Paper Citation Record · LEDGER

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 5 inbound Pith citation observations for arXiv:2507.16018.

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

pith.paper-citation-record.v1
2507.16018 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:24:50.181009Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

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

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T11:31:29.345098Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T23:23:26.799225Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy26
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c981a6ee-6035-4c34-95e1-a5d869e5675f · outbound

This paper cites Lawrence Zitnick, Dhruv Batra, and Devi Parikh.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Lawrence Zitnick, Dhruv Batra, and Devi Parikh

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:54.411510Z

Source-reported events for the cited work

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

Observation c14c6a63-cc6d-4ed0-83d1-352d24086854 · outbound

This paper cites Longformer: The Long-Document Transformer.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Longformer: The Long-Document Transformer

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:47.535550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76d94c1c-53ae-46cc-9d02-e993d99a2853 · outbound

This paper cites Lawrence Zitnick.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Lawrence Zitnick

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:54.309011Z

Source-reported events for the cited work

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

Observation 0e377806-5496-4520-a1a4-71771e2303da · outbound

This paper cites Learn- ing a sparse transformer network for effective image deraining.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Learn- ing a sparse transformer network for effective image deraining

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:54.181401Z

Source-reported events for the cited work

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

Observation 82440fe8-d2c7-4a32-97d4-e8fb0ff68fc4 · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Generating Long Sequences with Sparse Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:47.777832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4fe5d49-6dbe-4758-adc6-3e842fb54b4b · outbound

This paper cites Rethinking Attention with Performers.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Rethinking Attention with Performers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:47.885413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8539d5-1712-44c8-9495-9b5da9ce94b1 · outbound

This paper cites Flashattention-2: Faster attention with better paral- lelism and work partitioning.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Flashattention-2: Faster attention with better paral- lelism and work partitioning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:54.039306Z

Source-reported events for the cited work

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

Observation f4e46d5d-cb87-44f3-a0fd-6530e09718d4 · outbound

This paper cites Vision transformers need registers.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Vision transformers need registers

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:53.895352Z

Source-reported events for the cited work

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

Observation 150c8d31-39a9-4cba-831e-0ce38a5d6f71 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Imagenet: A large-scale hierarchical image database

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:53.779021Z

Source-reported events for the cited work

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

Observation 793bddf8-87e4-4b3f-9c16-05a14b17e26b · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:53.625408Z

Source-reported events for the cited work

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

Observation 2ad29104-935e-477e-b258-f75d9ebaf680 · outbound

This paper cites Everingham, L.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Everingham, L

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:53.485717Z

Source-reported events for the cited work

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

Observation f4bc3c22-68db-4dce-bba4-3d76c8fb402e · outbound

This paper cites When Attention Sink Emerges in Language Models: An Empirical View.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers When Attention Sink Emerges in Language Models: An Empirical View

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:48.407425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b810f74d-2605-4076-b8ff-27608eb3370b · outbound

This paper cites Masked autoencoders are scalable vision learners.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Masked autoencoders are scalable vision learners

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:53.393235Z

Source-reported events for the cited work

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

Observation f84d3fdc-0fc4-45e3-a2ed-aa14e6e2ec0b · outbound

This paper cites Openclip, July.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Openclip, July

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:48.511482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb906ab-391e-419d-8d36-f91f799e927a · outbound

This paper cites Visual instruction tuning.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Visual instruction tuning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:53.104255Z

Source-reported events for the cited work

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

Observation 613d3aa6-1653-40ec-9e92-4314902654a7 · outbound

This paper cites an unresolved cited work.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:48.757968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1f71f80-4a87-488d-b261-d6ae9a161511 · outbound

This paper cites Qi, Li Yi, Hao Su, and Leonidas J.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Qi, Li Yi, Hao Su, and Leonidas J

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:52.974535Z

Source-reported events for the cited work

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

Observation 7407b7d3-f489-4ee7-b2d9-4c200b7c5df0 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Learning transferable visual models from natural language supervision

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:52.812095Z

Source-reported events for the cited work

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

Observation 887fc386-b337-404e-a1b3-44e3b952507d · outbound

This paper cites Combiner: Full attention transformer with sparse computation cost.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Combiner: Full attention transformer with sparse computation cost

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:52.581440Z

Source-reported events for the cited work

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

Observation 3963c518-794f-44fc-b11f-d3ec84744a2d · outbound

This paper cites Normalized cuts and image segmentation.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Normalized cuts and image segmentation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:52.419266Z

Source-reported events for the cited work

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

Observation ac939149-f285-4c96-b1e9-8d3269bf9ef8 · outbound

This paper cites Massive Activations in Large Language Models.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Massive Activations in Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:49.076209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21acc710-784d-48fa-b769-4fd5bd0481bd · outbound

This paper cites Deit iii: Re- venge of the vit.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Deit iii: Re- venge of the vit

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:52.311329Z

Source-reported events for the cited work

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

Observation 385fcaf9-528c-493b-9d55-e508ad21057e · outbound

This paper cites Attention is all you need.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Attention is all you need

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:52.130781Z

Source-reported events for the cited work

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

Observation 9872199b-3cd0-4ccd-8a77-815bd6cb21b0 · outbound

This paper cites an unresolved cited work.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:24:51.921140Z

Source-reported events for the cited work

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

Observation 373cc9c3-2113-40de-95a3-8ff1148d0194 · outbound

This paper cites Nys- trömformer: A nyström-based algorithm for approximating self-attention.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Nys- trömformer: A nyström-based algorithm for approximating self-attention

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.731929Z

Source-reported events for the cited work

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

Observation 5c7a5663-dbc3-4728-b65f-e5b8c81fffc6 · outbound

This paper cites Ncut apis – nyström normalized cuts py- torch.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Ncut apis – nyström normalized cuts py- torch

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.605947Z

Source-reported events for the cited work

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

Observation 20f7a0c2-bf57-496c-ab5e-0708f9753091 · outbound

This paper cites Emernerf: Emergent spatial-temporal scene decomposition via self-supervision.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Emernerf: Emergent spatial-temporal scene decomposition via self-supervision

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.441107Z

Source-reported events for the cited work

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

Observation 00a7b2e1-645c-4ff7-a5df-c5f357d60d0f · outbound

This paper cites Denoising vision transformers.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Denoising vision transformers

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.321203Z

Source-reported events for the cited work

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

Observation 363ee880-592c-4e6c-a06d-7d8e9cba552a · outbound

This paper cites From image descriptions to visual denotations: New similarity metrics for semantic inference over event descrip- tions.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers From image descriptions to visual denotations: New similarity metrics for semantic inference over event descrip- tions

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.245241Z

Source-reported events for the cited work

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

Observation 67d73a31-db05-4f4b-82d6-838e5459c640 · outbound

This paper cites The Super Weight in Large Language Models.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers The Super Weight in Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:49.774027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc85da6c-f182-45db-87cb-d829a90742de · outbound

This paper cites Wein- berger, and Yoav Artzi.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Wein- berger, and Yoav Artzi

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.168221Z

Source-reported events for the cited work

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

Observation 7b523e6a-2383-4414-b63b-29c76b106f09 · outbound

This paper cites Scene parsing through ade20k dataset.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Scene parsing through ade20k dataset

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:51.002257Z

Source-reported events for the cited work

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

Observation db33a8c4-b6d7-4610-bc6f-5b7461c750f3 · outbound

This paper cites Type I sinking set T.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Type I sinking set T

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:50.868207Z

Source-reported events for the cited work

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

Observation fd4c1b60-4b93-4812-b25a-67615099b0d3 · outbound

This paper cites an unresolved cited work.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:24:50.729845Z

Source-reported events for the cited work

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

Observation 7d222fc5-a037-4081-92c6-45bb6423027d · outbound

This paper cites retain their place.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers retain their place

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:50.567470Z

Source-reported events for the cited work

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

Observation 705759e3-610b-416c-9d8b-c123a02ef1bd · outbound

This paper cites On the other hand, the attention pattern for any token t‰ t1 is identical to that of Type I sinking.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers On the other hand, the attention pattern for any token t‰ t1 is identical to that of Type I sinking

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:24:50.432531Z

Source-reported events for the cited work

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

Observation 0c3405cc-5fc8-482c-8de6-f1d30353fe0c · outbound

This paper cites an unresolved cited work.

Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers Unresolved cited work

Reference 2021

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:24:53.262896Z

Source-reported events for the cited work

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

Pith citing papers

Observation ffe15873-87bf-4702-baf9-177afbc04be7 · inbound

Activation Quantization of Vision Encoders Needs Prefixing Registers cites this paper.

Activation Quantization of Vision Encoders Needs Prefixing Registers Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.345098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c252b151-162f-490a-bf6d-061575cd5cdd · inbound

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models cites this paper.

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-13T23:23:26.802375Z

Source-reported events for the cited work

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

Observation d4627e67-aaac-41e0-b9f0-59d339972536 · inbound

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models cites this paper.

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T17:04:23.629886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 456fdfc1-d921-4322-a70a-677943c8e9c7 · inbound

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

Reference 119

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:05:57.868852Z

Source-reported events for the cited work

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

Observation dd8b77d6-729c-4f1e-bca1-40861b5c57ad · inbound

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs cites this paper.

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:49:48.965225Z

Source-reported events for the cited work

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