Paper Citation Record · LEDGER

SparseSAM: Structured Sparsification of Activations in Segment Anything Models

As of 22 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2605.17633.

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

pith.paper-citation-record.v1
2605.17633 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T13:45:26.106499Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T11:43:14.189200Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact19
verified fuzzy17
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e4176e4a-c383-4a1d-9a6b-4b43c636c360 · outbound

This paper cites Token Merging: Your ViT But Faster.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Token Merging: Your ViT But Faster

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.765055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f37c84c4-cca2-4189-bb84-f9e89296afe8 · outbound

This paper cites Perception Encoder: The best visual embeddings are not at the output of the network.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Perception Encoder: The best visual embeddings are not at the output of the network

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.762037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d3fb3e87-d955-40d0-ae12-3031c95f717d · outbound

This paper cites Slimsam: 0.1% data makes segment anything slim.Advances in Neural Information Processing Systems, 37:39434–39461.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Slimsam: 0.1% data makes segment anything slim.Advances in Neural Information Processing Systems, 37:39434–39461

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.244914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0ed95879-4399-4f8d-bbce-ee96086b4df3 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.752731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e187f09d-f3c7-4f0f-a384-cb673c9f1f5e · outbound

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

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Imagenet: A large- scale hierarchical image database

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.226230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0ca43b70-425c-4b9c-a413-ff57dfc1cd49 · outbound

This paper cites Space-filling curves for modeling spatial context in transformer- based whole slide image classification.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Space-filling curves for modeling spatial context in transformer- based whole slide image classification

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.228444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e6ac67af-2b58-4338-91ac-33fafc81ffb5 · outbound

This paper cites YOLOX: Exceeding YOLO Series in 2021.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models YOLOX: Exceeding YOLO Series in 2021

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.733885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 28e92f4a-8223-46da-ad96-8cdcd1f35d46 · outbound

This paper cites Pearson education india.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Pearson education india

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.223698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1d4c5261-4e2a-4f11-a627-c9daeed22eec · outbound

This paper cites DETRs with Hybrid Matching.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models DETRs with Hybrid Matching

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.731003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7bc44867-d5b3-41df-8563-0bba90d77740 · outbound

This paper cites Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Systems, 37:52481–52515.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Systems, 37:52481–52515

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.231089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fdde564f-2900-4dcd-b007-5ee2ed775996 · outbound

This paper cites Segment Anything in High Quality.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Segment Anything in High Quality

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.727582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ad69c3c3-8f39-44e3-99ab-9b92e148e62e · outbound

This paper cites Marlin: FP16xINT4 LLM inference kernel that can achieve near-ideal 4x speedups up to medium batchsizes.https://github.com/IST-DASLab/marlin.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Marlin: FP16xINT4 LLM inference kernel that can achieve near-ideal 4x speedups up to medium batchsizes.https://github.com/IST-DASLab/marlin

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.255869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 099cf2ab-fe16-4e24-ba43-b38bac73083b · outbound

This paper cites Pisa: Piecewise sparse attention is wiser for efficient diffusion transformers.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Pisa: Piecewise sparse attention is wiser for efficient diffusion transformers

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.714004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 012da5d8-de1c-450b-9862-e3a7fed9976b · outbound

This paper cites Expediting large-scale vision transformer for dense prediction without fine-tuning.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Expediting large-scale vision transformer for dense prediction without fine-tuning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.221791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 742b0c09-a8ea-41f0-bbab-1a965fd16849 · outbound

This paper cites Microsoft COCO: Common Objects in Context.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Microsoft COCO: Common Objects in Context

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.771138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f4a109e5-4eee-4d85-87f9-88b449a031e5 · outbound

This paper cites Group fisher pruning for practical network compression.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Group fisher pruning for practical network compression

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.251567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a8098829-aecd-424c-9f3d-2ad4575e9d54 · outbound

This paper cites Structured knowledge distillation for semantic segmentation.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Structured knowledge distillation for semantic segmentation

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.253809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 577fe702-8253-4992-ab3f-6ac53e3f3807 · outbound

This paper cites Learning efficient convolutional networks through network slimming.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Learning efficient convolutional networks through network slimming

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.246945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4575f969-2769-484a-aab4-b6fb06803274 · outbound

This paper cites Ptq4sam: Post-training quantization for segment anything.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Ptq4sam: Post-training quantization for segment anything

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.258089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8554ed9d-617a-4eec-ad16-c4aa81887b13 · outbound

This paper cites International Business Machines Company.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models International Business Machines Company

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.249422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d8caa454-352b-485d-817a-bb8c82eace91 · outbound

This paper cites StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-23T04:13:45.155142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 463732de-9288-4e16-9df1-d71240eca4fa · outbound

This paper cites Mix-qsam: Mixed-precision quantization of the segment anything model.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Mix-qsam: Mixed-precision quantization of the segment anything model

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.242454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 06613a92-86bc-4c4b-aa38-2cf76468897d · outbound

This paper cites JZ-Tree: GPU friendly neighbour search and friends-of-friends with dual tree walks in JAX plus CUDA.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models JZ-Tree: GPU friendly neighbour search and friends-of-friends with dual tree walks in JAX plus CUDA

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.736985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f6d00a94-5ed5-4d45-abe4-1634d45a36a9 · outbound

This paper cites Accelerating transformers with spectrum-preserving token merging.Advances in Neural Information Processing Systems, 37:30772–30810.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Accelerating transformers with spectrum-preserving token merging.Advances in Neural Information Processing Systems, 37:30772–30810

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.237958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 569e620a-6243-4ce9-84bb-48272d0c6f74 · outbound

This paper cites How many tokens do 3d point cloud transformer architectures really need?.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models How many tokens do 3d point cloud transformer architectures really need?

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.774395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 380508c1-b9ad-4865-ab96-6e6c7c1e93ed · outbound

This paper cites Q-vlm: Post-training quantization for large vision-language models.Advances in Neural Information Processing Systems, 37:114553–114573.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Q-vlm: Post-training quantization for large vision-language models.Advances in Neural Information Processing Systems, 37:114553–114573

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.240339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ed1dc2ec-a890-4357-8866-461fcf7ce513 · outbound

This paper cites Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.746267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 88acd9fb-d258-421b-a9fe-897cc6cc055c · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.724424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 233c3beb-d218-461b-9177-1fa9834854cc · outbound

This paper cites EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.717709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d1f37f47-ae53-40a7-bc1f-3da8e78e282d · outbound

This paper cites Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.749353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 83769a5d-cb42-4c0b-87d1-f23bf6c58ef7 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.742901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f2e2d016-b0f8-40ad-8641-644501669c6c · outbound

This paper cites Faster Segment Anything: Towards Lightweight SAM for Mobile Applications.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-20T13:48:19.768265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 931a1ae9-eed7-44a8-b008-580c281da36c · outbound

This paper cites DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T13:48:19.758809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 478e703f-f252-4e4d-ab65-21d1e1661b53 · outbound

This paper cites Spargeattn: Accurate sparse attention accelerating any model inference.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Spargeattn: Accurate sparse attention accelerating any model inference

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.756056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cee32401-ac8e-4636-a115-b289bf3b7ca9 · outbound

This paper cites Ahcptq: Accurate and hardware-compatible post-training quantization for segment anything model.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Ahcptq: Accurate and hardware-compatible post-training quantization for segment anything model

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.233208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bead400a-153f-4b21-adaa-4273ab925895 · outbound

This paper cites Fast Segment Anything.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Fast Segment Anything

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:48:19.721427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8eba6f84-6959-47f9-8246-569c90e10e13 · outbound

This paper cites Edgesam: Prompt-driven edge-aware segmentation with segment anything.

SparseSAM: Structured Sparsification of Activations in Segment Anything Models Edgesam: Prompt-driven edge-aware segmentation with segment anything

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T13:48:20.235466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation 338f8344-7367-44bc-8c7a-92be1741ec42 · inbound

Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2 cites this paper.

Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2 SparseSAM: Structured Sparsification of Activations in Segment Anything Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T11:43:14.189200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.