Paper Citation Record · LEDGER

Vision encoders should be image size agnostic and task driven

As of 22 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2508.16317.

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

pith.paper-citation-record.v1
2508.16317 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:27:27.457813Z

measured 50 of 50 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 2026-05-10T00:18:06.989944Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T00:19:46.830591Z

Reference resolution

49 of 49 outbound references displayed

verified exact0
verified fuzzy0
unresolved49
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0c8306b9-7663-4232-8c24-e05fde8a6198 · outbound

This paper cites Multiple Object Recognition with Visual Attention.

Vision encoders should be image size agnostic and task driven Multiple Object Recognition with Visual Attention

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.307944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927a8ded-f759-4f72-8949-2ea34848252d · outbound

This paper cites Recurrent memory transformer.Advances in Neural Information Processing Systems, 35:11079–11091, 2022.

Vision encoders should be image size agnostic and task driven Recurrent memory transformer.Advances in Neural Information Processing Systems, 35:11079–11091, 2022

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.312353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76f8050a-e11c-4d45-bdec-1cb159a25abc · outbound

This paper cites Unsupervised Foveal Vision Neural Networks with Top-Down Attention.

Vision encoders should be image size agnostic and task driven Unsupervised Foveal Vision Neural Networks with Top-Down Attention

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.315322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6dfe1e8-1524-4205-b161-7a7b20bedb88 · outbound

This paper cites End-to-end object detection with transformers.

Vision encoders should be image size agnostic and task driven End-to-end object detection with transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.319481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3aaa650-34d9-4903-a1ff-157b3166428c · outbound

This paper cites Emerging properties in self-supervised vision transformers.

Vision encoders should be image size agnostic and task driven Emerging properties in self-supervised vision transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.323004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fd0df24-9575-4499-9c72-ffe64e97bda5 · outbound

This paper cites Crossvit: Cross-attention multi- scale vision transformer for image classification.

Vision encoders should be image size agnostic and task driven Crossvit: Cross-attention multi- scale vision transformer for image classification

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.325912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9068d13-2f5d-46f2-b32b-c763bb70f79b · outbound

This paper cites Twins: Revisiting the design of spatial attention in vision transformers.

Vision encoders should be image size agnostic and task driven Twins: Revisiting the design of spatial attention in vision transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.329215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cd95916-f42c-4cbf-adbc-918a8140f988 · outbound

This paper cites Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context.

Vision encoders should be image size agnostic and task driven Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.331915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19075cf4-b951-4568-9071-75f6726d3fe8 · outbound

This paper cites Vision Transformers Need Registers.

Vision encoders should be image size agnostic and task driven Vision Transformers Need Registers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.335478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca2e5bf-ce41-48f1-b0f7-7ad4fdc9a6dc · outbound

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

Vision encoders should be image size agnostic and task driven Imagenet: A large- scale hierarchical image database

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.338506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1dce6c8-e76b-45a0-bffe-f61e0e53d208 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.

Vision encoders should be image size agnostic and task driven Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.341479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaf57278-b173-4168-b37f-92f2a593a554 · outbound

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

Vision encoders should be image size agnostic and task driven An image is worth 16x16 words: Transformers for image recognition at scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.344472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd9a9ecc-e463-4993-813d-b69c6f6f83d1 · outbound

This paper cites Multiscale vision transformers.

Vision encoders should be image size agnostic and task driven Multiscale vision transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.347313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6dada1-ce50-4a24-a437-ad3b1b399603 · outbound

This paper cites Levit: a vision transformer in convnet’s clothing for faster inference.

Vision encoders should be image size agnostic and task driven Levit: a vision transformer in convnet’s clothing for faster inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.350398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c15b22e6-0c54-4e8e-aadd-8a96b0755bca · outbound

This paper cites GMAT: Global Memory Augmentation for Transformers.

Vision encoders should be image size agnostic and task driven GMAT: Global Memory Augmentation for Transformers

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.353476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71b3601a-fb5c-4bde-9fdc-39f402495d78 · outbound

This paper cites Deep residual learning for image recognition.

Vision encoders should be image size agnostic and task driven Deep residual learning for image recognition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.356848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fce41d9-bef1-4e0b-b1a0-a33155f5f907 · outbound

This paper cites Rethinking spatial dimensions of vision transformers.

Vision encoders should be image size agnostic and task driven Rethinking spatial dimensions of vision transformers

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.359634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af1c7ca2-575d-46dc-bc05-1b8b7a613231 · outbound

This paper cites Long short-term memory.

Vision encoders should be image size agnostic and task driven Long short-term memory

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.362955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b1816c1-d9c0-45b2-bfd1-e280f749adea · outbound

This paper cites FoveaTer: Foveated Transformer for Image Classification.

Vision encoders should be image size agnostic and task driven FoveaTer: Foveated Transformer for Image Classification

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.365982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98bb2074-9493-4d4c-8edb-ec024923197e · outbound

This paper cites Learning multiple layers of features from tiny images.

Vision encoders should be image size agnostic and task driven Learning multiple layers of features from tiny images

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.369577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87a21bc2-22e8-4708-a579-c6890c405928 · outbound

This paper cites Imagenet classification with deep convolutional neural networks.

Vision encoders should be image size agnostic and task driven Imagenet classification with deep convolutional neural networks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.372280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b21999c8-807e-4d34-afef-ecaf1ad56060 · outbound

This paper cites The shape of ai to come! Talk presented at the AI Action Summit 2025, February.

Vision encoders should be image size agnostic and task driven The shape of ai to come! Talk presented at the AI Action Summit 2025, February

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.375259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874d4f48-181a-4bc9-991c-b30b33576cae · outbound

This paper cites Gradient-based learning applied to document recognition.

Vision encoders should be image size agnostic and task driven Gradient-based learning applied to document recognition

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.381369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42c87409-889a-47eb-92b7-833f2d6179c3 · outbound

This paper cites Swin transformer v2: Scaling up capacity and resolution.

Vision encoders should be image size agnostic and task driven Swin transformer v2: Scaling up capacity and resolution

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.384475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1797c047-40c3-4b18-84ee-8f7d92039e23 · outbound

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

Vision encoders should be image size agnostic and task driven Swin transformer: Hierarchical vision transformer using shifted windows

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.387249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e91a171c-f011-456f-81fa-4bff63703a76 · outbound

This paper cites Decoupled weight decay regularization.

Vision encoders should be image size agnostic and task driven Decoupled weight decay regularization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.390154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c347d50-b1ec-403d-81f6-f15313cf9843 · outbound

This paper cites Biologically inspired deep learning model for efficient foveal-peripheral vision.

Vision encoders should be image size agnostic and task driven Biologically inspired deep learning model for efficient foveal-peripheral vision

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.393193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dd77574-90b7-4942-a527-3ca615b0a47b · outbound

This paper cites Implicit-zoo: A large-scale dataset of neural implicit functions for 2d images and 3d scenes, 2024.

Vision encoders should be image size agnostic and task driven Implicit-zoo: A large-scale dataset of neural implicit functions for 2d images and 3d scenes, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.396652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bc456a7-46b0-4cc3-bf0e-17a4f878922e · outbound

This paper cites Recurrent models of visual attention.

Vision encoders should be image size agnostic and task driven Recurrent models of visual attention

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.399521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b48966fb-0c63-4651-83cb-0f33d89b9957 · outbound

This paper cites A focused backpropagation algorithm for temporal pattern recognition.

Vision encoders should be image size agnostic and task driven A focused backpropagation algorithm for temporal pattern recognition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.402827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2435bb80-3ff5-4bbc-97c1-b56ba8a7efc9 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Vision encoders should be image size agnostic and task driven DINOv2: Learning Robust Visual Features without Supervision

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.405864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48d4fc6e-9e8f-40bd-acd3-ceb99b965205 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

Vision encoders should be image size agnostic and task driven Compressive Transformers for Long-Range Sequence Modelling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.408925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 989c24ae-3e9a-4302-a5c8-f4ab83a36fac · outbound

This paper cites The utility driven dynamic error propagation network, volume 11.

Vision encoders should be image size agnostic and task driven The utility driven dynamic error propagation network, volume 11

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.412060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a252d4e-56bf-4346-8abd-e2766b715858 · outbound

This paper cites Learning to generate artificial fovea trajectories for target detection.

Vision encoders should be image size agnostic and task driven Learning to generate artificial fovea trajectories for target detection

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.415649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5179d160-0a2f-4669-b194-7892ebda47ac · outbound

This paper cites Proximal Policy Optimization Algorithms.

Vision encoders should be image size agnostic and task driven Proximal Policy Optimization Algorithms

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.418789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a4db0a-45d7-440e-81c6-7c63814bfb5b · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Vision encoders should be image size agnostic and task driven DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.421857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f43293-0f23-40df-8516-3ec868624b0f · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Vision encoders should be image size agnostic and task driven Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.424852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a741a6e9-efd4-4ca6-92eb-4c377c255371 · outbound

This paper cites Going deeper with convolutions.

Vision encoders should be image size agnostic and task driven Going deeper with convolutions

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.427895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9b68948-deba-4e4a-8d6b-1cc4eccc121c · outbound

This paper cites Training data-efficient image transformers & distillation through attention.

Vision encoders should be image size agnostic and task driven Training data-efficient image transformers & distillation through attention

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.430683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06fa8854-08a9-4831-9663-404560e1f09a · outbound

This paper cites Fixing the train-test resolution discrepancy.

Vision encoders should be image size agnostic and task driven Fixing the train-test resolution discrepancy

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.433377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3ac5e17-72f8-48c0-ada2-10a8eee68f8a · outbound

This paper cites Attention is all you need.

Vision encoders should be image size agnostic and task driven Attention is all you need

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.436126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4ad697-0d87-4c00-881b-3044eda8f240 · outbound

This paper cites Pyramid vision transformer: A versatile backbone for dense prediction without convolutions.

Vision encoders should be image size agnostic and task driven Pyramid vision transformer: A versatile backbone for dense prediction without convolutions

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.438932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 165d1bf8-f90b-421c-a49b-418a0760a1ee · outbound

This paper cites Generalization of backpropagation with application to a recurrent gas market model.

Vision encoders should be image size agnostic and task driven Generalization of backpropagation with application to a recurrent gas market model

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.442174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b8af0ec-c7a8-458f-97a2-51a01d46ca96 · outbound

This paper cites Simple statistical gradient-following algorithms for connectionist reinforce- ment learning.

Vision encoders should be image size agnostic and task driven Simple statistical gradient-following algorithms for connectionist reinforce- ment learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.445077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f04c197-1320-4127-b732-0d3446cc14c1 · outbound

This paper cites Memformer: A Memory-Augmented Transformer for Sequence Modeling.

Vision encoders should be image size agnostic and task driven Memformer: A Memory-Augmented Transformer for Sequence Modeling

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.447770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905ebcd7-5c79-456f-aecd-eada393113de · outbound

This paper cites Neural fields in visual computing and beyond.

Vision encoders should be image size agnostic and task driven Neural fields in visual computing and beyond

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.450958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afac8872-93a0-4c4c-8016-5053ab299a07 · outbound

This paper cites Focal Self-attention for Local-Global Interactions in Vision Transformers.

Vision encoders should be image size agnostic and task driven Focal Self-attention for Local-Global Interactions in Vision Transformers

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.454271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ffb39f8-4169-4983-87c7-b5a4406cbcc1 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Vision encoders should be image size agnostic and task driven mixup: Beyond Empirical Risk Minimization

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.457813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587bb495-b9dd-44c7-bd01-1131514e119e · outbound

This paper cites an unresolved cited work.

Vision encoders should be image size agnostic and task driven Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-05T17:27:27.378175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5adc7cf5-6218-46ef-94a0-ab5649bd6a69 · inbound

Self-supervised pretraining for an iterative image size agnostic vision transformer cites this paper.

Self-supervised pretraining for an iterative image size agnostic vision transformer Vision encoders should be image size agnostic and task driven

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:19:46.831894Z

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.