee reading of each family’s challenge statements against its headline claim under a published rubric (PROTOCOL.md), with its own Comparator runs per challenge. Its protocol describes a planned error-rate study; this import does not establish that the study has been completed.
AcceptedTheir term: “comparator-sandboxed-pass”.
Re-run through Comparator in a sandboxed virtual machine: accepted.
If Comparator is run under this configuration and accepts, the solution proves the configured theorem using only the allowed axioms, and the Lean kernel accepts every step.
This configuration lists no definition holes, so every definition the statement uses is compared as it is written in this file.
Acceptance leaves open whether the Lean statement means the same thing as the paper’s theorem, whether the paper’s other claims are correct, and whether the result is new. Those questions require comparing the definitions and statements, reviewing the paper’s arguments, and reading the earlier literature.
Do family 073’s Lean statements express the advertised result?
These assessments compare all the family’s Lean statements with the whole result OpenAI describes in its catalogue. They do not assess this statement alone. Each group uses its own published rules.
MathVet and cert-machine agree on how much of the advertised result the Lean statements express.
OpenAI’s own note on what this Lean statement covers
“The linked statements include both this all-dimensional result and the earlier planar case.”
An AI agent drafted an interpretation of that note, classifying this statement as “states a weaker form of a paper’s theorem”. No human review of the draft is recorded.
Supporting material
The complete Lean statement file
25 lines, copied from release version fd4aeeb. A name defined in this file links to its line; pointing at the name shows its definition.
Declared in this fileOpenAI’s library at fd4aeebOther linked names open the current documentation for Mathlib, Lean’s mathematical library.
Links in the file: 4 to its own declarations, 9 to Mathlib’s documentation. 4 declared names also link to the same declaration in OpenAI’s library. OpenAI uses Mathlib version d13f23b. The linked documentation describes the current version, so names that have since changed may be missing there.
propext, Classical.choice, Quot.soundThe axioms this configuration allows a proof to use. A replay shows which of them a proof uses.
Imports
Mathlib
Imports from outside Mathlib
None
Local vocabulary
3 local vocabulary declarations
Lines of Lean, without comments or blank lines
7
Second proof-verification program (nanoda)
Off in OpenAI's configuration.
Statement comparison
A shareable summary of this page: the proposed paper match, what the Lean statement expresses, and which reviews are recorded.
Plectis Atlas
Planar Falconer distance theorem
Family 073: The Falconer distance conjecture
Candidate pairing
Proposition (Starting pair measures)
Let E\subset\R^d be compact, d\ge2, and \dim_HE>S=d/2. Either Lemma prep:classical-plane already proves that its distance set has positive Lebesgue measure, or the following construction is possible.
After a similarity there are compact separated sets E_1,E_2\subset E and probabilities \mu_i supported on them, each satisfying
\mu_i(B(x,u))\le C u^{S+\chi}
for a fixed \chi>0. Their cross directions lie in a fixed arbitrarily small spherical patch. For every sufficiently small fixed \omega>0, there are decreasing Borel pair sets \Gamma_N\subset E_1\times E_2 such that
1.
(\mu_1\otimes\mu_2)(\bigcap_N\Gamma_N)>0;
2.
\Gamma_N is a disjoint union of at most C2^{2d\omega N} products of spatial Borel sets;
3.
for every e>0, there are c(e)>0, C_e<\infty and Borel B_N\subset\Gamma_N with (\mu_1\otimes\mu_2)(B_N)\le C_e2^{-c(e)N}, such that for G_N=\Gamma_N\setminus B_N, all 2^{-N}\le u\le1, and all spherical caps B(w,u),
The last bounds integrate the original opposite marginal, without normalizing its individual fibers. The B_N need not have a product partition or be nested. All constants are independent of N, but may depend on the fixed measures, \omega, and e.
The Falconer distance conjecture in all dimensions
TeX label prep:starting-pairs, build/sections/04_preparation.tex, line 733
The Lean statement says
defMainTarget : Prop := ∀ E : Set Plane, IsCompact E → 1 < dimH E → 0 < volume (distanceSet E)⋮theoremmainTarget_proved : MainTarget := bysorry
A Lean statement states the theorem and leaves its proof as sorry on purpose. OpenAI’s proof is in a separate solution module, and a program called Comparator checks that proof against this statement.
Recorded comparisons with the paper
Atlas records no contributed comparison of this statement with the paper.
Contributed Comparator run reports
Atlas records no contributed report of running Comparator for this statement file.