Paper Citation Record · LEDGER

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

As of 9 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2607.21072.

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

pith.paper-citation-record.v1
2607.21072 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T08:39:41.730369Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T00:54:58.326785Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T00:54:58.682244Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 751917e2-5586-4b9f-ab71-c3993b054f13 · outbound

This paper cites GPT-4 Technical Report.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:36.172840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa48be1d-8c24-4979-8ea7-c6e4f7a090c1 · outbound

This paper cites Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:36.595969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfe40d53-b601-4d15-800a-1e0873088288 · outbound

This paper cites Emu3.5: Native Multimodal Models are World Learners.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Emu3.5: Native Multimodal Models are World Learners

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:36.784561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c8bbc7-3954-478e-bafd-bb833e4922bd · outbound

This paper cites VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.227319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0450b52d-99f1-4deb-9547-b9dc204e2f84 · outbound

This paper cites Image Generators are Generalist Vision Learners.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Image Generators are Generalist Vision Learners

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.393050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6856bfed-fbff-426f-83f5-a7da9ed8eca5 · outbound

This paper cites RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.870420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df4d622e-7669-45e5-9a32-dddcb688a954 · outbound

This paper cites Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models.arXiv preprint arXiv:2506.03135 ,.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models.arXiv preprint arXiv:2506.03135 ,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:38.021033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3097d538-4df7-47cd-8105-22a90588c10a · outbound

This paper cites Joyai-image: Awakening spatial intelligence in unified multimodal understanding and generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Joyai-image: Awakening spatial intelligence in unified multimodal understanding and generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:38.201400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc3edf69-dad9-4353-8630-c22152300c63 · outbound

This paper cites FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:38.403605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61260bf7-9534-4614-98bc-bd70f4d3562e · outbound

This paper cites GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:38.560857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b15d9875-5b1b-46dc-bf3f-38f2e4209192 · outbound

This paper cites Viewspatial-bench: Evaluating multi-perspective spatial localization in vision-language models.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Viewspatial-bench: Evaluating multi-perspective spatial localization in vision-language models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:38.723115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bacd8e71-3b47-47d5-a705-9188e002bd1c · outbound

This paper cites Ssr: Enhancing depth perception in vision-language models via rationale-guided spatial reasoning.arXiv preprint arXiv:2505.12448,.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Ssr: Enhancing depth perception in vision-language models via rationale-guided spatial reasoning.arXiv preprint arXiv:2505.12448,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:38.919903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ecfc0cc-3e16-461d-aa21-0829e0c2e238 · outbound

This paper cites SpaceR: Reinforcing MLLMs in Video Spatial Reasoning.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.240342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32aad53a-00ba-4532-a80a-cc3a6becb46d · outbound

This paper cites Sat: Dynamic spatial aptitude training for multimodal language models.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Sat: Dynamic spatial aptitude training for multimodal language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.342345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f54c391-f3e8-4db5-8355-8b6c97d1afbc · outbound

This paper cites Seedream 4.0: Toward Next-generation Multimodal Image Generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Seedream 4.0: Toward Next-generation Multimodal Image Generation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.437251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3e6dab-3e1f-4d8f-a056-01001d16d180 · outbound

This paper cites Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.509832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf7b80b-6f2e-4bb7-b642-502c0a25c831 · outbound

This paper cites Yingbo Tang, Lingfeng Zhang, Shuyi Zhang, Yinuo Zhao, and Xiaoshuai Hao.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Yingbo Tang, Lingfeng Zhang, Shuyi Zhang, Yinuo Zhao, and Xiaoshuai Hao

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.626649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4eb2e2-0fdc-4ac0-ab67-deb7ac899a1d · outbound

This paper cites org/10.1145/3746027.3758209.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text org/10.1145/3746027.3758209

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.740636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1a2063d-680f-4928-86e8-7520052c9167 · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.852110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 162d9b19-9942-4e80-a14c-7f2a8ed002b9 · outbound

This paper cites Mindcube: Spatial mental modeling from limited views, 2026a.https://arxiv.org/abs/2506.21458.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Mindcube: Spatial mental modeling from limited views, 2026a.https://arxiv.org/abs/2506.21458

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:39.988118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b4fefa-9314-4d1d-8710-b28411d75609 · outbound

This paper cites Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:40.120708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d49f14-f828-49f3-b6b7-335078e0de3d · outbound

This paper cites Qiucheng Wu, Handong Zhao, Michael Saxon, Trung Bui, William Yang Wang, Yang Zhang, and Shiyu Chang.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Qiucheng Wu, Handong Zhao, Michael Saxon, Trung Bui, William Yang Wang, Yang Zhang, and Shiyu Chang

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:40.241042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2253254-bb0b-4b8b-b93a-96a24195c4dd · outbound

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

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:40.396402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d395aebd-a326-4e01-9ce4-ee26ee7bef62 · outbound

This paper cites Sphere: Unveiling spatial blind spots in vision-language models through hierarchical evaluation.ACL, 2025a.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Sphere: Unveiling spatial blind spots in vision-language models through hierarchical evaluation.ACL, 2025a

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:40.520878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a094702-8da5-4b8d-b8e7-8868f3660ee5 · outbound

This paper cites GEM: Generative Supervision Helps Embodied Intelligence.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text GEM: Generative Supervision Helps Embodied Intelligence

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:40.704498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 275e632a-55d9-4624-9b16-655157e579a5 · outbound

This paper cites Roborefer: Towards spatial referring with reasoning in vision-language models for robotics.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Roborefer: Towards spatial referring with reasoning in vision-language models for robotics

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:40.853401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 719611ca-6e89-463f-8885-d5f9cfc487d4 · outbound

This paper cites • Appendix B documents data sources, schema, and quality control.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text • Appendix B documents data sources, schema, and quality control

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:41.054054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f07522-73ef-4bab-822e-ab3c1a7b9294 · outbound

This paper cites GPT-5.4 OpenAI-compatible chat API; request model gpt-5.4; direct structured answer; deterministic request settings where supported.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text GPT-5.4 OpenAI-compatible chat API; request model gpt-5.4; direct structured answer; deterministic request settings where supported

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:41.232662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80b07f73-2746-4696-a9e8-5840ce7f5e30 · outbound

This paper cites VLM-3R-7B; SpatialRGPT-8B; Spatial-MLLM; SpatialBot-3B (Fan et al., 2025; Cheng et al., 2024; Wu et al., 2025b; Cai et al.,.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text VLM-3R-7B; SpatialRGPT-8B; Spatial-MLLM; SpatialBot-3B (Fan et al., 2025; Cheng et al., 2024; Wu et al., 2025b; Cai et al.,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:41.411567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6a9c072-c79c-434e-83f4-5eeea6c1547f · outbound

This paper cites SenseNova-Vision-7B-MoT; Janus-Pro-7B; Janus-1.3B (Han et al., 2026; Chen et al., 2025; Wu et al.,.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text SenseNova-Vision-7B-MoT; Janus-Pro-7B; Janus-1.3B (Han et al., 2026; Chen et al., 2025; Wu et al.,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:41.612334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 362e470c-d8fc-4a98-83f6-52048146213b · outbound

This paper cites 32 Table 17 continued.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text 32 Table 17 continued

Reference 1024

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:41.730369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23f1e4ba-6321-4b1e-a023-24f3724d5ea7 · outbound

This paper cites Vision as Unified Multimodal Generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Vision as Unified Multimodal Generation

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.738395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d397bc5e-c954-44b6-a872-c5f290657a1a · outbound

This paper cites Benchmarking Spatial Relationships in Text-to-Image Generation.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Benchmarking Spatial Relationships in Text-to-Image Generation

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.518805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6892ec34-3a4b-4b7b-9bc9-800038bb5662 · outbound

This paper cites Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:36.464785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7262283c-de5f-4f5b-b544-fee1b27583e0 · outbound

This paper cites LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:36.317366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c9d74b-f98e-463d-964f-e35f4f97a71d · outbound

This paper cites 14 Chaorui Deng, Deyao Zhu, Kunchang Li, Chenhui Gou, Feng Li, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, et al.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text 14 Chaorui Deng, Deyao Zhu, Kunchang Li, Chenhui Gou, Feng Li, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, et al

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.090693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7dc54b9e-9f3e-4f75-a76b-d0ca4a5dc8e9 · inbound

Image-Space Rule Discovery cites this paper.

Image-Space Rule Discovery Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T00:54:58.688729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.