Paper Citation Record · LEDGER

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

As of 21 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 6 inbound Pith citation observations for arXiv:2602.24173.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2602.24173 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:05:57.763677Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:18:57.472922Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation b4a44422-80b4-49ec-9128-de16d7991e5a · outbound

This paper cites First proof.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics First proof

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.148361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e302ccb0-f7e8-4004-967b-440bdb69e627 · outbound

This paper cites Fel’s conjecture on syzygies of numerical semigroups.arXiv preprint arXiv:2602.03716,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Fel’s conjecture on syzygies of numerical semigroups.arXiv preprint arXiv:2602.03716,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.615415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae5b453-b8a4-4110-bdcf-2ee28a0d2051 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.728815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb223fe-f231-4995-872c-325d810d418e · outbound

This paper cites Mathematical research with GPT-5: a Malliavin-Stein experiment.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Mathematical research with GPT-5: a Malliavin-Stein experiment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.919446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b6abe5-5624-4b03-9b09-ca2fc3f0c8e9 · outbound

This paper cites Project aletheia: Verifier-guided distillation of back- tracking for small language models.arXiv preprint arXiv:2601.14290,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Project aletheia: Verifier-guided distillation of back- tracking for small language models.arXiv preprint arXiv:2601.14290,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.031583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc79098-c4a3-4ac1-86f3-63d55d613da1 · outbound

This paper cites Semi-autonomous mathematics discovery with gemini: A case study on the erd\h {o} s problems.arXiv preprint arXiv:2601.22401,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Semi-autonomous mathematics discovery with gemini: A case study on the erd\h {o} s problems.arXiv preprint arXiv:2601.22401,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.105644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dd39d68-61f9-42c5-a67e-6b7a1480586d · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.217637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b11f53-8652-454d-89ae-f51e74600799 · outbound

This paper cites FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.402050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4df45a2d-1699-4b58-90ae-65099674c7b2 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Measuring Mathematical Problem Solving With the MATH Dataset

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.471045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 463fff06-97bf-4fc4-8513-52619fd05d02 · outbound

This paper cites Gemini 2.5 pro capable of winning gold at imo 2025.arXiv preprint arXiv:2507.15855,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Gemini 2.5 pro capable of winning gold at imo 2025.arXiv preprint arXiv:2507.15855,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.544138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e9d4597-38d2-4e48-b861-593460e336d3 · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.621707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8222b21f-bb37-4562-80e6-bb10c20254ca · outbound

This paper cites FIMO: A Challenge Formal Dataset for Automated Theorem Proving.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics FIMO: A Challenge Formal Dataset for Automated Theorem Proving

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.734724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8b06253-5a78-4153-b850-e996b538acd9 · outbound

This paper cites EternalMath: A Living Benchmark of Frontier Mathematics that Evolves with Human Discovery.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics EternalMath: A Living Benchmark of Frontier Mathematics that Evolves with Human Discovery

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.850393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c299cee-ab77-4d19-ba3b-1aeaa3a436e9 · outbound

This paper cites A New Approach Towards Autoformalization.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics A New Approach Towards Autoformalization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.925031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44806c9e-e9ac-4a7b-916d-e5f39cb499c4 · outbound

This paper cites Magistral.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Magistral

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.999962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 420d03a2-9d74-441d-a403-17f7909c3de9 · outbound

This paper cites Extremal descendant integrals on moduli spaces of curves: An inequality discov- ered and proved in collaboration with ai.arXiv preprint arXiv:2512.14575,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Extremal descendant integrals on moduli spaces of curves: An inequality discov- ered and proved in collaboration with ai.arXiv preprint arXiv:2512.14575,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.082986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e6a5a56-523d-4b27-ab0d-e3d05e2dcf9b · outbound

This paper cites Resolution of erd \h {o} s problem# 728: a writeup of aristotle’s lean proof.arXiv preprint arXiv:2601.07421,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Resolution of erd \h {o} s problem# 728: a writeup of aristotle’s lean proof.arXiv preprint arXiv:2601.07421,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.153967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0843425-eb41-4a5c-8872-974e20d21a22 · outbound

This paper cites Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.230480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb2768c-e514-4e27-9729-23ed8f151c19 · outbound

This paper cites Aristotle: IMO-level Automated Theorem Proving.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Aristotle: IMO-level Automated Theorem Proving

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.347754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe28aa3a-fe9e-4d03-8dbe-4ebbf99dc756 · outbound

This paper cites Uniqueness of the canonical reciprocal cost.arXiv preprint arXiv:2602.05753,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Uniqueness of the canonical reciprocal cost.arXiv preprint arXiv:2602.05753,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.389635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ccfd0b-1ad1-45a5-8e21-17c30ff436fd · outbound

This paper cites Benchmarking Benchmark Leakage in Large Language Models.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Benchmarking Benchmark Leakage in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.424441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eac8e4e-5ca0-47f2-8189-2041801c181c · outbound

This paper cites Realmath: A continuous benchmark for evaluating language models on research-level mathematics.arXiv preprint arXiv:2505.12575,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Realmath: A continuous benchmark for evaluating language models on research-level mathematics.arXiv preprint arXiv:2505.12575,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.481014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb11242e-4088-4b52-95ec-85022a328c70 · outbound

This paper cites MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.525719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f2f82f-4e04-4cea-ab55-ced4f98ea4b1 · outbound

This paper cites In natural language, one can cite for instance GSM8k Cobbe et al.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics In natural language, one can cite for instance GSM8k Cobbe et al

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.581966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 273c339d-f90d-4ed3-804a-2eb088a8f409 · outbound

This paper cites These benchmarks were often used to evaluate LLM capa- bilities to the point of being the staple of evaluation for mathematical abilities.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics These benchmarks were often used to evaluate LLM capa- bilities to the point of being the staple of evaluation for mathematical abilities

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.652609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf8406b6-1513-4047-8231-f648600ab3d5 · outbound

This paper cites A very large dataset of competition problems was created by the Numina project LI et al.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics A very large dataset of competition problems was created by the Numina project LI et al

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.696600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b16f78f-ae04-4493-a4d2-ee2ff5932a2f · outbound

This paper cites an unresolved cited work.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.740526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfb152b7-01a2-4982-a54b-3e17cb0c6bb4 · outbound

This paper cites It is worth mentioning that other benchmarks exist in formal language, also focusing on middle school to undergraduate level problems such as miniF2F Zheng et al.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics It is worth mentioning that other benchmarks exist in formal language, also focusing on middle school to undergraduate level problems such as miniF2F Zheng et al

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:57.763677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c804fa9-6c49-48b6-acbf-b8220346b0f3 · outbound

This paper cites Objective-Function Free Multi-Objective Optimization: Rate of Convergence and Performance of an Adagrad-like algorithm.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Objective-Function Free Multi-Objective Optimization: Rate of Convergence and Performance of an Adagrad-like algorithm

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.775362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4d33a85-59b1-4d0d-8c67-c684348360f9 · outbound

This paper cites Numina-lean-agent: An open and general agentic reasoning system for formal mathematics.arXiv preprint arXiv:2601.14027,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Numina-lean-agent: An open and general agentic reasoning system for formal mathematics.arXiv preprint arXiv:2601.14027,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:56.808051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f77057cf-3be0-4168-88c8-5e257064ae1c · outbound

This paper cites MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.301028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f178d5-08d6-4a96-8228-bbc78a47f290 · outbound

This paper cites PatternBoost: Constructions in Mathematics with a Little Help from AI.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics PatternBoost: Constructions in Mathematics with a Little Help from AI

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.466316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fc9ff95-a058-4bab-8b31-82b8715a7c66 · outbound

This paper cites Semantic search over 9 million mathematical theorems.arXiv preprint arXiv:2602.05216,.

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics Semantic search over 9 million mathematical theorems.arXiv preprint arXiv:2602.05216,

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-02T20:05:55.234189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6390744e-bf5f-4833-b8f9-ae9a27e484e0 · inbound

Matlas: A Semantic Search Engine for Mathematics cites this paper.

Matlas: A Semantic Search Engine for Mathematics LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-23T04:13:44.884775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 885b33b1-fbbf-463d-8208-520b4b720156 · inbound

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness cites this paper.

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-23T04:13:44.884775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bfbab266-10e3-4576-9ce2-eaa731f6d5b0 · inbound

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness cites this paper.

Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:45:06.686133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2bdf5c23-3566-46c9-9948-3e184d546ea8 · inbound

Mathematical Discovery in the Wild: AI-Guided Proofs in Banach Space Theory cites this paper.

Mathematical Discovery in the Wild: AI-Guided Proofs in Banach Space Theory LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T18:16:48.945820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09bfc06c-4615-4380-9c3b-14c7f4713fad · inbound

TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability cites this paper.

TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T15:30:26.831491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bfab0a4-9441-483f-8d3e-91a279737295 · inbound

TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability cites this paper.

TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-14T04:18:57.472922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.