Paper Citation Record · LEDGER

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning

As of 23 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 3 inbound Pith citation observations for arXiv:2506.22992.

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

pith.paper-citation-record.v1
2506.22992 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:58:37.379278Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T12:36:11.078426Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T10:58:03.052533Z

Reference resolution

38 of 38 outbound references displayed

verified exact1
verified fuzzy12
unresolved24
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 71f23740-4ea8-4ae2-a79e-0af7cbfaf600 · outbound

This paper cites an unresolved cited work.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:58:41.559556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9fa65a6f-0b0e-4935-af59-a566ec7981ad · outbound

This paper cites Anthropic 3.7 Sonnet and Claude Code, February 2025.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Anthropic 3.7 Sonnet and Claude Code, February 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:41.290990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4f5f6aca-6f04-4582-be07-aa55778b7f15 · outbound

This paper cites Qwen2.5-VL Technical Report.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:33.986544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43c1e1de-217a-495a-8173-e0d12cd02b9f · outbound

This paper cites MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.062989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422157e4-ca34-4ad6-b4f8-e8ef67b7ff88 · outbound

This paper cites PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.130708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f54a1f99-d458-49a9-9f05-63dd9e28dbff · outbound

This paper cites ARC Prize 2024: Technical Report.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning ARC Prize 2024: Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.269063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5323a548-c734-40e9-8993-40418f0ad7da · outbound

This paper cites Gemini 2.5: Our most intelligent ai model, March 2025.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Gemini 2.5: Our most intelligent ai model, March 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:41.010124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9a3e58d5-1a21-4898-a77d-7353fc41a3bf · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.574883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55df135a-9ca6-4fe7-ad75-4bb19f440d8c · outbound

This paper cites Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.684819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c693bec8-60b6-4092-921f-bf9915a14cc7 · outbound

This paper cites GPT-4o System Card.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning GPT-4o System Card

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.765255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2716bc3-a7f7-4910-9384-6c2b08627fa4 · outbound

This paper cites OpenAI o1 System Card.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning OpenAI o1 System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.825803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe372b08-9ebb-4dca-aa95-6831c2dd48dd · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Gonzalez, Hao Zhang, and Ion Stoica

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.889981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e245580-1958-4103-8574-f3fe9b702aa8 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning LLaVA-OneVision: Easy Visual Task Transfer

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:34.952780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ffb2137-ebcc-4c47-9cbb-0734ca3f02e7 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 2022.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 2022

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:40.740212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 46cf99d3-70c3-4f9e-9e9d-078b3d5184c2 · outbound

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

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:35.147201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c65437ae-ec93-47bb-9010-2741d98050b0 · outbound

This paper cites Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:40.455987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 274fb955-24be-4beb-9356-a8f78aef8ce2 · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation, April.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning The llama 4 herd: The beginning of a new era of natively multimodal ai innovation, April

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:40.248399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0793762e-8e82-4f78-8a06-6029680aaf5c · outbound

This paper cites Introducing OpenAI o3 and o4-mini, April 2025.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Introducing OpenAI o3 and o4-mini, April 2025

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:40.005208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c907db30-c60b-4fd9-8b81-5d94405db144 · outbound

This paper cites BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:35.562229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f38f3e-bc2b-4c7f-b695-4de9a451878c · outbound

This paper cites Vision language models are blind.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Vision language models are blind

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:39.750746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8b828970-477b-4c7d-9a28-5ff816bebc27 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.Advances in Neural Information Processing Systems, 36: 68539–68551, 2023.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Toolformer: Language models can teach themselves to use tools.Advances in Neural Information Processing Systems, 36: 68539–68551, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:35.747438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f92bd1b7-0158-4d54-80f4-72785261939e · outbound

This paper cites Seed1.5-VL Technical Report.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Seed1.5-VL Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:35.866414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48a9cbf9-cc31-4456-864e-99662855b8f8 · outbound

This paper cites Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:39.570020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e773708e-4e7f-4d08-95e7-99412259d6b0 · outbound

This paper cites Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:36.058002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fed9c57-af9d-43bd-8859-6d95fb1569f6 · outbound

This paper cites Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:36.149678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d90fc2ee-d585-4bf2-8cd9-fcf0af9741d2 · outbound

This paper cites EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:36.240135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f228efe-7267-430d-8562-d590635a02cf · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Chain-of-thought prompting elicits reasoning in large language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:39.358129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8a3c70c4-92f9-4b4e-8c0b-9b1c00385ba8 · outbound

This paper cites A Surprising Failure? Multimodal LLMs and the NLVR Challenge.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning A Surprising Failure? Multimodal LLMs and the NLVR Challenge

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:58:37.600994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 90a30213-3e7f-4c12-b533-0f468969e11b · outbound

This paper cites Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:36.481400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3d11d3a-6604-48d1-baa9-841b5a36ad22 · outbound

This paper cites MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:39.068558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f53fbc16-76f0-4e1a-ac19-6bbe59c1d99f · outbound

This paper cites Critic-V: VLM critics help catch vlm errors in multimodal reasoning.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Critic-V: VLM critics help catch vlm errors in multimodal reasoning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:38.805419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b3704fd4-c091-4474-ad4e-862ce394f6cd · outbound

This paper cites V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:36.765386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a134556-4bf6-4279-8326-56b86a14e154 · outbound

This paper cites MiniGPT-4: En- hancing vision-language understanding with advanced large language models.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning MiniGPT-4: En- hancing vision-language understanding with advanced large language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:58:38.615545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8f2729da-216a-4dd5-b01d-af2c50343ca5 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:37.045728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b50949e8-86e1-4596-9e45-50394a21456a · outbound

This paper cites an unresolved cited work.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:58:38.377201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8d134b8d-b30a-4ce3-87f1-a0d7b8563ad6 · outbound

This paper cites an unresolved cited work.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:58:38.150195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c0e0c15f-2212-4f50-a1fa-3d90c62db8d3 · outbound

This paper cites Here is the converted 2D array: [array].

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Here is the converted 2D array: [array]

Reference 38

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T21:58:37.915242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fe4b42a5-6a7d-4595-a522-daf2aa9b585e · outbound

This paper cites an unresolved cited work.

MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T21:58:35.398934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 294a2766-7419-449c-aa47-d9c95d147ea8 · inbound

Forecasting Future Behavior as a Learning Task cites this paper.

Forecasting Future Behavior as a Learning Task MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T06:07:41.330244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98df79a8-d010-4b24-b290-71a7166aceaf · inbound

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning cites this paper.

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:58:03.053990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f89f6fef-cf17-449d-b882-b044d01dd1b0 · inbound

When Reasoning Narrows the Move: Diversity Collapse in LLM Game Play cites this paper.

When Reasoning Narrows the Move: Diversity Collapse in LLM Game Play MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T12:36:11.078426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.