Paper Citation Record · LEDGER

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

As of 23 August 2026, this Paper Citation Record lists 100 of 172 outbound references and 44 inbound Pith citation observations for arXiv:2501.16411.

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

pith.paper-citation-record.v1
2501.16411 v2

Coverage vector

measured 100 of 172 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T13:32:59.189284Z

measured 144 of 144 standing notices

One-hop event checks from named stored sources.

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

measured 44 of 44 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:21:12.227048Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T18:06:25.898385Z

Reference resolution

100 of 172 outbound references displayed

verified exact0
verified fuzzy4
unresolved94
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c2262a3d-47e2-4439-bc02-52c12ec9e78b · outbound

This paper cites M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding M$^3$CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.231052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9c57d82-a4ed-4c87-9ef9-306701124697 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.271360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347c38f5-0796-422b-bc37-b0579f4ece85 · outbound

This paper cites For the same ‘video description‘, you may provide multiple question-answer pairs, which should be presented in a list format.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding For the same ‘video description‘, you may provide multiple question-answer pairs, which should be presented in a list format

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.276995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ea23dca-994b-4c80-b15e-78d6a214907c · outbound

This paper cites <|endoftext|>.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding <|endoftext|>

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.329475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7320a22f-8076-4fef-b6a4-d38cff41a061 · outbound

This paper cites - The progressive darkening of the images suggests that the light source is becoming weaker.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The progressive darkening of the images suggests that the light source is becoming weaker

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.408976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea9ec6c-0f37-4a7b-8cc0-91a9a8b93705 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.266276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 742d86d7-6d85-41e6-99e7-121012abe115 · outbound

This paper cites Air resistance B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Air resistance B

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.283514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dba84930-5cda-47f5-aec2-2bb6091d0f99 · outbound

This paper cites Mass of the ball B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Mass of the ball B

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.288658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ec239e0-f209-42b9-a604-f60843807874 · outbound

This paper cites It travels farther horizontally B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding It travels farther horizontally B

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.294542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d835cc66-b2a0-4ef1-b9af-66c0a2123570 · outbound

This paper cites The feather falls faster B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The feather falls faster B

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.299489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b3d215-d9e8-4012-bc9f-0a416518c69c · outbound

This paper cites It would fall faster B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding It would fall faster B

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.305361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c80f977a-3727-42d0-b3a7-faaa12229d3d · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 14

Resolution: parse uncertain; no resolver link, observed 2026-08-10T13:32:58.310818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 154cc3f2-33fb-4540-a471-dab7205400bf · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.316360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92659d7e-94ca-4ab3-8d26-b3f2a690cd2c · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.322804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76570ed1-a9b8-4fad-857f-df8741bd8cbc · outbound

This paper cites video” is replaced with “image.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding video” is replaced with “image

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.336232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c662fe4-9afc-4fb6-9669-7f160bf0fce9 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.343076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ca70d74-ada7-43e0-83bf-50cd39849bc2 · outbound

This paper cites seq” refers to the sequential input of images after frame selection from videos, while.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding seq” refers to the sequential input of images after frame selection from videos, while

Reference 20

Resolution: malformed identifier; no resolver link, observed 2026-08-10T13:32:58.350661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f93dab-b565-4f5a-887b-69517b365be4 · outbound

This paper cites the inequities of societies.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding the inequities of societies

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.358021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b922bbe4-f913-4593-bfdb-21ddd0c42586 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.363757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecb89ec3-772a-4111-8c88-4c0d9b20d0cd · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.368984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3274bb7e-5d9d-4da0-b632-bba4cfa13069 · outbound

This paper cites This means the alteration is most likely due to the light source itself, rather than any changes in the objects being illuminated.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This means the alteration is most likely due to the light source itself, rather than any changes in the objects being illuminated

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.374907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130c99ac-a6c6-4b16-9693-c0bcd77f08e7 · outbound

This paper cites - A stronger light source (D) would result in shorter and sharper shadows.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - A stronger light source (D) would result in shorter and sharper shadows

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.380452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e0cb619-f627-436e-9a62-32e03cb06355 · outbound

This paper cites - The shadows and lighting on the objects remain consistent in terms of direction and shape throughout the series of images.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The shadows and lighting on the objects remain consistent in terms of direction and shape throughout the series of images

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.385475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65aa2edc-b555-4296-b0cb-71410989ffff · outbound

This paper cites - The images progressively become darker, indicating a reduction in the intensity of the light source.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The images progressively become darker, indicating a reduction in the intensity of the light source

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.390378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49644a23-9a8e-435f-b936-a80d3cdddc12 · outbound

This paper cites This is not observed in the images.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is not observed in the images

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.395646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157f119b-42c2-4f2e-9ef6-20330f411e4b · outbound

This paper cites This is contrary to what is observed.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is contrary to what is observed

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.401440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c5e4862-ad15-41c2-ab97-5f394ae1868f · outbound

This paper cites Therefore, the black ball will drop into the right pit if the green floating wall and other balls are removed.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Therefore, the black ball will drop into the right pit if the green floating wall and other balls are removed

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.506973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36e00025-110d-4c9f-ab92-09f9c014c638 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.513561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54314a5e-faee-4487-a81a-8786395fa9e1 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.519358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c65afcd9-527a-4a66-88a0-352a03057cd7 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.524627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9527e3fb-6151-4852-8754-962c32bc2031 · outbound

This paper cites The shockwave appears to bend as it travels across the landscape, which is evidence of reflection.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The shockwave appears to bend as it travels across the landscape, which is evidence of reflection

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.529840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fdb8c08-6ba8-44df-bd6a-b7afd8f67246 · outbound

This paper cites - The explosion generates a large amount of smoke and fire, followed by shockwaves propagating through the air.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The explosion generates a large amount of smoke and fire, followed by shockwaves propagating through the air

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.535322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f6b9383-0090-4489-a146-3c550f1ef47c · outbound

This paper cites The images do not show any evidence of waves bending around obstacles.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The images do not show any evidence of waves bending around obstacles

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.540128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2b33a3-9c50-4d55-a481-efd807ab580d · outbound

This paper cites The shockwave is a type of pressure wave that travels through the air.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The shockwave is a type of pressure wave that travels through the air

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.544934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c3ff513-8575-46e0-b6be-79e512dac127 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.549357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation badde3b0-6b1d-4758-83ff-49ee66a09617 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.554089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51afc4f-1329-40e9-8602-31f60d798466 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.558596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c72fada8-76c1-4184-b465-cf8762cb6f7d · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.562915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9aeb27-7f73-4950-bbdf-4cc1ea855d05 · outbound

This paper cites Choice: B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Choice: B

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.567047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a35a5c1-edc6-4bf8-b3e1-23bd396c773f · outbound

This paper cites - The green floating wall is currently preventing the black ball from falling directly into the right pit.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The green floating wall is currently preventing the black ball from falling directly into the right pit

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.571189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e956cf1-4f00-4c90-8ac3-81170ed4099a · outbound

This paper cites - The black ball will fall straight down due to gravity.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The black ball will fall straight down due to gravity

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.575161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cd0e9ef-e310-40cf-8fb7-4a29bf540b8e · outbound

This paper cites - The black ball is positioned directly above the right pit.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The black ball is positioned directly above the right pit

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.579224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f03348-107e-423a-867a-c36a1f229a45 · outbound

This paper cites Therefore, the black ball will drop into the right pit if the green floating wall and other balls are removed.

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.583437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55dae799-eb07-40d9-8e4a-2871ab24f55b · outbound

This paper cites - Option C (The camera moves upward or downward): This would result in vertical movement of the objects relative to the background, which is not observed.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - Option C (The camera moves upward or downward): This would result in vertical movement of the objects relative to the background, which is not observed

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.668272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a60fc32-d026-440e-853e-3182a1f15a7b · outbound

This paper cites The shadows are also relatively faint and indistinct, suggesting the light source is not very strong.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The shadows are also relatively faint and indistinct, suggesting the light source is not very strong

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.673462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ee14f7-2751-4886-8504-6920f3b68603 · outbound

This paper cites Stronger light source: A stronger light source would produce sharper, more defined shadows.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Stronger light source: A stronger light source would produce sharper, more defined shadows

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.678987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dc16454-049b-415e-b9a5-8a67159cc056 · outbound

This paper cites A weaker light source produces less intense light, resulting in softer, more blurred shadows.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding A weaker light source produces less intense light, resulting in softer, more blurred shadows

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.685487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba3ae3dc-32ef-4d00-939e-37ab80059643 · outbound

This paper cites - The shadows do not change in size, shape, or direction, indicating that the position of the light source remains constant.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The shadows do not change in size, shape, or direction, indicating that the position of the light source remains constant

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.690900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdeece4-bf2f-4b63-99f8-5838d57ff3eb · outbound

This paper cites - If the light source were weaker, the shadows would be less defined and lighter in appearance.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - If the light source were weaker, the shadows would be less defined and lighter in appearance

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.696894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17dedddf-0a4c-4f5e-86a9-ff43166e2720 · outbound

This paper cites The ground and objects maintain a consistent color throughout the series of images.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The ground and objects maintain a consistent color throughout the series of images

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.702896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9853623-9aba-4ed2-89cd-81014cb08844 · outbound

This paper cites - Therefore, the correct choice is B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - Therefore, the correct choice is B

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.708442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c2aeaab-409c-4f00-a943-f20bf710c8da · outbound

This paper cites This creates a perspective where objects farther away appear smaller.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This creates a perspective where objects farther away appear smaller

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.715204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 337da951-2145-4678-9d23-bf8d8d483f97 · outbound

This paper cites As the camera moves upward, the objects below it appear to shrink and move apart, creating the illusion of them getting farther away.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding As the camera moves upward, the objects below it appear to shrink and move apart, creating the illusion of them getting farther away

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.721597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47a4bc43-8375-4301-a3b0-131928d06b07 · outbound

This paper cites Move parallel to the line between the pudding and the blanket: Moving parallel to this line wouldn't change the relative size of the objects.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Move parallel to the line between the pudding and the blanket: Moving parallel to this line wouldn't change the relative size of the objects

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.729634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e656ad1-540f-4f15-bcc2-b13e8074a6cc · outbound

This paper cites - The Rubik's cube and the yellow object appear to move horizontally across the images, while the egg on the plate and the blanket remain relatively stationary.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The Rubik's cube and the yellow object appear to move horizontally across the images, while the egg on the plate and the blanket remain relatively stationary

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.735125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 306179ef-b0e0-47d1-9196-188c24e84cb9 · outbound

This paper cites - The blanket and pillows, which are in the background, do not show significant vertical movement, indicating that the camera is not moving upward or downward.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - The blanket and pillows, which are in the background, do not show significant vertical movement, indicating that the camera is not moving upward or downward

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.739925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70757bb0-ad4e-4dbe-b861-8895abf3469d · outbound

This paper cites - This horizontal movement aligns with the direction between the cube and the blanket, suggesting that the camera is moving parallel to this line.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - This horizontal movement aligns with the direction between the cube and the blanket, suggesting that the camera is moving parallel to this line

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.745849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2af3a7de-96e3-409e-8bea-c7a0a3bdc5ad · outbound

This paper cites - Option C (The camera moves upward or downward): This would result in vertical movement of the objects relative to the background, which is not observed.

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.754384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c1c3910-ba36-49f3-b4c4-f38f84ce277e · outbound

This paper cites Based on these observations, the correct choice is B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Based on these observations, the correct choice is B

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.844086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cb824b9-b96a-4b01-acdf-d2ad01d92611 · outbound

This paper cites This suggests a shift in perspective.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This suggests a shift in perspective

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.849440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbcb6543-e503-4734-857d-eec22147453e · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.855031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc76ad17-96f5-4b21-9588-092efe8245d3 · outbound

This paper cites The camera is closer to the objects: This would make the objects appear larger and closer together, the opposite of what we see in the video.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The camera is closer to the objects: This would make the objects appear larger and closer together, the opposite of what we see in the video

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.860883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9cc20e-ab4c-42ae-97a1-1d3a553b07f1 · outbound

This paper cites Moving the camera further away from the objects would make them appear smaller and further apart, matching the video.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Moving the camera further away from the objects would make them appear smaller and further apart, matching the video

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.866086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6854d486-7c98-49c3-927a-8958ffe07aeb · outbound

This paper cites Specifically, the cereal box and the cymbal seem to change their relative positions more significantly compared to the other objects.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Specifically, the cereal box and the cymbal seem to change their relative positions more significantly compared to the other objects

Reference 111

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.870833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fde3cf-ce88-4d0f-b21e-fbb2032fe50a · outbound

This paper cites As the images progress, the cereal box moves from the left side of the frame towards the right, while the cymbal moves from the right side of the frame towards the left.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding As the images progress, the cereal box moves from the left side of the frame towards the right, while the cymbal moves from the right side of the frame towards the left

Reference 112

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.875454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d50801d-1517-48b8-b64e-ae54cec0f163 · outbound

This paper cites This indicates a movement parallel to the line connecting these two objects.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This indicates a movement parallel to the line connecting these two objects

Reference 113

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.880348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fe4086b-4e28-4fec-b325-2607f2babca3 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 114

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.885362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 093b0edf-7032-4894-9040-8d216062ef0d · outbound

This paper cites This movement would cause the cereal box and the cymbal to appear to shift positions relative to each other, as seen in the images.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This movement would cause the cereal box and the cymbal to appear to shift positions relative to each other, as seen in the images

Reference 115

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.890427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb9c689-bf88-414f-a591-435e9e580286 · outbound

This paper cites The flame at the top suggests the candle is burning.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The flame at the top suggests the candle is burning

Reference 116

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.895241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbde7c75-cd3e-4c61-b239-56d0300bd0c2 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 117

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.900648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2ad0b2-eb4b-417f-9e43-29861d5eb41e · outbound

This paper cites Candle causing wax to overflow Detailed Explanation:.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Candle causing wax to overflow Detailed Explanation:

Reference 118

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.905785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 629102bd-09f1-46fa-88f5-a52bfa854d90 · outbound

This paper cites The flame is consistent and does not show signs of being blown out deliberately (which would typically show a sudden change in the flame's behavior).

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The flame is consistent and does not show signs of being blown out deliberately (which would typically show a sudden change in the flame's behavior)

Reference 119

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.910705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 472dc76d-98fa-4bb9-a9f4-0293addb04be · outbound

This paper cites This indicates that the candle has been burning for a while, causing the wax to melt and overflow.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This indicates that the candle has been burning for a while, causing the wax to melt and overflow

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.915365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93e135e5-90ee-4526-b600-33fb74f2a89c · outbound

This paper cites The flame is singular and centered, which is typical for a single-wick candle.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The flame is singular and centered, which is typical for a single-wick candle

Reference 121

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.919829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49d3f6bd-7979-4e77-a5fe-9748887f3475 · outbound

This paper cites Based on these observations, the correct choice is B.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Based on these observations, the correct choice is B

Reference 122

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.925269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5716d5-59d9-4c3f-a855-4cd91761d6c8 · outbound

This paper cites This is the final step where the door has been successfully closed.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is the final step where the door has been successfully closed

Reference 131

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.972342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c45eb83-d35b-4972-bdda-aa202c270bc7 · outbound

This paper cites This is the starting point where the door is in its most open position.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is the starting point where the door is in its most open position

Reference 132

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.976822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 816d48a2-2886-47d1-bc19-36f450b6eb09 · outbound

This paper cites This indicates that the door is in the process of being closed but has not yet reached the fully closed position.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This indicates that the door is in the process of being closed but has not yet reached the fully closed position

Reference 133

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.981040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc4a65d6-b261-40dc-8456-3370c45f782b · outbound

This paper cites This is the final position where the door is completely shut.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is the final position where the door is completely shut

Reference 134

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.985589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf18d01-3aea-4fa9-b2a6-7d8c1fb6f277 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 135

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.989883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a44937c-b4c5-4f87-ad4a-e144d6ccd3d7 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 136

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.994700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e8f471c-6802-424c-9873-96e08fb6512f · outbound

This paper cites 1 - 3 - 2.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding 1 - 3 - 2

Reference 137

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:58.999820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eedd1ef-4252-4861-a191-3d11d17d587e · outbound

This paper cites This is the initial step where the robot is preparing to close the door.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is the initial step where the robot is preparing to close the door

Reference 138

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.005186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 790ce12b-c759-4e79-849d-09183a408e4d · outbound

This paper cites This is the intermediate step where the door is being moved towards the closed position.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is the intermediate step where the door is being moved towards the closed position

Reference 139

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.013852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41efd581-255c-4aa7-8452-2d2a5b64f9bb · outbound

This paper cites This is the final step where the door has been successfully closed.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This is the final step where the door has been successfully closed

Reference 140

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.019054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 729a8083-6542-4379-9fa8-86578aa9d50e · outbound

This paper cites Therefore, the chameleon turns from blue to red in the video.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Therefore, the chameleon turns from blue to red in the video

Reference 158

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T13:33:01.473274Z

Source-reported events for the cited work

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

Observation 9f8de575-de91-4d58-80d6-91264c55f90f · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 159

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.125385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef9d537-0838-40c4-b0e8-b654bcdbe1ee · outbound

This paper cites The brown cloth drapes in a more fluid and uneven manner.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The brown cloth drapes in a more fluid and uneven manner

Reference 160

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.130549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f4c7b0-4d2d-434b-89e8-877adee229d2 · outbound

This paper cites This suggests it is more flexible.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding This suggests it is more flexible

Reference 161

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.135885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8428424-fbc0-41b6-b07c-8dc244309bdb · outbound

This paper cites Therefore, based on the way the cloths drape, we can infer that the brown cloth is more flexible than the plaid cloth.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Therefore, based on the way the cloths drape, we can infer that the brown cloth is more flexible than the plaid cloth

Reference 162

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.142192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f28788-8945-436c-b65e-21c6b8ddc658 · outbound

This paper cites The left cloth is orange, and the right cloth is checkered.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The left cloth is orange, and the right cloth is checkered

Reference 163

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.147341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f69a91d7-a0f3-4cd3-ad5d-a555bf7976b5 · outbound

This paper cites The left cloth (orange) and the right cloth (checkered) are both pinned at the corners.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding The left cloth (orange) and the right cloth (checkered) are both pinned at the corners

Reference 164

Resolution: unresolved; no resolver link, observed 2026-08-10T13:32:59.152445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8e01e9-b6a4-4c8d-8945-d8b6255601f4 · outbound

This paper cites - In the fifth image, the left cloth (orange) continues to show more flexibility, conforming more closely to the shape of the object underneath it.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding - In the fifth image, the left cloth (orange) continues to show more flexibility, conforming more closely to the shape of the object underneath it

Reference 165

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T13:33:01.695073Z

Source-reported events for the cited work

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

Observation dd8996bf-1877-43b3-b92e-7c1a6cf0cf19 · outbound

This paper cites Based on these observations, the left cloth (orange) is more flexible compared to the right cloth (checkered).

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Based on these observations, the left cloth (orange) is more flexible compared to the right cloth (checkered)

Reference 166

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T13:33:01.677342Z

Source-reported events for the cited work

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

Observation d47cfe00-fe38-4d8f-a980-61953397063d · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 167

Resolution: unresolved; raw_fallback, observed 2026-08-10T13:33:01.660262Z

Source-reported events for the cited work

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

Observation af27ad7b-52d1-4739-a335-e79cfd8bbdaf · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 168

Resolution: unresolved; raw_fallback, observed 2026-08-10T13:33:01.644380Z

Source-reported events for the cited work

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

Observation 4eea45d9-d2fc-41d9-9c73-41bfd7b0d1f2 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 169

Resolution: unresolved; raw_fallback, observed 2026-08-10T13:33:01.626301Z

Source-reported events for the cited work

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

Observation 5ddc604f-8e8b-43f4-87fb-e3438485e5ca · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 170

Resolution: unresolved; raw_fallback, observed 2026-08-10T13:33:01.603368Z

Source-reported events for the cited work

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

Observation b519faee-7af7-4ec0-a9e8-71e45f4be0dc · outbound

This paper cites Thus, the chameleon turns from blue to red.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Thus, the chameleon turns from blue to red

Reference 171

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T13:33:01.580716Z

Source-reported events for the cited work

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

Observation 41ae4a6f-94d1-4c78-8c68-0cc16b870130 · outbound

This paper cites an unresolved cited work.

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Unresolved cited work

Reference 172

Resolution: unresolved; raw_fallback, observed 2026-08-10T13:33:01.565139Z

Source-reported events for the cited work

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

Pith citing papers

Observation 3c46dd01-378a-44f9-b539-b04c800706f5 · inbound

A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges cites this paper.

A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T22:17:22.833277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0cd0ca3-4dbc-49ee-ac8c-52c7c301d3b4 · inbound

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models cites this paper.

Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T23:21:12.227048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd68b17c-0d3e-4941-9785-c660c43d028a · inbound

Multi-agent Embodied AI: Advances and Future Directions cites this paper.

Multi-agent Embodied AI: Advances and Future Directions PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:15.412406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4862e706-3f21-448d-9770-eb781bd02a35 · inbound

GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation cites this paper.

GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:18:08.148069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21ad921-79a6-4560-9b7f-864dd3f762ce · inbound

MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models cites this paper.

MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:12:19.785850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a157a6-5b60-499a-a687-1dab7813fcdc · inbound

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models cites this paper.

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:51:30.872381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a68e7cff-fea3-490a-ba38-0dc1711637de · inbound

mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation cites this paper.

mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:23.938745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d74019f-fe34-4f14-a255-a411d2c9ff04 · inbound

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT cites this paper.

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T12:36:21.624537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 436010c1-1f0f-436c-b484-c25ccb20e378 · inbound

BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models cites this paper.

BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T10:35:45.016934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a394c52-f008-4a5f-9765-91e767e95606 · inbound

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning cites this paper.

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T10:26:32.092036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92e2212-d8da-45b3-9170-e0be4cac742f · inbound

From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship cites this paper.

From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:54:44.462046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e2afbd-c8a4-42e7-98b2-3df09b155d46 · inbound

Abstract 3D Perception for Spatial Intelligence in Vision-Language Models cites this paper.

Abstract 3D Perception for Spatial Intelligence in Vision-Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:45:24.431565Z

Source-reported events for the cited work

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

Observation 78f07fa2-0a71-46e7-ab1d-4b349425d388 · inbound

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios cites this paper.

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T21:14:08.671259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 466b7f2c-449d-402f-b6c3-6a4b6c17a26f · inbound

MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models cites this paper.

MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:59:08.633140Z

Source-reported events for the cited work

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

Observation 88b3674e-346b-4206-a479-2edee83aa4e4 · inbound

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

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T17:17:05.467145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b379fa1c-68a0-47ce-829c-38684ac4ae24 · inbound

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions cites this paper.

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T16:47:24.462509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ad7f2f2-4cb9-40be-a877-71b08816f498 · inbound

Agentic Physical AI toward a Domain-Specific Foundation Model for Nuclear Reactor Control cites this paper.

Agentic Physical AI toward a Domain-Specific Foundation Model for Nuclear Reactor Control PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-21T17:00:24.008404Z

Source-reported events for the cited work

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

Observation c8afffaa-b52f-4a36-8ee1-4d4446130432 · inbound

SCP: Spatial Causal Prediction in Video cites this paper.

SCP: Spatial Causal Prediction in Video PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T16:50:11.227229Z

Source-reported events for the cited work

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

Observation 253d7d01-5785-4c20-8e07-4864a5d3dbbe · inbound

Multimodal Language Models Cannot Spot Spatial Inconsistencies cites this paper.

Multimodal Language Models Cannot Spot Spatial Inconsistencies PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T23:13:24.768838Z

Source-reported events for the cited work

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

Observation 4b761ef7-61fa-437e-8043-744e943c169f · inbound

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving cites this paper.

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:46:04.347333Z

Source-reported events for the cited work

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

Observation c6304c87-1c74-40c7-9399-168e0d4138f5 · inbound

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving cites this paper.

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 96

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T14:21:03.894039Z

Source-reported events for the cited work

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

Observation 935b2493-3073-40e1-bb43-26b7cdfca23a · inbound

Grounding Video Reasoning in Physical Signals cites this paper.

Grounding Video Reasoning in Physical Signals PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-09T22:34:07.272291Z

Source-reported events for the cited work

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

Observation f65b4cce-0ad5-4843-b705-438b4bd60786 · inbound

From Priors to Perception: Grounding Video-LLMs in Physical Reality cites this paper.

From Priors to Perception: Grounding Video-LLMs in Physical Reality PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:21:08.313979Z

Source-reported events for the cited work

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

Observation 4ef3b87a-c965-4d11-b366-5270fa6a8c92 · inbound

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs cites this paper.

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:53.207696Z

Source-reported events for the cited work

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

Observation 2d14ffac-878a-4c03-aa2e-43ef42ff1033 · inbound

Quantitative Video World Model Evaluation for Geometric-Consistency cites this paper.

Quantitative Video World Model Evaluation for Geometric-Consistency PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T03:14:53.082576Z

Source-reported events for the cited work

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

Observation 6ab7aa76-0d97-4a16-b022-74df7f7b3ab3 · inbound

PhysBrain 1.0 Technical Report cites this paper.

PhysBrain 1.0 Technical Report PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-19T16:37:39.921164Z

Source-reported events for the cited work

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

Observation a84fa5a1-28c9-4685-9564-e6224bcd8179 · inbound

Evidence of a Cognitive Shift in AI Education: How Students Are Rethinking Human Intelligence? cites this paper.

Evidence of a Cognitive Shift in AI Education: How Students Are Rethinking Human Intelligence? PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T01:33:56.534774Z

Source-reported events for the cited work

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

Observation 150f97be-9eaa-4875-9b79-17369e18171e · inbound

GeoWorld-VLM: Geometry from World Models for Vision-Language Models cites this paper.

GeoWorld-VLM: Geometry from World Models for Vision-Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T17:58:49.557468Z

Source-reported events for the cited work

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

Observation 637f56f8-b75c-46b0-8cd7-9eef946ff3c5 · inbound

GeoWorld-VLM: Geometry from World Models for Vision-Language Models cites this paper.

GeoWorld-VLM: Geometry from World Models for Vision-Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.630085Z

Source-reported events for the cited work

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

Observation 6fdda63d-6d25-48c9-a74e-4b9c0c25729a · inbound

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop cites this paper.

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T10:53:13.228601Z

Source-reported events for the cited work

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

Observation 20dda940-1c8b-48fd-9f8f-0d7591ca878a · inbound

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop cites this paper.

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T14:55:48.810709Z

Source-reported events for the cited work

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

Observation e87495d2-7025-455f-9942-efeb2ac24e45 · inbound

$\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos cites this paper.

$\Delta$ynamics: Language-Based Representation for Inferring Rigid-Body Dynamics From Videos PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:14:40.989000Z

Source-reported events for the cited work

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

Observation 5ead1bbb-04be-4290-af55-1656208acec8 · inbound

World Models in Words: Auditing Physical State-Transition Commitments in Vision-Language Models cites this paper.

World Models in Words: Auditing Physical State-Transition Commitments in Vision-Language Models PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T08:23:15.377444Z

Source-reported events for the cited work

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

Observation 6b6d6710-75cd-4995-8649-3336d863e737 · inbound

Benchmarking Single-Factor Physical Video-to-Audio Generation cites this paper.

Benchmarking Single-Factor Physical Video-to-Audio Generation PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:43:13.382683Z

Source-reported events for the cited work

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

Observation dbf71278-e1e7-40ad-8abb-55308a286db9 · inbound

Physically Viable World Models: A Case for Query-Conditioned Embodied AI cites this paper.

Physically Viable World Models: A Case for Query-Conditioned Embodied AI PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-29T09:13:16.514166Z

Source-reported events for the cited work

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

Observation 99ed44cd-9b49-4b80-b54e-42c1ffa78105 · inbound

Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs cites this paper.

Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-02T15:57:06.745261Z

Source-reported events for the cited work

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

Observation 03672721-5de8-42b2-84a0-91793d035cc0 · inbound

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them cites this paper.

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:36:57.143795Z

Source-reported events for the cited work

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

Observation d8f0afaf-4af6-4b32-b691-5135409340bd · inbound

ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors? cites this paper.

ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors? PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:27:22.649811Z

Source-reported events for the cited work

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

Observation 75b7dd1d-4257-4bb6-9d38-070252d0be41 · inbound

RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation cites this paper.

RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-04T17:39:59.976044Z

Source-reported events for the cited work

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

Observation 8fac81bd-607e-4c0c-a713-b8d29f4845d8 · inbound

RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation cites this paper.

RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:19:50.512556Z

Source-reported events for the cited work

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

Observation 3de5026f-5932-46d8-afa2-1f54c803ea22 · inbound

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

OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-02T14:17:02.469095Z

Source-reported events for the cited work

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

Observation e04f13be-3fad-462a-862b-e35eaebd4cb3 · inbound

Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks cites this paper.

Does AI Understand Imaging? A Systematic Benchmark of Agentic AI for Computational Imaging Tasks PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-09T18:06:25.899637Z

Source-reported events for the cited work

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

Observation 8299f42c-fbf6-4c4a-bca0-c50e31843b7c · inbound

RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning cites this paper.

RetroHolmes: When Semantic Plausibility Fails Retrospective Physical Process Reasoning PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T07:27:08.281893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c6b2d5e-c3fd-4ab7-922d-cf3aabae0e3b · inbound

Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence cites this paper.

Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T21:07:24.575800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.