Paper Citation Record · LEDGER

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities

As of 16 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2608.08964.

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

pith.paper-citation-record.v1
2608.08964 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:23:22.187734Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy33
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 33a46855-1266-4c2d-84dc-5278432360f9 · outbound

This paper cites NeurIPS Datasets Track (2024).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS Datasets Track (2024)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.873954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9763c1df-6b86-4974-bd6a-db97948869ef · outbound

This paper cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T04:23:22.047932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d43b2715-f41c-4f90-b167-93eecf573c87 · outbound

This paper cites ACL Findings (2021).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities ACL Findings (2021)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.779954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d80be691-aa1c-48dd-a77f-4c86d6ba155d · outbound

This paper cites CVPR (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities CVPR (2025)

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.694249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7678af81-10a5-4a22-84ff-ce0c58e49d55 · outbound

This paper cites L@S (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities L@S (2025)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.600714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fc4bd820-7541-49dd-864e-58d73488a29e · outbound

This paper cites NeurIPS (2024).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS (2024)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.521916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ef7024d5-58e0-4665-a9d4-4285a072e756 · outbound

This paper cites AIED (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities AIED (2025)

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.423490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fc8e6fb2-c4ba-453d-aeb4-0c6074fe7354 · outbound

This paper cites ACM MM (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities ACM MM (2025)

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.348207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 155c9a4b-00f6-4ead-a35a-e0be0f567328 · outbound

This paper cites NeurIPS Math-AI Workshop (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS Math-AI Workshop (2025)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.270606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 25201520-6564-4517-a8e6-6f43738893e1 · outbound

This paper cites IEEE ICCWAMTIP (2023).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities IEEE ICCWAMTIP (2023)

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.175173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e00eff3e-b91b-4ad9-b462-465828cd1d79 · outbound

This paper cites MagicGeo: Training-Free Text-Guided Geometric Diagram Generation.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities MagicGeo: Training-Free Text-Guided Geometric Diagram Generation

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-08-14T04:23:22.251474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f1ecc6d6-811c-4d88-943e-1ef1bf3cc6b4 · outbound

This paper cites CVPR (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities CVPR (2025)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:24.057829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c843705c-21f4-4204-8342-a08f23fb428f · outbound

This paper cites CVPR (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities CVPR (2025)

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.973820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 86cbf768-8c90-4861-8047-88743926239a · outbound

This paper cites NeurIPS Workshop (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS Workshop (2025)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.875353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bdec19bb-652c-46bc-b68b-936a546fc497 · outbound

This paper cites NeurIPS (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS (2025)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.815518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fdfbb0cf-521d-4a53-baed-6f5b17255b34 · outbound

This paper cites EMNLP (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities EMNLP (2025)

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.695357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4bd33df8-1d7f-4f8b-b1fa-5f888b28c442 · outbound

This paper cites ICML (2021).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities ICML (2021)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.615865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c5974e1c-51c3-4a27-9530-bbc70dc354fd · outbound

This paper cites NeurIPS (2017).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS (2017)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.540217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation af5e22a7-9df2-4735-afb4-8324de334803 · outbound

This paper cites SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T04:23:22.125330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a6c63ba-3e7d-447d-9c4b-1e555918f178 · outbound

This paper cites arXiv (2026).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities arXiv (2026)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.484658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b68b9b7d-7110-424e-9836-91acab9151c8 · outbound

This paper cites ICML (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities ICML (2025)

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.410933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1bcafea0-95fe-40a9-9866-d096d675f382 · outbound

This paper cites Under review ICLR (2026) 12 Kashyap et al.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities Under review ICLR (2026) 12 Kashyap et al

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.322317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9179f5e1-2a88-479d-b7f0-fe39b3f01afc · outbound

This paper cites NeurIPS (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS (2025)

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.250630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ba647c86-53fc-4375-a8be-33fea3a7163a · outbound

This paper cites ICLR (2024).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities ICLR (2024)

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.202125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 960d1567-20a6-4922-8b79-2b3e99bcc253 · outbound

This paper cites NeurIPS (2024).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities NeurIPS (2024)

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.124314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 872495fe-74ad-472a-839e-06c9bef0c310 · outbound

This paper cites ECCV (2024).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities ECCV (2024)

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.069039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation edb2dfd7-cd3f-479d-ad6f-a88d3f725501 · outbound

This paper cites CVPR (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities CVPR (2025)

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:23.010490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 935c51ed-bb27-4d10-b3bc-6580bbb284ba · outbound

This paper cites Findings of ACL (2021).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities Findings of ACL (2021)

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.948015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 94fe6757-e1d9-4c78-9b7f-92afcbe98067 · outbound

This paper cites CVPR (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities CVPR (2025)

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.898533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 98649c4d-78d1-47c0-9402-5eba1df6d14c · outbound

This paper cites EMNLP (2025).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities EMNLP (2025)

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.819107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5087e679-857b-4c39-9de6-703550e986d8 · outbound

This paper cites IEEE TPAMI (2020).

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities IEEE TPAMI (2020)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.748288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation feb624aa-21cc-4d46-a8d3-9aa400b8fa8b · outbound

This paper cites draw in latex/xml a circle inscribed in a triangle with all of its sides being a tangent.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities draw in latex/xml a circle inscribed in a triangle with all of its sides being a tangent

Reference 32

Resolution: malformed identifier; raw_fallback, observed 2026-08-14T04:23:22.660574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0c9b9edb-0a02-4f3c-9a65-588d97f387b0 · outbound

This paper cites Model selection depends on which property matters most for a given application.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities Model selection depends on which property matters most for a given application

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.574539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 68adfa70-4b0c-483c-969d-67bc2071497e · outbound

This paper cites In a production pipeline, the combination of high quality and low reliability may be worse than a model with moderate quality and high reliability.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities In a production pipeline, the combination of high quality and low reliability may be worse than a model with moderate quality and high reliability

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.511494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 05070c88-8aab-4caf-982b-3c5421c6efe6 · outbound

This paper cites The Nano Banana models are perceptually competitive but fall short on edge overlap, suggesting that explicit geometric primitives in code still matter for mathematical precision.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities The Nano Banana models are perceptually competitive but fall short on edge overlap, suggesting that explicit geometric primitives in code still matter for mathematical precision

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.445157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5e1a25e5-ce92-4f6a-9dbb-82cf4aaf8be3 · outbound

This paper cites Future work on diagram generation should target these underperforming categories specifically.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities Future work on diagram generation should target these underperforming categories specifically

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.378080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0e924c43-237e-41c4-b243-e0b458e528fa · outbound

This paper cites We hypothesize that its extended chain-of-thought reasoning, while beneficial for problem solving, may actively hurt code generation by producing overly complex output.

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities We hypothesize that its extended chain-of-thought reasoning, while beneficial for problem solving, may actively hurt code generation by producing overly complex output

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:23:22.308072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.