Paper Citation Record · LEDGER

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

As of 14 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 8 inbound Pith citation observations for arXiv:2509.26076.

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

pith.paper-citation-record.v1
2509.26076 v2

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:37:32.560955Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:18:03.059645Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T20:47:34.576528Z

Reference resolution

12 of 12 outbound references displayed

verified exact0
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0a0b2507-5364-45d0-b760-f35a7f8848f4 · outbound

This paper cites auto" max tokens=32000 reasoningtokens=31000 GPT-5gpt-5 reasoning effort=.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation auto" max tokens=32000 reasoningtokens=31000 GPT-5gpt-5 reasoning effort=

Reference 3

Resolution: malformed identifier; no resolver link, observed 2026-08-04T13:37:32.491188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 859ddf17-b539-4bd9-aaf0-85183824d9cb · outbound

This paper cites True”, “False.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation True”, “False

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.486780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c497c22-3734-4a45-91c4-60d6ae89c9cd · outbound

This paper cites Underlying system is ArchLinux with many standard open-source computer algebra systems (like GAP) pre-installed.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Underlying system is ArchLinux with many standard open-source computer algebra systems (like GAP) pre-installed

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.527322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1793932a-450d-4f67-8f15-7aec79b04cdf · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.531671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab2dc781-301c-4951-8797-eb55724f477c · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.536767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed45ed3d-7901-4e1b-a2b2-daf658740686 · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.540729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b91531d-a425-4294-a01d-215f96e14b7a · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.544745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a13de7cd-8341-4d60-9d74-722221a2b506 · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.548634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9b8500a-a5ff-4292-ad51-64bca15661ea · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.553254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e86454a3-6f74-44f0-86a9-23feabeadd4b · outbound

This paper cites an unresolved cited work.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.557052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0bebd92-ee2c-4141-ab8c-a4915d36f924 · outbound

This paper cites Automorphismsˆ2: {G.automorphism_number()ˆ2}.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation Automorphismsˆ2: {G.automorphism_number()ˆ2}

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.560955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0223ef71-1371-4e6e-be0e-a8e68dc2a275 · outbound

This paper cites MathArena: Evaluating LLMs on Uncontaminated Math Competitions.

IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation MathArena: Evaluating LLMs on Uncontaminated Math Competitions

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T13:37:32.480041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1f8abaf7-22a3-46b4-8828-108f2c723af3 · inbound

QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs cites this paper.

QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T21:18:03.059645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7557716-135e-44c1-8d77-199091052b5e · inbound

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs cites this paper.

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-10T02:19:32.479333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f01528dd-f169-4bd6-a94c-d75730cf07d8 · inbound

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs cites this paper.

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-10T02:19:32.479333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ea917522-b376-4351-a2bc-241d004cb161 · 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 IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 6

Resolution: malformed identifier; arxiv_id, observed 2026-07-10T02:19:32.479333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8cad4ab0-97cb-45f3-aafb-bbed3f1ae5b1 · 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 IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 6

Resolution: malformed identifier; arxiv_id, observed 2026-07-10T02:19:32.479333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b357d459-e2a5-4e25-a717-66f7bdb4f7cf · inbound

Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation cites this paper.

Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T02:19:32.479333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1f328be5-23e9-4f65-acc4-f99081908c3c · inbound

Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics cites this paper.

Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T20:47:34.577936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6b684b02-1c91-4de6-8725-708a62daab8b · 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 IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T18:16:49.376545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.