Paper Citation Record · LEDGER

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

As of 8 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2506.08297.

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

pith.paper-citation-record.v1
2506.08297 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:21:37.303004Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T01:25:52.762836Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T07:17:29.550333Z

Reference resolution

36 of 36 outbound references displayed

verified exact2
verified fuzzy19
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 17eec38e-970e-4841-86b9-4a4260f6edae · outbound

This paper cites Longformer: The Long-Document Transformer.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Longformer: The Long-Document Transformer

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.177006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028da89c-ac47-47fe-8c62-1c8bd009f584 · outbound

This paper cites Mixformer: Mixing features across windows and dimensions.CVPR, 2022.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Mixformer: Mixing features across windows and dimensions.CVPR, 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.689519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1e87e9eb-9736-463b-ad54-d0110feccec6 · outbound

This paper cites Conditional positional encodings for vision transformers.ICLR, 2023.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Conditional positional encodings for vision transformers.ICLR, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.678492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 326e51c8-4c24-4323-ae38-3fb11ad92c1e · outbound

This paper cites Randaugment: Practical automated data augmentation with a reduced search space.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Randaugment: Practical automated data augmentation with a reduced search space

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.666937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9b7f7022-8213-404e-89a5-1a0f44227130 · outbound

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

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Imagenet: A large- scale hierarchical image database

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.192332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75ce774c-c806-4713-83db-669966a8bd83 · outbound

This paper cites Cswin transformer: A general vision transformer backbone with cross-shaped windows.CVPR, 2022.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Cswin transformer: A general vision transformer backbone with cross-shaped windows.CVPR, 2022

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.648836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 769f58d7-3b85-45c9-8a67-c08a523d2e17 · outbound

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

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging An image is worth 16x16 words: Transformers for image recognition at scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.201226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f4d272-16da-4a81-b30f-57b939427d4f · outbound

This paper cites Mamba: Linear-time sequence modeling with selective state spaces.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Mamba: Linear-time sequence modeling with selective state spaces

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.204961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1dcecac-1f1e-4cf5-9e20-c1c3c6fa2bb7 · outbound

This paper cites Hippo: Recurrent memory with optimal polynomial projections.NeurIPS, 2020.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Hippo: Recurrent memory with optimal polynomial projections.NeurIPS, 2020

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.625199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 449eeeb3-eb32-4b13-a4fe-69c308cc5e62 · outbound

This paper cites an unresolved cited work.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:21:37.614868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c5f13aab-e2dd-4af2-9d94-196aeb842777 · outbound

This paper cites Flatten transformer: Vision transformer using focused linear attention.ICCV, 2023.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Flatten transformer: Vision transformer using focused linear attention.ICCV, 2023

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.603975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation afff5472-db83-4516-acba-6f2c2dd7a5f4 · outbound

This paper cites Bridging the divide: Reconsidering softmax and linear attention.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Bridging the divide: Reconsidering softmax and linear attention

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.592306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b2449e63-aa77-450c-9f9b-cda0edbed132 · outbound

This paper cites Demystify Mamba in Vision: A Linear Attention Perspective.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Demystify Mamba in Vision: A Linear Attention Perspective

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.581261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e2df83a4-6a23-4a88-8a8a-91d2a7d31b2b · outbound

This paper cites Neighborhood attention transformer.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Neighborhood attention transformer

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.570131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8eaa44d6-77d3-43c4-8d4f-c9721408cbcd · outbound

This paper cites LocalMamba: Visual State Space Model with Windowed Selective Scan.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging LocalMamba: Visual State Space Model with Windowed Selective Scan

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.230687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5688884a-c318-48db-b8d5-fa120a1bd0c6 · outbound

This paper cites Katharopoulos, A.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Katharopoulos, A

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.560149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0ac28da9-62f4-44db-b904-ca9b569171bb · outbound

This paper cites Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:21:37.389145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 628aed8e-e36d-4422-92e4-b1f54f324239 · outbound

This paper cites Rethinking vision transformers for MobileNet size and speed.ICCV, 2023.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Rethinking vision transformers for MobileNet size and speed.ICCV, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.549811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 970b95eb-ad57-40b6-ae6d-d3a236a3f754 · outbound

This paper cites Lawrence Zitnick.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Lawrence Zitnick

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.244862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34def07f-1070-4096-b482-f6673a87550b · outbound

This paper cites DefMamba: Deformable Visual State Space Model.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging DefMamba: Deformable Visual State Space Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.248020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b6eb66-10ce-4df8-9149-3972c38f971c · outbound

This paper cites VMamba: Visual State Space Model.NeurIPS, 2024.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging VMamba: Visual State Space Model.NeurIPS, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.533726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0b5da0a6-c366-47f3-a41b-df4791035a89 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Swin transformer: Hierarchical vision transformer using shifted windows

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.523646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c969419d-0594-45d1-8fa1-a9e44e1ea066 · outbound

This paper cites A ConvNet for the 2020s.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging A ConvNet for the 2020s

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.514030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d36abdc7-aafc-4fdb-bc7a-9948e0a163c8 · outbound

This paper cites Decoupled weight decay regularization.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Decoupled weight decay regularization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.261469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3160762b-4e03-4274-b040-06cd21b9839b · outbound

This paper cites an unresolved cited work.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:21:37.497473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 550f8bdc-60de-4c53-9679-f5fa3973efb1 · outbound

This paper cites an unresolved cited work.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:21:37.487795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7754fbea-310d-4bbf-b10b-172eef1fbd89 · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 2024.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.477163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 37608d6b-0855-4eaa-8cf7-363ecf9b5e56 · outbound

This paper cites Vaswani, N.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Vaswani, N

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.466786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 91d006b8-d3e3-4789-b1d6-b19fb5fe7d0a · outbound

This paper cites Softmax is not Enough (for Sharp Size Generalisation).

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Softmax is not Enough (for Sharp Size Generalisation)

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.278432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b19aba5-9c12-4583-a343-b6d4f58970cc · outbound

This paper cites Pvt v2: Improved baselines with pyramid vision transformer.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Pvt v2: Improved baselines with pyramid vision transformer

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.282042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39e43ae-5d97-45aa-b055-0bd67f66f035 · outbound

This paper cites Low-Resolution Self-Attention for Semantic Segmentation.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Low-Resolution Self-Attention for Semantic Segmentation

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:21:37.351539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bba0ff3f-6533-4a6d-ade0-88923297aa26 · outbound

This paper cites Differential Transformer.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Differential Transformer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.289088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 929a87d8-6f75-45fb-8f23-c1cdd8fab411 · outbound

This paper cites Mambaout: Do We Really Need Mamba for Vision?CVPR, 2025.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Mambaout: Do We Really Need Mamba for Vision?CVPR, 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.449035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 032dfc7a-7f09-4bc9-a878-b04b6fa0885b · outbound

This paper cites Cutmix: Regularization strategy to train strong classifiers with localizable features.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Cutmix: Regularization strategy to train strong classifiers with localizable features

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.438544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2b816775-70c4-4c33-9274-670a57a9ef69 · outbound

This paper cites Dauphin, and David Lopez-Paz.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging Dauphin, and David Lopez-Paz

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:37.299441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46073f1-c934-4e35-a544-4105251465d1 · outbound

This paper cites dim64 head2 window size7 # ×2 2 28×28 downsampling, 128.

SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging dim64 head2 window size7 # ×2 2 28×28 downsampling, 128

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:37.421138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 23b7e9c4-8eda-424e-8658-2c99eec65b92 · inbound

USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation cites this paper.

USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-17T01:20:35.902956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d450261e-6653-4083-8fbe-c18cfce826a2 · inbound

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding cites this paper.

VideoSEMA: a scalable and efficient Mamba-like attention for video understanding SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T01:25:52.762836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.