AI4Math

4core

19adjacent

67downweighted

0warnings

Today's Scan

Start with When Does Structured Knowledge Help Neural Theorem Proving?, then Zero-Storage Procedural Neural Synthesis via Boundary Dynamics: Formal Verification in Lean 4 and Bare-Metal Gauntlet Validation. 23 fresh useful item(s) are inside the 21-day content window.

Source Mix

arXiv22
GitHub1

Best Use

Open only the first lane during a busy morning. Older recurring seeds are kept below the daily scan instead of competing with fresh items.

Start Here

The top few items most likely to matter for formal proof agents or Lean-facing AI4Math work.

core score 6.5 2026-09-28 arXiv

When Does Structured Knowledge Help Neural Theorem Proving?

Sareh Nabi, Roland Vogl, Marzieh Nabi

Does structured mathematical knowledge help LLMs prove theorems in Lean 4? If so, for which models, and does the answer vary by problem? Formal libraries such as Mathlib encode 285,000+ verified theorems with syntactic dependencies, but the semantic layer m...

Why it matters Infrastructure signal: this may improve premise discovery, dependency retrieval, or library navigation for agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Read if you have 5 minutes and want a direct AI4Math signal.

Lean proof agentsmathlib search

Open PDF Semantic Scholar

core score 6.5 2026-09-27 arXiv

Zero-Storage Procedural Neural Synthesis via Boundary Dynamics: Formal Verification in Lean 4 and Bare-Metal Gauntlet Validation

Volkan Dağlı, Zerrin Dağlı, Dağhan Dağlı

Contemporary neural inference architectures rely on dense floating-point weight matrices stored in high-bandwidth memory (VRAM), incurring severe memory-wall bottlenecks and preventing native execution inside deterministic virtual machines like the Ethereum...

Why it matters Most relevant if you are tracking proof-search loops that use verifier feedback instead of treating Lean as a binary oracle.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Read if you have 5 minutes and want a direct AI4Math signal.

Lean proof agentsverifier feedback

Open PDF Semantic Scholar

core score 6.5 2026-09-26 arXiv

Formalising Linear Elliptic PDE Theory in Lean 4

Alejandro José Soto Franco, Kobe Marshall-Stevens

We formalise in Lean 4, on top of Mathlib, the solvability of the Dirichlet problem for second-order linear elliptic operators in divergence form. The machine-verified results, with no sorry in the development, include the Poincaré inequality, the existence...

Why it matters Infrastructure signal: this may improve premise discovery, dependency retrieval, or library navigation for agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Read if you have 5 minutes and want a direct AI4Math signal.

Lean proof agentsmathlib search

Open PDF Semantic Scholar

Worth Opening

Good candidates after the first three. These are plausible paper-tab opens, not a mandatory reading list.

core score 6.5 2026-09-25 arXiv

Choir: An Open Protocol for Distributed Multi-Agent Autoformalization

Yidi Qi, Melanie Weber

AI agents can now formalize entire textbooks and major theorems in proof assistants such as Lean, but current efforts are typically centralized: a single team runs all agents and bears the full computational cost. We introduce Choir, an open protocol for di...

Why it matters Useful for the informal-to-formal bottleneck: it is about preserving mathematical intent across the translation boundary.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Read if you have 5 minutes and want a direct AI4Math signal.

autoformalizationLean proof agents

Open PDF Semantic Scholar

adjacent score 4.9 2026-09-26 arXiv

Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation

Hantao Yu, Sandy Han, Udaya Ghai et al.

On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the teacher is conditioned on privileged information, and the goal is to minimize the Kullback-L...

Why it matters Useful for the informal-to-formal bottleneck: it is about preserving mathematical intent across the translation boundary.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

autoformalizationRL or distillation

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-28 arXiv

Session Type State Spaces Form Lattices

Alexandre Zua Caldeira

We prove that the state space of every well-formed session type, quotiented by strongly connected components, forms a bounded lattice; n-ary parallel composition yields product lattices. Two consequences follow: duality preserves the lattice up to isomorphi...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim the task definition, metric, and whether the benchmark has Lean-checkable artifacts.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-28 arXiv

Peppy: An AI-Assisted Workflow for Tight Convergence Analysis of Optimization Algorithms

Jaewook J. Suh, TaeHo Yoon, Edward Duc Hien Nguyen et al.

This paper presents Peppy, an AI-assisted workflow for discovering tight, analytic convergence proofs for first-order optimization algorithms. Generic approaches to using LLMs to conduct mathematical research target an unspecified, broad spectrum of problem...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim the search loop: proposal source, verifier call, retry strategy, and stopping rule.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-28 arXiv

Moments of random multiplicative functions with polynomial coefficients

Xinyu Wang

Let $f$ be a Steinhaus random multiplicative function and let $g$ be a polynomial of degree $d$. Write $S_N=N^{-1/2}\sum_{n\le N}f(n)\,e(g(n))$. We prove a quantitative dichotomy for the moments of $S_N$: for each integer $s\ge 2$, either $\mathbb{E}|S_N|^{...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-28 arXiv

Blackwell Boundaries

Shuo Li Liu

We give a finite simplex theorem. When the number of states equals the number of source signals and the source posterior likelihood-ratio vectors form a simplex, Blackwell dominance is characterized by a universal barycentric-coordinate condition. We also g...

Why it matters Infrastructure signal: this may improve premise discovery, dependency retrieval, or library navigation for agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-27 arXiv

More than 83.69% of the zeros of the Riemann zeta function are distinct

Kristian Muri Knausgård

The lower asymptotic proportion of distinct nontrivial zeros of the Riemann zeta function, counted with multiplicity, is at least $0.8369928814\ldots$. The previous bound was $0.83625\ldots$. As in the proof of that bound, an unconditional version of Montgo...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim the search loop: proposal source, verifier call, retry strategy, and stopping rule.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-27 arXiv

Formalization of the Galerkin Construction for the Two-Dimensional Navier--Stokes Equations in Lean

Weinan Wang

We formalize in Lean 4 the Galerkin construction of global Leray--Hopf weak solutions for the unforced two-dimensional Navier--Stokes equations on arbitrary bounded open domains with no-slip boundary conditions. For every initial datum in the solenoidal \(L...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-26 arXiv

Unit fractions with semiprime denominators: an elementary proof of Erdős Problem #306

Shisheng Li

We give an elementary proof that every positive rational number $a/b$ with $b$ squarefree is a finite sum of distinct unit fractions $1/n$, where each $n$ is a product of two distinct primes (Erdős Problem #306). After a reduction to small targets, we take...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

Watch Later

Adjacent formalization or infrastructure signals. Keep them in peripheral vision unless they match an active project.

adjacent score 3.5 2026-09-26 arXiv

The Same and Not the Same: A Machine-Checked Genealogy of Photochemical Theory

Junyi Gong, Zijie Qiu, Ben Zhong Tang

Chemistry's phenomenological theories multiply with its observables: the same physical reality is repeatedly named in different measurement contexts, and the relations among theories have never had an auditable carrier. Here we present PhotoLean, a machine-...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-26 arXiv

Predicting the Next State Is Not Enough: JEPA Representations for Lean Theorem Proving

Aarnav Choudhary

Neural theorem provers must both propose tactics and decide which valid successor states to explore. We study whether one-step Lean transitions provide a self-supervised signal for branch ordering. A JEPA-style model predicts latent successor representation...

Why it matters Most relevant if you are tracking proof-search loops that use verifier feedback instead of treating Lean as a binary oracle.

Skim cue Skim the search loop: proposal source, verifier call, retry strategy, and stopping rule.

Read if Save for later unless the title matches your current proof-agent work.

verifier feedback

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-26 arXiv

Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs

Jorryt de Jong, Stefan Moraca, Ettore Cesari et al.

Large Language Models (LLMs) are highly capable of natural language reasoning and appear to store a great deal of lexical knowledge, but it is still unclear how much of this knowledge they actually use when reasoning, and whether they use it in the right wa...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim the search loop: proposal source, verifier call, retry strategy, and stopping rule.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-26 arXiv

AltGDA Achieves Global $O(1/T)$ Ergodic Convergence in Matrix Games

Tianlong Nan, Garud Iyengar, Christian Kroer et al.

Alternating gradient descent-ascent (AltGDA) is a simple and practically effective method for solving finite two-player zero-sum matrix games. However, the theory of AltGDA remains limited: existing results either apply only to unconstrained settings or req...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim the search loop: proposal source, verifier call, retry strategy, and stopping rule.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-26 arXiv

A Transfer Tactic for Lean

Zhaoxi Chen, Daniel Raggi

Rewriting in proof assistants spans a strict hierarchy. Equational rewriting substitutes based on extensional equality; subequational rewriting substitutes based on homogeneous relations such as $\leq$ or $\subseteq$, justified by monotonicity lemmas; and g...

Why it matters Infrastructure signal: this may improve premise discovery, dependency retrieval, or library navigation for agents.

Skim cue Skim the task definition, metric, and whether the benchmark has Lean-checkable artifacts.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

adjacent score 3.5 2026-09-25 arXiv

The stacking number of a tree

John Fairfax-Ball

The stacking number of a graph is the least integer t >= 2 such that every configuration of t pebbles can be transformed by pebbling moves into a configuration supported on one vertex. We prove that, for every finite tree T with at least two vertices, this...

Why it matters Direct Lean signal: likely relevant to the formalization or theorem-proving environment around AI4Math agents.

Skim cue Skim which definitions entered Lean and whether the work adds reusable library surface.

Read if Save for later unless the title matches your current proof-agent work.

Lean proof agents

Open PDF Semantic Scholar

Older but Useful

0 relevant item(s) are outside the 21-day content window. Keep them for context, but do not let them drive today's scan.

No older useful items were retained in this run.

Downweighted 67 low-priority match(es), folded for daily reading.

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: test: re-enable the `grind_bitvec2` benchmark (#15408)

Leonardo de Moura

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim the task definition, metric, and whether the benchmark has Lean-checkable artifacts.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: perf: memoize the search path root of each package in `findOLean` (#15291)

Hongyu Ouyang

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim the search loop: proposal source, verifier call, retry strategy, and stopping rule.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: fix: sharing violation in the `Sym.Arith` normalizer (#15405)

Leonardo de Moura

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim only the changed subsystem and whether it affects your Lean workflow.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: fix: introduce `__`-prefixed binders as implementation details in `Sym.intros` (#15322)

Sebastian Graf

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim only the changed subsystem and whether it affects your Lean workflow.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: fix: avoid sharing bug in bv_decide (#15403)

Henrik Böving

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim only the changed subsystem and whether it affects your Lean workflow.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: feat: make codegen for ctorIdx O(1) (#15407)

Henrik Böving

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim only the changed subsystem and whether it affects your Lean workflow.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: feat: lattice lemmas and `PredTrans` rules for `do` notation (#15387)

Sebastian Graf

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim only the changed subsystem and whether it affects your Lean workflow.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

negative score 0.8 2026-09-29 GitHub

leanprover/lean4: feat: control-flow reduction in the `Sym.simp`-based `grind` normalizer (#15409)

Leonardo de Moura

Recent commit on leanprover/lean4.

Why it matters Toolchain signal: open only if the commit touches proof search, elaboration, tactics, Lake, or mathlib behavior you depend on.

Skim cue Skim only the changed subsystem and whether it affects your Lean workflow.

Read if Open only if you are debugging Lean or mathlib locally.

Open Semantic Scholar

Source Health

Warnings are preserved so failed sources do not silently disappear from the brief.

None