Paper Citation Record · LEDGER

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

As of 7 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2605.07148.

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

pith.paper-citation-record.v1
2605.07148 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-11T00:56:06.243890Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:23:00.372251Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T09:35:41.079576Z

Reference resolution

58 of 58 outbound references displayed

verified exact28
verified fuzzy25
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 08c3477f-89d2-4975-8896-0434b2e46ef6 · outbound

This paper cites Cognitive maps in rats and men.Psychological review, 55(4):189.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Cognitive maps in rats and men.Psychological review, 55(4):189

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.835669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0f1b2dc9-aa01-48ea-92ff-d63faf01c576 · outbound

This paper cites Oxford university press.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Oxford university press

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.864222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f6200967-202b-452d-8c8f-86f4c8d91f81 · outbound

This paper cites Non-euclidean navigation.Journal of Experimental Biology, 222(Suppl_1):jeb187971.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Non-euclidean navigation.Journal of Experimental Biology, 222(Suppl_1):jeb187971

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.776402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cd19fa2b-720d-4c83-96cd-69a6048d47bc · outbound

This paper cites Structuring knowledge with cognitive maps and cognitive graphs.Trends in cognitive sciences, 25(1):37–54.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Structuring knowledge with cognitive maps and cognitive graphs.Trends in cognitive sciences, 25(1):37–54

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.750044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 27281b9e-500c-480a-bf0e-caf4a31cd9d7 · outbound

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

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:00:55.062047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5155a600-edc0-47e2-8798-bfc8cfff8a9d · outbound

This paper cites Video-chatgpt: Towards detailed video understanding via large vision and language models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Video-chatgpt: Towards detailed video understanding via large vision and language models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.830776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ee7d748a-dd6c-4c90-a4d3-f1fe73c1ad7f · outbound

This paper cites GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.057963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ef9c6ca6-02f4-4ae1-ab5f-df39ffd73df5 · outbound

This paper cites SQA3D: Situated Question Answering in 3D Scenes.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models SQA3D: Situated Question Answering in 3D Scenes

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.089512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e743d46-bcb1-403b-86ee-2961d9043cd8 · outbound

This paper cites Reasoning paths with reference objects elicit quantitative spatial reasoning in large vision-language models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Reasoning paths with reference objects elicit quantitative spatial reasoning in large vision-language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.787266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 927ebeab-a5bc-4728-99de-eb2cbe62b1dc · outbound

This paper cites Spatial reasoning in multimodal large language models: A survey of tasks, benchmarks and methods.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Spatial reasoning in multimodal large language models: A survey of tasks, benchmarks and methods

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.110438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6b8a87e7-0520-4788-87c1-62fa8f53e181 · outbound

This paper cites Infinibench: Infinite benchmarking for visual spatial reasoning with customizable scene complexity.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Infinibench: Infinite benchmarking for visual spatial reasoning with customizable scene complexity

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.177210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e86367b-a397-4a40-bd3a-17dffc49096b · outbound

This paper cites Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.855459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85e2888c-989e-427a-b271-75f040e6cd36 · outbound

This paper cites Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.093786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 614fd597-f426-4038-920b-02175952746f · outbound

This paper cites Beyond semantics: Rediscovering spatial awareness in vision-language models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Beyond semantics: Rediscovering spatial awareness in vision-language models

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.140796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c2cc8c22-7df3-492c-83e6-ca6d44185f43 · outbound

This paper cites The Geometry of Categorical and Hierarchical Concepts in Large Language Models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:54.996003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c6a61006-fe26-4a2a-82bb-a79f507e37c3 · outbound

This paper cites Linear mechanisms for spa- tiotemporal reasoning in vision language models.arXiv preprint arXiv:2601.12626.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Linear mechanisms for spa- tiotemporal reasoning in vision language models.arXiv preprint arXiv:2601.12626

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.078944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5d1eb770-c5a5-4726-b3d8-4ce8a463a431 · outbound

This paper cites Visual symbolic mechanisms: Emergent sym- bol processing in vision language models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Visual symbolic mechanisms: Emergent sym- bol processing in vision language models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.074503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 49f331ee-9b96-4d8e-a761-040cd6933770 · outbound

This paper cites Analyzing the behavior of visual question answering models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Analyzing the behavior of visual question answering models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.821555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9bae1465-c803-42dc-adac-5b739f011eab · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answering.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Making the v in vqa matter: Elevating the role of image understanding in visual question answering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.797458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 037a3f59-e3e9-40d4-9a48-0538a26a2384 · outbound

This paper cites Vision Transformers Need More Than Registers.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Vision Transformers Need More Than Registers

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:00:55.183613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b3b7ce2-3770-4241-add7-677b6fecd296 · outbound

This paper cites Thinking in space: How multimodal large language models see, remember, and recall spaces.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Thinking in space: How multimodal large language models see, remember, and recall spaces

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.817349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a3c8bfe4-cf8e-4839-a798-c2f68178f098 · outbound

This paper cites Mindcube: Spatial mental modeling from limited views.arXiv e-prints, pages arXiv–2506.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Mindcube: Spatial mental modeling from limited views.arXiv e-prints, pages arXiv–2506

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.840123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 87938ae6-6ca2-4747-b61f-b550c280af50 · outbound

This paper cites arXiv preprint arXiv:2602.07082 (2026),https://arxiv.org/ abs/2602.070824.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models arXiv preprint arXiv:2602.07082 (2026),https://arxiv.org/ abs/2602.070824

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:00:55.121495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 181f7c00-1c9a-4297-9606-1a175e9b9ef2 · outbound

This paper cites Spatialrgpt: Grounded spatial reasoning in vision-language models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Spatialrgpt: Grounded spatial reasoning in vision-language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.850247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 338621f3-c352-40ec-801e-fa934f5f5090 · outbound

This paper cites Scaling spatial intelligence with multimodal foundation models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Scaling spatial intelligence with multimodal foundation models

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.013102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

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

This paper cites SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards.

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 2026-08-07T06:34:17.273281+00:00.

Observation 2d33efec-352e-454e-86c7-bb00797f260e · outbound

This paper cites Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:58:10.438799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37da16b4-2c4e-4f13-9efc-754e4fa9f5c7 · outbound

This paper cites Causal abstractions of neural networks.Advances in neural information processing systems, 34:9574–9586.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Causal abstractions of neural networks.Advances in neural information processing systems, 34:9574–9586

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.812012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b410ba3a-7c41-4aed-b402-320a88e5580e · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis.Advances in neural information processing systems, 33:12388–12401.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Investigating gender bias in language models using causal mediation analysis.Advances in neural information processing systems, 33:12388–12401

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.771191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b743b19c-20f2-4c89-b492-e9dba5bb284c · outbound

This paper cites Emergent linear representations in world models of self-supervised sequence models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Emergent linear representations in world models of self-supervised sequence models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.760153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cfd72f98-76e0-4803-b261-18f66a79e08b · outbound

This paper cites Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:43:10.747895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0c5c4716-1a45-4ccb-b2ce-10b46640e1ac · outbound

This paper cites Does object binding naturally emerge in large pretrained vi- sion transformers?.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Does object binding naturally emerge in large pretrained vi- sion transformers?

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.021812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cbe57a86-3ae8-4a3f-a2d5-0c3ca7acd9a5 · outbound

This paper cites SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:00:55.152020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 058cd24e-667c-4fd4-a396-ed5a7c8120bb · outbound

This paper cites Spatialvid: A large-scale video dataset with spatial annotations.arXiv preprint arXiv:2509.09676, 2025a.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Spatialvid: A large-scale video dataset with spatial annotations.arXiv preprint arXiv:2509.09676, 2025a

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.048555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4ef4ad3a-7120-4fda-a182-e177201cabc0 · outbound

This paper cites Qwen2.5-vl, January 2025.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Qwen2.5-vl, January 2025

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.803547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0bbd56e6-483b-4a62-8228-81bf73abc4eb · outbound

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

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:00:55.145785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6493fa68-41b8-4a0b-a46c-d4e7f916c00e · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Linear Representations of Sentiment in Large Language Models

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-15T12:43:06.705954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7813ad13-0ad4-425f-bb5b-dd6db8a09fc0 · outbound

This paper cites Linear spaces of meanings: compositional structures in vision-language models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Linear spaces of meanings: compositional structures in vision-language models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.825709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c4936031-72cf-45e6-bedf-49071b82a667 · outbound

This paper cites Deciphering personalization: Towards fine-grained explainability in natural language for personalized image generation models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Deciphering personalization: Towards fine-grained explainability in natural language for personalized image generation models

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.156748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 910488ed-2c93-4e9a-8e62-f61b379587e9 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:43:32.339354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9fe6844e-8149-443b-8446-9f62bf4d1938 · outbound

This paper cites On the Origins of Linear Representations in Large Language Models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models On the Origins of Linear Representations in Large Language Models

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:00:55.069345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cad0295a-cb29-49e2-b2e8-09af52fc21fc · outbound

This paper cites Line of Sight: On Linear Representations in VLLMs.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Line of Sight: On Linear Representations in VLLMs

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.043918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 203ca3fe-6312-480a-8f52-b33d225eff26 · outbound

This paper cites Interpreting clip with sparse linear concept embeddings (splice).Advances in Neural Information Processing Systems, 37:84298–84328.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Interpreting clip with sparse linear concept embeddings (splice).Advances in Neural Information Processing Systems, 37:84298–84328

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.766403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d0fdd4e-6d1a-4a93-9455-6b94734e17c1 · outbound

This paper cites Linear Spatial World Models Emerge in Large Language Models.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Linear Spatial World Models Emerge in Large Language Models

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:54.983163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc1baed4-e6aa-4312-a630-77e07bc6c1e4 · outbound

This paper cites Laplacian eigenmaps for dimensionality reduction and data representation.Neural computation, 15(6):1373–1396.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Laplacian eigenmaps for dimensionality reduction and data representation.Neural computation, 15(6):1373–1396

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.742602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 689aa3bb-4778-4f13-9d7f-a1543783fed9 · outbound

This paper cites ICLR: In-Context Learning of Representations.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models ICLR: In-Context Learning of Representations

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.026979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cabe0242-351e-46ee-8f59-8b5a6bfc806d · outbound

This paper cites Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps: An Interpretation and Potential Improvements.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps: An Interpretation and Potential Improvements

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.098204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5ec14619-68aa-49f3-8e0b-34c367b7f2d9 · outbound

This paper cites Learning Continually by Spectral Regularization.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Learning Continually by Spectral Regularization

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:00:54.975635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6d13ab07-fc8f-4fbc-8322-3c90687f59e2 · outbound

This paper cites Principal spectral regularization makes momentum surpass adam for llm training.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Principal spectral regularization makes momentum surpass adam for llm training

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.860201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 337f0e07-c135-47fd-a09f-8002e729bb5c · outbound

This paper cites Representation Learning on Graphs: Methods and Applications.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Representation Learning on Graphs: Methods and Applications

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:55.162225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 94272ea8-8158-4e44-879e-c6267b7de011 · outbound

This paper cites Semi-Supervised Classification with Graph Convolutional Networks.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Semi-Supervised Classification with Graph Convolutional Networks

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:00:55.187460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2d70da38-6d48-4dc0-9a45-ffe457edcad4 · outbound

This paper cites cognitive-map.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models cognitive-map

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.735211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5c985aba-b092-4bf8-8ed1-a8b7c7065b12 · outbound

This paper cites an unresolved cited work.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-05-16T00:51:59.868005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b09b197-e4c4-48ec-a358-ca4d05ba1cbe · outbound

This paper cites an unresolved cited work.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-05-16T00:51:59.807668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 65e336db-7681-45b7-82c0-613d46b187b9 · outbound

This paper cites Each row is rescaled to unit norm.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Each row is rescaled to unit norm

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.781489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c8697e43-b4f4-4bc0-8f19-1de257aafae3 · outbound

This paper cites Drop columns with diagonal |Rkk| below 10−6 of the maximum (rank-deficient class directions).

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Drop columns with diagonal |Rkk| below 10−6 of the maximum (rank-deficient class directions)

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.791989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 512bef4f-93ca-4709-b63c-60a3c64a58b3 · outbound

This paper cites Algorithm summary.The end-to-end per-step computation is: 1.Forward pass, capturingH ℓ ∈R B×T×d at each Dirichlet-target layer via forward hooks.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Algorithm summary.The end-to-end per-step computation is: 1.Forward pass, capturingH ℓ ∈R B×T×d at each Dirichlet-target layer via forward hooks

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.754920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 512158b3-f242-451b-a783-c838eca33480 · outbound

This paper cites For the residMulti variant, steps 1–8 run independently at 5 layers and step 9 averages the resulting ratios.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models For the residMulti variant, steps 1–8 run independently at 5 layers and step 9 averages the resulting ratios

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-16T00:51:59.844562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation b1f00412-5aeb-4dde-92e4-cf5cb283b46c · inbound

Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning cites this paper.

Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:41.081680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.