OpenAI groups related papers into a “family”. OpenAI’s catalogue describes this one:
Proves Donaldson’s tamed-to-compatible conjecture: every smooth almost complex structure on a closed four-manifold that is tamed by a symplectic form admits a compatible symplectic form. The almost complex structure stays fixed; the form’s cohomology class may change. (OpenAI’s Lean note)
Lean is a language for mathematical statements and proofs that a computer can verify. The assessments below ask whether those statements express the result OpenAI describes here.
Both independent assessments find that the Lean statements express or imply the whole result described above.Read the assessments
Possible match to OpenAI’s description, selected from the papers’ main statements because it shares the most wording. No review confirming the selection is recorded.
The other possible matches are Corollary 1.3 in the same paper () and Theorem 1.2(Taming and compatible cones) in the same paper ().
Suppose that a smooth almost complex structure J on a closed connected smooth real four-manifold X is tamed by a symplectic form. Then there is a smooth symplectic form compatible with J.
Reported proof verification
One Lean statement in the release; two independent groups report that Comparator accepted runs for this file at the version shown here.
This version characterizes the compatible cone by intersection positivity, restricts the cone-sum equality to $h_J^-=b_2^+-1$, and adds a four-torus example of strict inclusion; see the previous version.
We prove that every smooth almost complex structure on a closed four-manifold which is tamed by a symplectic form is compatible with a symplectic form. This gives a positive solution to Donaldson’s tamed-to-compatible conjecture. We also characterize the compatible cone by strict intersection positivity on the closure of the invariant part of the taming cone.
Lean is a language for mathematical statements and proofs that a computer can verify. The Lean statement below is shown beside its possible paper counterpart, with the reason they were linked.
For a configured theorem, the Comparator program tests whether OpenAI’s separate proof proves the exact Lean statement using only the allowed axioms. Some statement files instead configure definitions for comparison by name and type. Acceptance does not establish that a formal statement means the same thing as the paper’s theorem.
Suppose that a smooth almost complex structure J on a closed connected smooth real four-manifold X is tamed by a symplectic form. Then there is a smooth symplectic form compatible with J.
The words they share: connected, real, almost, complex, manifold, tamed, compatible, symplectic, smooth, form, closed, implies, compatibility, four.
Possible Lean counterpart
Selected from shared wording. No review of whether the statements mean the same thing is recorded.
This file states the theorem with sorry, a placeholder, in place of its proof. OpenAI supplies a separate proof file. Comparator tests whether that proof proves the statement here.
Other mathematical statements in OpenAI’s Lean library
Atlas found these propositions by scanning the text of the project’s Model.lean file. Each name links to its definition, with any associated statement file beside it. This list does not record running Lean to interpret or verify those definitions.
Independent comparisons and proof-verification reports
Does the Lean express the advertised result?
MathVet and cert-machine agree on how much of the advertised result the Lean statements express.
MathVet and Carlos Toledo’s cert-machine independently assessed whether this family’s Lean statements express the whole result OpenAI describes in its catalogue. These are assessments of the family as a whole, not of each paper theorem separately.
MathVet finds that the Lean statements express or imply the whole advertised result (their term: “full”).
Their note:taming_implies_compatibility: for a closed connected smooth 4-manifold X and a smooth almost complex structure J, if some symplectic form tames J then some symplectic form η satisfies Compatible η J (tames and J-invariant), with J fixed and no integrability or cohomology-class condition.
Definitions the group asks readers to compare with the paper:Differential forms are hand-built: TwoForm X := ∀ x, (T_x X)[⋀²]→L[ℝ] ℝ with IsSmooth (pullbacks along every smooth chart-like map f : ℝ⁴ → X are C^∞) and IsClosed (extDerivWithin of the pullback vanishes); AlmostComplexStructure with smoothness as a map of tangent bundles. Reads as the standard notions.
“full”, in their words: The challenge statements imply the headline claim after unpacking definitions or one routine step.
Their method: 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.
Donaldson’s tamed-to-compatible conjecture asks whether an almost-complex structure tamed by a symplectic form also admits a compatible symplectic form. The formalized result establishes this for every closed connected smooth four-manifold, keeping the almost-complex structure fixed. No integrability assumption or prescribed cohomology class for the compatible form is required.
AI-drafted comparisons, with no recorded human review
Taming implies compatibilityTamingCompatibility
Unreviewed AI draft: states a paper’s theorem as the paper does. States the main theorem (of the current edition of the paper the note links): on a closed connected four-manifold, an almost-complex structure tamed by a symplectic form admits a compatible one. The cone results are not part of the statement.
Who ran the proof-verification program?
These groups report running Comparator with the release’s Lean statement files. For a configured theorem, it verifies OpenAI’s separate proof against the exact statement; some files instead configure definitions for comparison by name and type. Each row is the named group’s report. Atlas has not repeated the runs.
These reports do not list the software versions, proof-verification programs, axioms, time or memory in separate fields. Any such details in a report’s prose are reproduced below.
Taming implies compatibilityTamingCompatibility
Two reports, all at the release’s recorded version.
Reported by
Their word
Their account
Date
Original report
cert-machine
“CERTIFIED”
Re-run through Comparator with the independent nanoda kernel switched on: Lean’s kernel and nanoda both accept OpenAI’s solution.
Other people’s accounts of running proof-verification software, with links to their reports.
Pico, openai-math-counterexamples: do the counterexamples in openai/math hold when someone else computes them?, 9 October 2026. Source
The four-torus example added on 7 October to repair a retracted claim checks (F self-dual, |F|^2 = 2 and the stated eigenvalue relations).
What these papers cite in the release, and what cites them
These links come from the papers’ bibliographies. A citation records that one paper cites another; how each cited result is used has not been examined here.
Papers elsewhere in the release that this family’s papers cite
Each paper’s outside references are listed with it on its reading page, where each citation is placed. Every outside work cited in the release: References outside the release
Explain a result, compare statements or propose a correction
Atlas has no contributed explanation for this family yet. You can offer one with a GitHub account. You receive named credit and disclose any AI assistance.
Each button opens a GitHub form with this page and its source version filled in. Opening the form does not reserve the work.
Commentary on this family by others, dated and credited. It is commentary, not a finding.
An unsigned public tier list, the OpenAI Math Tier List, classes it as a proof and rates its significance, if it holds up, as “Major math journal”. The page says that nothing on it is verified.
Each item identifies a statement, definition or report that needs further review. Its link opens a GitHub form with the source version already recorded.
Read the Lean statement against the paper
An AI agent drafted an assessment of which part of the paper this Lean statement expresses. No named human review is recorded.Open the form
Identify the theorem the catalogue describes
Family 342The theorem shown was selected from shared wording with OpenAI’s description. Atlas records no review confirming that it is the theorem the description means.Open the form
Address a question raised in an independent assessment
The challenge statements imply the headline claim after unpacking definitions or one routine step.
Their method
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.
The challenge statements state the headline as OpenAI wrote it.
Their method
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…
Re-run through Comparator in a sandboxed virtual machine: accepted.
Date
8 October 2026
Version
at the release’s recorded version
Their method
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.