Pith. sign in

Paper Citation Record · LEDGER

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization

As of 7 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2506.06398.

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

pith.paper-citation-record.v1
2506.06398 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:19:32.086306Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

21 of 21 outbound references displayed

  • verified exact4
  • verified fuzzy1
  • unresolved16
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7ad8bfc7-20ff-40bd-8769-c3b653705cd5 · outbound

This paper cites Unconstrained representation of orthogonal matrices with application to common principle components.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Unconstrained representation of orthogonal matrices with application to common principle components

Reference 1

Resolution
verified exact
local_arxiv, observed 2026-08-07T10:19:32.953160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.156526Z digest=sha256:141c17c09ee6be4afa1ba6ec730f4a913040e378cfbdaad7b632615b478f7969

Observation b3798f3b-b609-4e96-810c-33ba724c48a3 · outbound

This paper cites and Mendelson, S.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization and Mendelson, S

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T10:19:33.587061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.246368Z digest=sha256:aaa3912422501e4d6acd688a6f1f6e203c6b33343f0332db7d5edc328d6d7a7f

Observation dc171fc4-10e0-47ee-b9bd-4a73c2207481 · outbound

This paper cites A Universal Law of Robustness via Isoperimetry.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization A Universal Law of Robustness via Isoperimetry

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:30.332600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:30.332600Z digest=sha256:ad1886d8a0219d046ea221d84efb2675fe0e6d722928458b92d27c47d3631397

Observation 4c728534-3b2a-451e-b66d-0d34509433ac · outbound

This paper cites AutoFormer: Searching Transformers for Visual Recognition.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization AutoFormer: Searching Transformers for Visual Recognition

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-08-07T10:19:32.774839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.410597Z digest=sha256:075850ca9488ae9872717d6915974a0c82a3efa0c20b7ce7d9e1178d3daeef9c

Observation ac2c5f3c-aa08-4d11-8ea9-b037cd5082a6 · outbound

This paper cites Naturalistic audio-visual volumetric sequences dataset of sounding actions for six degree-of-freedom interaction.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Naturalistic audio-visual volumetric sequences dataset of sounding actions for six degree-of-freedom interaction

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-08-07T10:19:32.595687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.528890Z digest=sha256:55779f74b6394fd860d3e75f7add58208aea0b940e37156171f9ad519f052704

Observation 54ce9111-c511-4091-88f4-902a3ec13d5d · outbound

This paper cites an unresolved cited work.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-07T10:19:33.434175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.792586Z digest=sha256:4f52817fa16de4e0b2736cb3b89edc24f158826e3f192d2b93b8bebcebe29f36

Observation 042b9330-00aa-4be9-8d94-0ad9898dab60 · outbound

This paper cites an unresolved cited work.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-07T10:19:33.304007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.889653Z digest=sha256:0e0e4c148eaad75f7b2bd662c0f6d881202438921b4cff78b9e8112d969d1099

Observation 10216bbe-cc0d-41a7-b5e1-4748187d990b · outbound

This paper cites an unresolved cited work.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-07T10:19:33.127874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.920214Z digest=sha256:fd8e3883e19450ff643e8b1668728b2c80ec87fc69ad58d22d29f5c12f0854ad

Observation d2675f38-6d3c-48e6-81bc-c3b8073fb057 · outbound

This paper cites ConvBERT: Improving BERT with Span-based Dynamic Convolution.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization ConvBERT: Improving BERT with Span-based Dynamic Convolution

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-07T10:19:32.445067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-07T10:19:30.997976Z digest=sha256:6d98dbb860d6c9c7c04fcfb8efb296247a1218965108cf1ca1d7f66983a478bc

Observation b04b5812-7f82-4b0c-a0eb-1b8c113e494f · outbound

This paper cites Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.112025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.112025Z digest=sha256:f48a665d30daaf9c6bdf625febeda90ca5175de2cb8be421edcdb9e3fe6cbee4

Observation 509fa2d2-c090-4cfa-ae32-e654d9307da2 · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.163992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.163992Z digest=sha256:e9a52226507d8388502181b963bb4e7f4fbcb975b2b196b0f122f6d245cfd75f

Observation 8c9bd168-5301-482c-8fbd-2d8016df0ff0 · outbound

This paper cites Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.246860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.246860Z digest=sha256:4256495e8bb7d5095d147767a10701fd26a5cae5e4e0e8dbc9281022522f77bb

Observation 006bdfb4-ff31-4941-8949-ab402362cee8 · outbound

This paper cites Self-Attention with Relative Position Representations.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Self-Attention with Relative Position Representations

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.342489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.342489Z digest=sha256:3b3a1487150441a43af422270ca2720d88def186f95cbe08d94ed51254beafaf

Observation 732b4608-62bf-481d-b2c4-5589b82ba0c2 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.465132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.465132Z digest=sha256:1fa791c0dcb882545bd2227a8fb52fc5dc96e83c5aebcac6d440a1c02a82ebc8

Observation 27c16d0e-8299-4644-922a-4a85167292ac · outbound

This paper cites Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.558026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.558026Z digest=sha256:317e0bebea4dcccbaaddf08075971219ca4a67989da5c1680205886bb7bceab8

Observation 10f83ea2-3167-47af-be9d-9e55322ee048 · outbound

This paper cites Efficient Transformers: A Survey.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Efficient Transformers: A Survey

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.651037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.651037Z digest=sha256:8e7bb1023c9a9b94687e675749079fa1b784021ad2fd872bec5c7a5e345f4200

Observation 1a322ae6-6cac-4d3b-ae9c-6b92d9341414 · outbound

This paper cites Attention Is All You Need.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Attention Is All You Need

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.725031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.725031Z digest=sha256:7a120edee069221f319588636c1a90946d5dbb600820c303a87eebac464659b6

Observation 4a130c54-a35d-459e-a7ab-7aa0a4cda795 · outbound

This paper cites On Layer Normalization in the Transformer Architecture.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization On Layer Normalization in the Transformer Architecture

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.818374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.818374Z digest=sha256:b9fdac72c308ffc8f8c8bdff92be9fabcefe536f16d6760195562c3a031f5787

Observation d8d327d9-dd89-41f0-a37d-80218f5ed129 · outbound

This paper cites Efficient Attention: Attention with Linear Complexities.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Efficient Attention: Attention with Linear Complexities

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.887945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.887945Z digest=sha256:3881e9ab7d9276dde1192d2fdc14e9f7316a6bcdfcb7bbc6b62b06fb943a20e8

Observation 84a07a37-1edc-468f-b252-8735743043ca · outbound

This paper cites Are Transformers universal approximators of sequence-to-sequence functions?.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Are Transformers universal approximators of sequence-to-sequence functions?

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:31.995796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:31.995796Z digest=sha256:7a49abd77837c0af9aaccc9c147567afe1c426c07f5f1dcb20de85f999489e6e

Observation c2e63405-5085-4b8d-b3c8-131abe7a4d76 · outbound

This paper cites Transformers without Tears: Improving the Normalization of Self-Attention.

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization Transformers without Tears: Improving the Normalization of Self-Attention

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T10:19:32.086306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:19:32.086306Z digest=sha256:ba8e4dd9a046f9dcc204be5266372cf437f915e62706ee200daa39ffd0615b03

Pith citing papers

No inbound Pith citation observations are available.