Paper Citation Record · LEDGER

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

As of 18 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 7 inbound Pith citation observations for arXiv:2504.15485.

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

pith.paper-citation-record.v1
2504.15485 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:29:01.175213Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:50:32.315784Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T16:44:56.123044Z

Reference resolution

49 of 49 outbound references displayed

verified exact2
verified fuzzy31
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9f31bd67-203f-4f7d-88e3-cbd31f32813e · outbound

This paper cites Llama 3.1 model card.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Llama 3.1 model card

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:02.034118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6499a395-ef09-4816-90d8-3637fc2a5575 · outbound

This paper cites UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:00.908466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c776e55d-2837-410e-bbb0-7cadd595de7e · outbound

This paper cites CountGD: Multi-Modal Open-World Counting.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting CountGD: Multi-Modal Open-World Counting

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:00.914353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc7c5e2b-8c77-4c54-a770-dda9cf0f1db8 · outbound

This paper cites Vqa: Visual question answering.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Vqa: Visual question answering

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:02.019502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6846673f-be1f-4b85-9144-d502784f0bc6 · outbound

This paper cites Image amodal completion: A survey.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Image amodal completion: A survey

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:02.005506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d14a7d27-4ea5-46cd-a8ec-0c5c370ef6b5 · outbound

This paper cites Open-World Amodal Appearance Completion.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Open-World Amodal Appearance Completion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:00.931495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c968a922-a7d0-43da-8583-453e9b970118 · outbound

This paper cites Text to image model arena, 2025.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Text to image model arena, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.990689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 23a56670-7aec-4c5f-8b6a-45c8f415ea98 · outbound

This paper cites Partially occluded object detection and count- ing.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Partially occluded object detection and count- ing

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.976430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cb31961b-808d-48f3-a39f-a22f7d99613f · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:00.949346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41fe2455-d86c-42db-9f8c-585c9f72f1ef · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:00.955941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471c5f52-e430-42b9-95f1-1c6d803dacf3 · outbound

This paper cites The coefficient of determination r-squared is more informa- tive than smape, mae, mape, mse and rmse in regression anal- ysis evaluation.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting The coefficient of determination r-squared is more informa- tive than smape, mae, mape, mse and rmse in regression anal- ysis evaluation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.961827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 45b0d63f-6371-42f7-b4b7-8ee6f5251cb1 · outbound

This paper cites How frequent are numbers? Language & Communication, 31(1):27–37, 2011.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting How frequent are numbers? Language & Communication, 31(1):27–37, 2011

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.947714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation aef7b08c-cec9-435c-bfe1-41ecec495e7d · outbound

This paper cites Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:00.974177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dfb5193-b9c1-4c1c-91dc-bbb667780387 · outbound

This paper cites Multi- branch segmentation-guided attention network for crowd counting.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Multi- branch segmentation-guided attention network for crowd counting

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.933775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0d786f96-1eec-433d-8679-4ad315aa6664 · outbound

This paper cites A pragmatic view of accuracy measurement in forecasting.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting A pragmatic view of accuracy measurement in forecasting

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.919721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6d78ec9b-9a67-4011-9db0-d02b7147ce83 · outbound

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

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.905314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4f53422c-6e23-4feb-98e3-19eb44128216 · outbound

This paper cites Recurrent world models facilitate policy evolution.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Recurrent world models facilitate policy evolution

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.891371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 404abf88-149c-48f7-85e5-5c831ac726b0 · outbound

This paper cites Countnet3d: A 3d computer vision approach to infer counts of occluded objects.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Countnet3d: A 3d computer vision approach to infer counts of occluded objects

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.877312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1db48b16-d25b-470f-b93c-03bdebf3cd9f · outbound

This paper cites Organi- zation in vision : essays on gestalt perception.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Organi- zation in vision : essays on gestalt perception

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.863277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 08df761c-23e5-40c9-8be6-a27e018fff66 · outbound

This paper cites Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:29:01.446550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 66b90470-0cf3-42cc-be60-74c5a908b42b · outbound

This paper cites an unresolved cited work.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:29:01.848574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eb936311-59f6-4a9a-a854-c8c57a70f60b · outbound

This paper cites NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.026211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a290d531-097d-44be-aa37-50b8ac296e44 · outbound

This paper cites Crowdclip: Unsupervised crowd counting via vision-language model.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Crowdclip: Unsupervised crowd counting via vision-language model

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.834691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation db2caff6-265b-470e-aa48-598244cd92b8 · outbound

This paper cites Visual spatial reasoning.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Visual spatial reasoning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.820486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 86eb0e07-47ad-4b9a-96a8-143d74cf52a3 · outbound

This paper cites Optimum design of chamfer masks using symmetric mean absolute percentage error.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Optimum design of chamfer masks using symmetric mean absolute percentage error

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.806803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4a81c6e7-f02c-4416-95a5-9e8cd3ab01d3 · outbound

This paper cites Spartqa: A tex- tual question answering benchmark for spatial reasoning.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Spartqa: A tex- tual question answering benchmark for spatial reasoning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.791821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bd50a9ad-b90c-4263-a8d1-5ab1322668a1 · outbound

This paper cites Neuronal representation of occluded objects in the human brain.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Neuronal representation of occluded objects in the human brain

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.776120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9a3ea8cd-264d-48b5-9cf6-a3178ca4eb34 · outbound

This paper cites Hello gpt-4o, 2024.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Hello gpt-4o, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.761366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 352c322f-0a46-4be9-8794-f126c3db1c54 · outbound

This paper cites Openvlm leaderboard.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Openvlm leaderboard

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.747360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation eeba0727-1b0d-48fd-9a85-334c0d069f5d · outbound

This paper cites Development of modal and amodal completion in infants.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Development of modal and amodal completion in infants

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.733165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3c94c717-76e7-4d0d-a49c-d6ed29561c96 · outbound

This paper cites pix2gestalt: Amodal segmentation by synthesizing wholes.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting pix2gestalt: Amodal segmentation by synthesizing wholes

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.718689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b60186fa-f33d-4f53-b6e1-4f7c59db9b4f · outbound

This paper cites Is Temperature the Creativity Parameter of Large Language Models?.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Is Temperature the Creativity Parameter of Large Language Models?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.083875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69323239-fae5-4061-a84b-38469b2a8c6b · outbound

This paper cites Lvlm-count: Enhancing the count- ing ability of large vision-language models.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Lvlm-count: Enhancing the count- ing ability of large vision-language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.089146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e74d68-641c-4462-ab1a-a961132b9137 · outbound

This paper cites OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded Objects.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting OCC-MLLM:Empowering Multimodal Large Language Model For the Understanding of Occluded Objects

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:29:01.281300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 706b7659-1b93-4291-9592-09540f894774 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Learning transferable visual models from natural language supervi- sion

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.099402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b803602-9b66-418e-835f-b9f4d8dd977a · outbound

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

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.104745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11ee0401-5b64-4942-aa9b-45f79300784f · outbound

This paper cites Learning to count everything.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Learning to count everything

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.694020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f847fe79-1dae-44a9-a70a-e700f10963e9 · outbound

This paper cites Mask guided gated convolution for amodal content completion.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Mask guided gated convolution for amodal content completion

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.680057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0ddd6478-86dd-4d7d-b813-1f81b48882df · outbound

This paper cites A cor- pus of natural language for visual reasoning.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting A cor- pus of natural language for visual reasoning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.664181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f27f5309-6a1e-4093-bda8-687e96f7a299 · outbound

This paper cites an unresolved cited work.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:29:01.648208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c5dee602-87b3-4022-ae44-acd4e8ab93e0 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.130709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31b297b8-3407-4f5b-b568-0eb633295175 · outbound

This paper cites Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.135882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46df3c93-5ee8-42fb-bc57-102584265e0b · outbound

This paper cites Occlusion robust wheat ear counting algorithm based on deep learning.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Occlusion robust wheat ear counting algorithm based on deep learning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.631770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 31e8c6e0-60c6-436d-8431-49cc9738e2fe · outbound

This paper cites Dual- branch counting method for dense crowd based on self- attention mechanism.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Dual- branch counting method for dense crowd based on self- attention mechanism

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.614682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9cafec2d-51d5-4c78-aeb6-b85e7bd5c8ca · outbound

This paper cites Children’s understanding of counting.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Children’s understanding of counting

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.599014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1480534f-aed0-489b-9db3-13a090094f9d · outbound

This paper cites Amodal com- pletion via progressive mixed context diffusion.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Amodal com- pletion via progressive mixed context diffusion

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.583139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 20e52af8-35a5-4f22-ace5-0e13340980cb · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T11:29:01.164596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5099834-2171-4fbd-a9c5-bc6bc5e53d90 · outbound

This paper cites Multi-branch progressive embedding network for crowd counting.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting Multi-branch progressive embedding network for crowd counting

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.566952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 44685ef7-9712-47f9-8abc-972ae342f9f8 · outbound

This paper cites no”, the images were immediately discarded. If the model output was “yes.

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting no”, the images were immediately discarded. If the model output was “yes

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:29:01.551241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 0f972e68-e574-42ee-a6ed-21d647e6ff52 · inbound

Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models cites this paper.

Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:50:32.315784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ed4db9-1ac1-465e-9632-203f668c3226 · inbound

AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making cites this paper.

AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:27.167072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1d2c762-7cdd-4a35-a45b-60977dcf6494 · inbound

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates cites this paper.

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T17:17:07.618065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64a2ad40-79a8-4e5a-b180-c7fa679bd364 · inbound

Using street view images and visual LLMs to predict heritage values for governance support: Risks, ethics, and policy implications cites this paper.

Using street view images and visual LLMs to predict heritage values for governance support: Risks, ethics, and policy implications CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T14:53:02.245247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 818d1e8a-e5a3-4816-b936-dd8ead34c7a9 · inbound

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

VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 37

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 20a09eda-3925-4e68-8f68-0ab48bdece20 · 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 CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:15:22.749650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e513a6c6-598c-42cc-946a-022c513cc61d · 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 CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:44:56.124516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.