Pith. sign in

Paper Citation Record · LEDGER

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

As of 6 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 2 inbound Pith citation observations for arXiv:1907.11065.

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

pith.paper-citation-record.v1
1907.11065 v2

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-24T16:21:56.723289Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T05:38:12.882914Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

16 of 16 outbound references displayed

  • verified exact13
  • verified fuzzy2
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

34
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 455e1d63-0152-4ba9-b2ff-e52b0495b38d · outbound

This paper cites Layer Normalization.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Layer Normalization

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.604044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:ecbf5814c4763d9b60d7ffb1c03a9770bc042a8a3e791e00849fa43e18eb362a

Observation cfee279b-89c1-47f5-8daa-2e7b356b3ba9 · outbound

This paper cites A large annotated corpus for learning natural language inference.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks A large annotated corpus for learning natural language inference

Reference 2

Resolution
metadata mismatch
local_arxiv, observed 2026-05-24T16:24:40.597594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:c067143a346415725ea48ea8fea39dbe618830a741c0348970ee394beb6169ef

Observation 3aa9fcc1-20d4-4ec8-a5a2-3fd871e56814 · outbound

This paper cites A Fast Unified Model for Parsing and Sentence Understanding.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks A Fast Unified Model for Parsing and Sentence Understanding

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.665328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:cfda26c04734bccb11eb921259b81424fe9e30f08c9853d73682a4eee10b50c6

Observation 03b9a047-c677-4f9c-8ab0-1fc840b3ab11 · outbound

This paper cites Improved Regularization of Convolutional Neural Networks with Cutout.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Improved Regularization of Convolutional Neural Networks with Cutout

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.629341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:df773effe31555e2a465fe2a596bfc2e31d7a81c78a3c53cc1bfd4d066c1a542

Observation 2b98b9c5-37c2-4eff-8e92-3f8d6f04dbf2 · outbound

This paper cites Shake-Shake regularization.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Shake-Shake regularization

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.660558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:4f948da314151466dda70a4422347bb53537edd24fd0dd5bb0da7b525798cfdd

Observation 99add77e-1a44-4f6b-b734-005b95635f94 · outbound

This paper cites Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

Reference 6

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.654846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:4dc8a60c50b0691be18d102433a74df1a47f42ecbc29f280dc1a643397bc64dc

Observation be3f2a85-1d4d-4009-a534-38daabf7007a · outbound

This paper cites FractalNet: Ultra-Deep Neural Networks without Residuals.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks FractalNet: Ultra-Deep Neural Networks without Residuals

Reference 7

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.619522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:91e62b5062f8942d72a1d7ed24302a1876b61986a18c7acfb71ea3a89bdb7bc4

Observation 029888f5-3fce-4f4a-ac9e-a12fe88822bd · outbound

This paper cites Multi-Head Attention with Disagreement Regularization.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Multi-Head Attention with Disagreement Regularization

Reference 8

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.650077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:205f2d93cfc03eea8bdfeb9b97d98662b175dd715d6242dcbe962bbd14abf6fe

Observation 76e96180-c9bd-4dfe-a0ab-bc64bed8da73 · outbound

This paper cites A Structured Self-attentive Sentence Embedding.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks A Structured Self-attentive Sentence Embedding

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.639360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:10aa062ddc75a96ee04f72354bdc62b0746f73c3920dadba37ea7e30068f6625

Observation 765f4032-333a-454f-832f-9fa8a1cff8cc · outbound

This paper cites Scaling Neural Machine Translation.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Scaling Neural Machine Translation

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.614014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:757c1fcf9490ddbe9de989c9d057215b2767624de0a2f7a5eb09f033c2093a91

Observation bf86cfd3-6cc2-4959-b976-e580facc9aa4 · outbound

This paper cites Recurrent Dropout without Memory Loss.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Recurrent Dropout without Memory Loss

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.608947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:3c53008b37fd45d8094fb47895c481693cd24e3c9d4d8640f0054cd5c38526e6

Observation 717f01bd-1150-44bc-b59f-4b45acca9ea4 · outbound

This paper cites Neural Machine Translation of Rare Words with Subword Units.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Neural Machine Translation of Rare Words with Subword Units

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.624403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:8e001f3ad8a5a70094ce9c0729048e647756d804adb00fb5c77683a12979f1d4

Observation a946d029-c64d-49ad-8e59-0df37f61023c · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Dropout: a simple way to prevent neural networks from overfitting

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-24T16:24:41.723911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:fd029f0a3e0b4e0d2e278a617986e42f33ed57a1c0e9270677e0cb812fc421d9

Observation 2bf2915d-f25e-4ba3-8513-2b03f9650ac6 · outbound

This paper cites Document modeling with gated recurrent neural network for sentiment classification.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Document modeling with gated recurrent neural network for sentiment classification

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-24T16:24:41.720276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:f89ff7c99e2ac084ace9825f3bedd9f8c3501cb0bc5b069783bcbd3b9829c018

Observation fb610ff7-6f68-4d04-b92f-089923217bb5 · outbound

This paper cites ShakeDrop Regularization for Deep Residual Learning.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks ShakeDrop Regularization for Deep Residual Learning

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-24T16:24:40.644605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:03ad7d96e6b9abafc7142b3d06a28d3ba942a91cd117fcffc034d382aeff0802

Observation 1612a02a-b768-4bb1-a41c-904e4749f701 · outbound

This paper cites Multi-Task Cross-Lingual Sequence Tagging from Scratch.

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks Multi-Task Cross-Lingual Sequence Tagging from Scratch

Reference 16

Resolution
verified exact
local_arxiv, observed 2026-05-24T16:24:40.633858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-24T16:21:56.723289Z digest=sha256:662a435fa0e5878a14635fcecb007afcbea9eec530b35f2bf1687140a010d42c

Pith citing papers

Observation 47a04ff2-2b44-42cb-99dc-edf3e28a25f5 · inbound

Language models recognize dropout and Gaussian noise applied to their activations cites this paper.

Language models recognize dropout and Gaussian noise applied to their activations DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-07-04T23:49:42.666573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T05:38:12.882914Z digest=sha256:fff2f5cd918822a0fa920cae3fec7e85879d7a0bd664403dec89ff18ffdba6ed

Observation 7aab1a54-bdef-4a3d-b301-ed8851fad4e4 · inbound

Explicit Dropout: Deterministic Regularization for Transformer Architectures cites this paper.

Explicit Dropout: Deterministic Regularization for Transformer Architectures DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

Reference 23

Resolution
metadata mismatch
arxiv_id, observed 2026-07-04T23:49:42.666573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-10T00:54:55.790878Z digest=sha256:a72905e80dbc13deed73e0397c33059773aa8585ecbaa6a63ece6b0878589005