Paper Citation Record · LEDGER

DeepCrossAttention: Supercharging Transformer Residual Connections

As of 10 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 2 inbound Pith citation observations for arXiv:2502.06785.

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

pith.paper-citation-record.v1
2502.06785 v2

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T14:27:23.951214Z

measured 19 of 19 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-13T20:23:40.027519Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T20:28:14.158183Z

Reference resolution

17 of 17 outbound references displayed

verified exact0
verified fuzzy4
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 593cb35f-fa29-4db7-b6dd-e7f34b11b94b · outbound

This paper cites Better plain ViT baselines for ImageNet-1k.

DeepCrossAttention: Supercharging Transformer Residual Connections Better plain ViT baselines for ImageNet-1k

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.888943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 783e7de9-cd6a-49e3-98a0-b1ab4c55b4e8 · outbound

This paper cites One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling.

DeepCrossAttention: Supercharging Transformer Residual Connections One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.894211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9759928c-8ce4-4ff5-9f24-604fff12399c · outbound

This paper cites W., Sutton, C., Gehrmann, S., et al.

DeepCrossAttention: Supercharging Transformer Residual Connections W., Sutton, C., Gehrmann, S., et al

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.898824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37633e80-5360-479c-be5f-de2840968c61 · outbound

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

DeepCrossAttention: Supercharging Transformer Residual Connections An image is worth 16x16 words: Transformers for image recognition at scale

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:27:24.164534Z

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 1cbb7fb1-6273-465e-a884-4f5be2fe33a0 · outbound

This paper cites Ast: Audio spectrogram transformer.

DeepCrossAttention: Supercharging Transformer Residual Connections Ast: Audio spectrogram transformer

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:27:24.151255Z

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 3a9a08e7-9aee-49a8-bead-934a5a76d27d · outbound

This paper cites Deep residual learning for image recognition.

DeepCrossAttention: Supercharging Transformer Residual Connections Deep residual learning for image recognition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.909955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f674a701-29e5-4768-8592-8184de9b72cc · outbound

This paper cites an unresolved cited work.

DeepCrossAttention: Supercharging Transformer Residual Connections Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.914050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0fda96f-23ec-4f9a-8a0a-eecb387a4b3e · outbound

This paper cites Implicit bias of large depth networks: a notion of rank for nonlinear functions.

DeepCrossAttention: Supercharging Transformer Residual Connections Implicit bias of large depth networks: a notion of rank for nonlinear functions

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:27:24.120768Z

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 c2b0e381-456a-4b3f-b579-633d9a0bf29c · outbound

This paper cites L., Bahl, L.

DeepCrossAttention: Supercharging Transformer Residual Connections L., Bahl, L

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.921078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6da9f9e7-34f2-424f-aeaf-38bcd88db844 · outbound

This paper cites Decoupled Weight Decay Regularization.

DeepCrossAttention: Supercharging Transformer Residual Connections Decoupled Weight Decay Regularization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.924588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed8aae0d-e99a-484c-b214-ce3b05374553 · outbound

This paper cites Laurel: Learned augmented residual layer.

DeepCrossAttention: Supercharging Transformer Residual Connections Laurel: Learned augmented residual layer

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T14:27:24.098733Z

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 ebe7aba1-6590-450a-9732-4e7ba3053499 · outbound

This paper cites DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging.

DeepCrossAttention: Supercharging Transformer Residual Connections DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.931619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6696358e-39fe-4ff6-aad2-4f647a3d8fbf · outbound

This paper cites an unresolved cited work.

DeepCrossAttention: Supercharging Transformer Residual Connections Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-08T14:27:24.085090Z

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 03ec395e-b3e2-4ef9-8f85-9964b6245f06 · outbound

This paper cites an unresolved cited work.

DeepCrossAttention: Supercharging Transformer Residual Connections Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-08T14:27:24.071262Z

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 e02c36f7-e47b-484d-9647-a79daabc3a75 · outbound

This paper cites K., Greff, K., and Schmidhuber, J.

DeepCrossAttention: Supercharging Transformer Residual Connections K., Greff, K., and Schmidhuber, J

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.943092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510495fb-65f0-4c26-b99f-ce311b911ef4 · outbound

This paper cites Attention is all you need.

DeepCrossAttention: Supercharging Transformer Residual Connections Attention is all you need

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.947141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79a16749-1245-4e4d-8edf-09d0619b7b54 · outbound

This paper cites Hyper-Connections.

DeepCrossAttention: Supercharging Transformer Residual Connections Hyper-Connections

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T14:27:23.951214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a0d77b53-2146-4a9b-94fe-a3dc23cc81e7 · inbound

Gradient Boosting within a Single Attention Layer cites this paper.

Gradient Boosting within a Single Attention Layer DeepCrossAttention: Supercharging Transformer Residual Connections

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:28:14.159760Z

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 023d5f0b-4017-484d-be4d-bd9ffc1f901f · inbound

Hyperloop Transformers cites this paper.

Hyperloop Transformers DeepCrossAttention: Supercharging Transformer Residual Connections

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:16:04.542772Z

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.