Paper Citation Record · LEDGER

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers

As of 14 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2507.04388.

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

pith.paper-citation-record.v1
2507.04388 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:53:38.731551Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy33
unresolved8
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 83f9ad9c-c322-40a3-9a09-d4aff20d8d9c · outbound

This paper cites Quantifying attention flow in transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Quantifying attention flow in transformers

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:48.504937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c398e632-26f9-420b-a449-961ab1d040b9 · outbound

This paper cites Sanity checks for saliency maps.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Sanity checks for saliency maps

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:48.203348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c49733a-83f9-4956-bc7b-34d79414b0e1 · outbound

This paper cites Deep variational information bottleneck.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Deep variational information bottleneck

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:47.854508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fbd504a6-6a2b-4d1c-b1a6-76a4dc504bd2 · outbound

This paper cites Towards better understanding of gradient-based attri- bution methods for deep neural networks.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Towards better understanding of gradient-based attri- bution methods for deep neural networks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:47.483094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d6aaff7b-64f4-48ca-ab5e-6811571a08dc · outbound

This paper cites BEit: BERT pre-training of image transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers BEit: BERT pre-training of image transformers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:47.149812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a964bd95-4ba0-4d04-b341-12f46b43c740 · outbound

This paper cites Visual explanations via iterated integrated attributions.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Visual explanations via iterated integrated attributions

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:46.840052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8aa06276-3efa-4b61-845a-5ee3ad0e7a5a · outbound

This paper cites Layer-wise relevance propagation for neural networks with local renormalization layers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Layer-wise relevance propagation for neural networks with local renormalization layers

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:46.501094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1bbfde0c-4970-452f-af7c-e8c634e7238c · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Emerg- ing properties in self-supervised vision transformers

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:46.099260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ccbd941e-b379-48fc-b09c-c95255937975 · outbound

This paper cites Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:34.790560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a5c2d51-faf3-4a33-8787-88e259ad5797 · outbound

This paper cites Transformer inter- pretability beyond attention visualization.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Transformer inter- pretability beyond attention visualization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:45.803533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 14bea9b6-9337-4284-8c40-69f564730852 · outbound

This paper cites Beyond intuition: Rethinking token attributions in- side transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Beyond intuition: Rethinking token attributions in- side transformers

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:45.549551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1ce864e5-0c18-463f-aa45-7077632ff6eb · outbound

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

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Imagenet: A large-scale hierarchical image database

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:45.250076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 250196e4-cef7-43ea-9e8a-3dea707e83fa · outbound

This paper cites Towards A Rigorous Science of Interpretable Machine Learning.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Towards A Rigorous Science of Interpretable Machine Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:35.273984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af409825-0c54-4b3c-9593-a34bcfb69e16 · outbound

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

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:44.970789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 528db324-215d-4069-b542-b4908f31ec64 · outbound

This paper cites Eva: Exploring the limits of masked visual representa- tion learning at scale.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Eva: Exploring the limits of masked visual representa- tion learning at scale

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:35.492400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d917153-7578-4848-b7e6-edaa2d0686c8 · outbound

This paper cites Masked autoencoders are scalable vision learners.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Masked autoencoders are scalable vision learners

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:44.669179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c50a7be-7c4f-44eb-b730-fc749caec23e · outbound

This paper cites The many faces of robust- ness: A critical analysis of out-of-distribution generalization.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers The many faces of robust- ness: A critical analysis of out-of-distribution generalization

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:44.317417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f07ca56d-1ccc-4700-964b-0821bb2fb0d7 · outbound

This paper cites Natural adversarial examples.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Natural adversarial examples

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:44.035292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8e6b7ef2-b442-48a4-a9cc-38514300da38 · outbound

This paper cites Fun- nybirds: A synthetic vision dataset for a part-based analysis of explainable ai methods.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Fun- nybirds: A synthetic vision dataset for a part-based analysis of explainable ai methods

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:43.790595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 43d8fee4-bac8-48fa-a0aa-b7d8afb28b9c · outbound

This paper cites Optimizing rele- vance maps of vision transformers improves robustness.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Optimizing rele- vance maps of vision transformers improves robustness

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:43.439590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3eb96d2d-439a-4c35-ab61-ff038c764110 · outbound

This paper cites A benchmark for interpretability methods in deep neural networks.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers A benchmark for interpretability methods in deep neural networks

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:43.139656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0da14c76-47dc-4d0f-a141-5b6fc3942d56 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Adam: A Method for Stochastic Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:36.225633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0334bed-3f29-45c7-a7e3-79330b1166ee · outbound

This paper cites Auto-Encoding Variational Bayes.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Auto-Encoding Variational Bayes

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:36.312385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbb7c216-4fff-44e6-bfa5-873f4b5a599e · outbound

This paper cites Similarity of neural network represen- tations revisited.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Similarity of neural network represen- tations revisited

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:42.874855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 085cc99d-af4d-416e-907d-8a0c1c220f20 · outbound

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

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Swin transformer: Hierarchical vision transformer using shifted windows

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:36.463403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13ab5ecb-9ba9-4fc3-99dc-ffb1e6226109 · outbound

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

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Swin transformer v2: Scaling up capacity and resolution

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:42.538530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c914536b-7010-473e-aec5-50368e684de6 · outbound

This paper cites Safe and interpretable machine learning: a methodological review.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Safe and interpretable machine learning: a methodological review

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:42.219435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3b36f53c-21e6-4aa2-a067-8f450da5712c · outbound

This paper cites Rise: Random- ized input sampling for explanation of black-box models.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Rise: Random- ized input sampling for explanation of black-box models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:41.969514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6cee9456-380e-45f0-81d1-1f91e79298fb · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Learn- ing transferable visual models from natural language super- vision

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:41.659558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef2defea-189f-4685-b18e-9637050e4c54 · outbound

This paper cites A consistent and efficient eval- uation strategy for attribution methods.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers A consistent and efficient eval- uation strategy for attribution methods

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:41.347229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation be4f4c5f-9428-454d-ba4d-ce1572454be0 · outbound

This paper cites Towards explain- able artificial intelligence.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Towards explain- able artificial intelligence

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:41.104300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f41a9dd-8c80-4753-9080-b99b9a424d02 · outbound

This paper cites Restricting the flow: Information bottlenecks for attri- bution.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Restricting the flow: Information bottlenecks for attri- bution

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:40.782113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5c952ede-9c99-41be-a7fc-0baa1ada94d4 · outbound

This paper cites Grad-cam: Visual explanations from deep networks via gradient-based localization.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Grad-cam: Visual explanations from deep networks via gradient-based localization

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:40.555041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation caff3b23-5053-42fc-9dcf-b67341edbfde · outbound

This paper cites How to train your vit? data, augmentation, and regularization in vision transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers How to train your vit? data, augmentation, and regularization in vision transformers

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:40.270206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3f75709f-3407-4604-9e57-3d28dbb40b2d · outbound

This paper cites Axiomatic attribution for deep networks.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Axiomatic attribution for deep networks

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:40.087675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9095b91c-04b9-400a-b132-f2602268bb6a · outbound

This paper cites The information bottleneck method.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers The information bottleneck method

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:37.971815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2433b9ff-927c-4fd5-88b3-72ab286adda6 · outbound

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

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Training data-efficient image transformers & distillation through at- tention

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:39.841022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dcaf4bb0-6aa8-4dc2-a210-e5fb92507160 · outbound

This paper cites Deit iii: Revenge of the vit.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Deit iii: Revenge of the vit

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:39.613139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fad41dce-e81a-4333-8b7e-7f6fc586bf55 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Image quality assessment: from error visibility to structural similarity

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:39.426211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 32c763a6-08ea-4aa9-9270-925e5af2276e · outbound

This paper cites Vit-cx: causal explanation of vision transformers.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Vit-cx: causal explanation of vision transformers

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:53:39.173631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d344516a-8599-4b10-a426-04fc13a81c5f · outbound

This paper cites Sigmoid loss for language image pre-training.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Sigmoid loss for language image pre-training

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:38.663332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322ec5d0-cfa0-419e-9ab3-0fcb13239fdf · outbound

This paper cites Fine-grained neural net- work explanation by identifying input features with predic- tive information.

Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Fine-grained neural net- work explanation by identifying input features with predic- tive information

Reference 42

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T19:53:38.933777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

No inbound Pith citation observations are available.