Paper Citation Record · LEDGER

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

As of 6 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 14 inbound Pith citation observations for arXiv:2511.07403.

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

pith.paper-citation-record.v1
2511.07403 v2

Coverage vector

measured 61 of 61 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T23:08:57.431844Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 14 of 14 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T05:12:59.576553Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-05T01:50:34.827326Z

Reference resolution

61 of 61 outbound references displayed

verified exact0
verified fuzzy0
unresolved61
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c89204c0-a66f-433b-9146-90382ced24ee · outbound

This paper cites SpatialBot: Precise Spatial Understanding with Vision Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards SpatialBot: Precise Spatial Understanding with Vision Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.001243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78df0953-2684-4d92-a73a-77feec1f572f · outbound

This paper cites The final set consists of 50% samples from the relation category, and the remaining 50% distributed across the eight other categories.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards The final set consists of 50% samples from the relation category, and the remaining 50% distributed across the eight other categories

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.351341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 754c7e6f-e5aa-4259-9b5c-544b0f9bf65d · outbound

This paper cites MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.211667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b75dce60-90e9-4b68-b252-93ff18ef8dd0 · outbound

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

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.319147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4106c95-603e-4526-b91a-3109f8fdc443 · outbound

This paper cites Kimi-VL Technical Report.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Kimi-VL Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.425505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80da89b1-98fb-43e9-8400-1d37f0472ea6 · outbound

This paper cites BLINK: Multimodal Large Language Models Can See but Not Perceive.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards BLINK: Multimodal Large Language Models Can See but Not Perceive

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.532620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691282a9-ed0d-4b96-9c9b-afde5300dec0 · outbound

This paper cites Xia, Ted Xiao, Jiajun Wu, Brian Ichter, Anirudha Majumdar, and Dorsa Sadigh.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Xia, Ted Xiao, Jiajun Wu, Brian Ichter, Anirudha Majumdar, and Dorsa Sadigh

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.752446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec25f26-b34a-410d-8b88-9f51e742458a · outbound

This paper cites Tenenbaum, Antonio Torralba, Florian Shkurti, and Liam Paull.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Tenenbaum, Antonio Torralba, Florian Shkurti, and Liam Paull

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.905731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00d6395-04a7-43f8-a724-3c149d321124 · outbound

This paper cites an unresolved cited work.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:50.006008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e990fd-39a4-40b1-a9fa-b3e215801bea · outbound

This paper cites Scene Graph Reasoning for Visual Question Answering.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Scene Graph Reasoning for Visual Question Answering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:50.161728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684ffb9a-8e32-4797-9e20-825ddc225477 · outbound

This paper cites Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:50.379903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ed267b-4d82-460f-8344-e74390229a56 · outbound

This paper cites Visual language maps for robot navigation.2023 IEEE International Conference on Robotics and Automation (ICRA), pp.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Visual language maps for robot navigation.2023 IEEE International Conference on Robotics and Automation (ICRA), pp

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:50.569283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12199c74-cd1d-47a9-8c57-0bec1d2b0098 · outbound

This paper cites $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:51.090448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a74d0c71-6a7e-4dac-b709-2950e1d0698a · outbound

This paper cites What's "up" with vision-language models? Investigating their struggle with spatial reasoning.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards What's "up" with vision-language models? Investigating their struggle with spatial reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:51.252391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b651970-7826-49d1-aa5a-51902c38b2e3 · outbound

This paper cites VR-GPT: Visual Language Model for Intelligent Virtual Reality Applications.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards VR-GPT: Visual Language Model for Intelligent Virtual Reality Applications

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:51.434311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc975e27-dd5f-468e-ae0f-9bf2ba40cd60 · outbound

This paper cites Relation-r1: Progressively cognitive chain-of-thought guided reinforcement learning for unified relation comprehension.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Relation-r1: Progressively cognitive chain-of-thought guided reinforcement learning for unified relation comprehension

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:51.695890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83870d2b-27e4-4637-b5e3-c217f810ec08 · outbound

This paper cites Visual Instruction Tuning.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Visual Instruction Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:51.834140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0747c495-7def-4a55-b911-31dd296e47ba · outbound

This paper cites Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:52.041071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c891422c-6e37-45f5-bffc-9d02a50b97e0 · outbound

This paper cites SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:52.208502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a06ed670-65f6-48a4-991d-add349d902c4 · outbound

This paper cites SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:52.541313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e759782-f9f9-4f57-9c33-1ef2fafb3c75 · outbound

This paper cites LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:52.730617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f39ec1f3-04ff-4a4c-9c30-c8683155be63 · outbound

This paper cites Kosmos-2: Grounding Multimodal Large Language Models to the World.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:52.900128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7353cbc-a74a-4f24-9d51-4d6adfe96c72 · outbound

This paper cites Tuning computer vision models with task rewards.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Tuning computer vision models with task rewards

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.063278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b5eb21f-d1d3-4ea5-b9d0-0162255ccabd · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.181240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45e8f9db-be2d-4c7d-aa71-c9aac05fda5d · outbound

This paper cites Satori-r1: Incentivizing multimodal reasoning with spatial grounding and verifiable rewards.ArXiv, abs/2505.19094, 2025a.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Satori-r1: Incentivizing multimodal reasoning with spatial grounding and verifiable rewards.ArXiv, abs/2505.19094, 2025a

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.286554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b7a79e8-c0f5-47b5-9ddd-417b685a1554 · outbound

This paper cites LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.435983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18eb29e9-b2f6-43ac-bd47-c68f2c47f2f7 · outbound

This paper cites Gemini Robotics: Bringing AI into the Physical World.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Gemini Robotics: Bringing AI into the Physical World

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.597396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2c0cf1-8d70-4105-b250-082a05566d2f · outbound

This paper cites Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.784146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184ba021-4085-4680-adac-263da207cb1b · outbound

This paper cites Learning 3d semantic scene graphs from 3d indoor reconstructions.2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Learning 3d semantic scene graphs from 3d indoor reconstructions.2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:53.880851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f1a966-d0d5-4fa1-b6ae-f49e5e29be33 · outbound

This paper cites SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.014934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bcb050c-f830-470d-bf5e-a9fb35ed203d · outbound

This paper cites Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.150077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ab87b4-c715-4fd4-a794-66a83e21b3ac · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.313086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ddaedc-c736-4ea3-8d8d-1ca4bb035de5 · outbound

This paper cites V*: Guided visual search as a core mechanism in multimodal llms.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards V*: Guided visual search as a core mechanism in multimodal llms.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.436266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb66f52d-fd70-4f0a-8f51-9b80d47b2c4f · outbound

This paper cites Zang, Peng Gao, Yixuan Li, and Kaiyang Zhou.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Zang, Peng Gao, Yixuan Li, and Kaiyang Zhou

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.579374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1e0177b-f4a2-4bee-8e91-f8ccc98bf475 · outbound

This paper cites Advancing multimodal reasoning capabilities of multimodal large language models via visual perception reward.ArXiv, abs/2506.07218,.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Advancing multimodal reasoning capabilities of multimodal large language models via visual perception reward.ArXiv, abs/2506.07218,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.699568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da96a50-0811-4637-a97e-afca4a1a2534 · outbound

This paper cites Evaluating Spatial Understanding of Large Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Evaluating Spatial Understanding of Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.820458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097102b2-558c-4e44-b174-d754c5e13c78 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.096964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e378c4c-a10a-4695-a5af-ca05f8850fde · outbound

This paper cites RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.221065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 872c63a0-cae0-4106-8105-33e54e94d821 · outbound

This paper cites MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.368717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741f7457-e977-48e8-906b-26677e10b43a · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.516798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30ad8c8b-2656-4860-81cc-30be0e6f4a53 · outbound

This paper cites The doubly librating Plutinos.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards The doubly librating Plutinos

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.631675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d1af005-a726-46b2-94d0-6c2d3323fdb6 · outbound

This paper cites R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.751893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a3f40e-dfc0-4bbe-9685-9adb8bd9b6bf · outbound

This paper cites Struct2d: A perception-guided framework for spatial reasoning in large multimodal models.ArXiv, abs/2506.04220,.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Struct2d: A perception-guided framework for spatial reasoning in large multimodal models.ArXiv, abs/2506.04220,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:55.911489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a89eb08-1985-4207-a103-1cbe9ea12b18 · outbound

This paper cites an unresolved cited work.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.091197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb9456ff-e1b5-41a9-948e-44ef2f8846f9 · outbound

This paper cites an unresolved cited work.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.235392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5831bdf6-d86d-49f3-89c5-382b79c9af35 · outbound

This paper cites These serve as upper bounds for spatial generalization under non-public training regimes.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards These serve as upper bounds for spatial generalization under non-public training regimes

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.662635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01525c57-1a31-4dfa-85e1-b4bd8224ac02 · outbound

This paper cites an unresolved cited work.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.802456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f535576d-f97a-44fe-b75b-e468cb08611c · outbound

This paper cites an unresolved cited work.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:57.144009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004f16b0-dabe-41d0-a4de-48ae173b8d56 · outbound

This paper cites aha moment.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards aha moment

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:57.290068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 392b51f9-2491-4a61-94b4-539e7c057893 · outbound

This paper cites In contrast, Huang et al.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards In contrast, Huang et al

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:57.431844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cb75062-c408-4e15-b1be-f34b8d972534 · outbound

This paper cites Training time totals around 13 hours for the 3B model and 15 hours for the 7B model.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Training time totals around 13 hours for the 3B model and 15 hours for the 7B model

Reference 128

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.468585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4a28644-7eea-4469-ab5b-f78d4e3d5ea8 · outbound

This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:54.932557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6be8b81c-1b5a-44a9-849b-a13e185874eb · outbound

This paper cites TopViewRS: Vision-Language Models as Top-View Spatial Reasoners.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards TopViewRS: Vision-Language Models as Top-View Spatial Reasoners

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:51.560457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc46fea0-5a8f-4cd9-8c99-16b686b37315 · outbound

This paper cites GPT-4o System Card.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards GPT-4o System Card

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:50.963202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a184775b-87aa-4aad-b5e2-e31d00093f42 · outbound

This paper cites Scene Graph Generation with Role-Playing Large Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Scene Graph Generation with Role-Playing Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.079544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ace252f-c4e0-4843-b1d3-24b59dcc3d43 · outbound

This paper cites PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:52.414897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850b4d05-8185-4f29-8c22-664b61f7907f · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:50.746629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e1f95ee-15d3-4f39-ab9a-a06880eb7999 · outbound

This paper cites Compile Scene Graphs with Reinforcement Learning.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Compile Scene Graphs with Reinforcement Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.130584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 984968e4-4ccf-46c3-bc48-db3fe18d1771 · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:49.679221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba40aad-bee4-4534-b73c-9358d4f9d998 · outbound

This paper cites Qwen2.5-VL Technical Report.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards Qwen2.5-VL Technical Report

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:48.929476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3412f57a-a493-4f14-a5ce-f65aa372c0f5 · outbound

This paper cites For models with spe- cific reasoning templates such as VLAA-Thinker, SpaceThinker, and SpaceOm, we utilize their corresponding structured prompts.

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards For models with spe- cific reasoning templates such as VLAA-Thinker, SpaceThinker, and SpaceOm, we utilize their corresponding structured prompts

Reference 2048

Resolution: unresolved; no resolver link, observed 2026-08-03T23:08:56.979052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6d737bce-47ec-4e2c-8b49-03e8735a432b · inbound

SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence cites this paper.

SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34996bd8-253e-4ffe-b57e-554946a45837 · inbound

VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations cites this paper.

VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T23:42:44.515158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc44c71c-409f-4383-b157-2cb6a8ac337c · inbound

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning cites this paper.

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c9708611-744c-4878-a6f2-9b9a02fc20ed · inbound

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning cites this paper.

SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ca4585f3-9bbd-455f-99f5-b88ee5681fbf · inbound

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models cites this paper.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7b3f3a60-4cf2-4ab3-a2cc-181b3a92d60b · inbound

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models cites this paper.

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b770fcad-f881-40ee-942e-4d520cea9eb5 · inbound

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving cites this paper.

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 38dfe81d-c142-4e66-b0af-0bf30c46bbe1 · inbound

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving cites this paper.

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0bb8841c-5d38-4287-be56-530b505ae253 · inbound

Rethinking VLM Representation for VLA Initialization cites this paper.

Rethinking VLM Representation for VLA Initialization SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c29adb50-0f1a-4caa-b011-fe7216da0b91 · inbound

OneCanvas: 3D Scene Understanding via Panoramic Reprojection cites this paper.

OneCanvas: 3D Scene Understanding via Panoramic Reprojection SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 11d137df-2567-4086-9f64-d5816779820b · inbound

OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping cites this paper.

OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-07-07T01:16:00.407423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f5472762-4fe3-4c0a-b2ec-3df3a4fd17b6 · inbound

GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement cites this paper.

GReFEM: Multimodal LLMs as Zero-Shot Semantic Assistants for Physics-Guided 3D Mesh Refinement SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T06:42:45.558324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f830fba-1192-4c41-a984-bf514729bb13 · inbound

GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding cites this paper.

GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T05:12:59.576553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795b0743-653f-439a-b168-6fc537821dbe · inbound

Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models cites this paper.

Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T08:34:11.633653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.