Pith. sign in

Paper Citation Record · LEDGER

Provably Overwhelming Transformer Models with Designed Inputs

As of 9 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2502.06038.

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

pith.paper-citation-record.v1
2502.06038 v2

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:08:17.138254Z

measured 18 of 18 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 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

18 of 18 outbound references displayed

  • verified exact0
  • verified fuzzy3
  • unresolved14
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4616ee3d-3f44-41e9-b546-6e612dbcec3d · outbound

This paper cites write newline.

Provably Overwhelming Transformer Models with Designed Inputs write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.083535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.083535Z digest=sha256:6f4161eb2c4497023fbb42ab98242d6b16a055afa85bd12acd007c9ceffecf6c

Observation f3a02fd8-8b6a-4a7b-ab0e-57354eb9c68d · outbound

This paper cites On the Bottleneck of Graph Neural Networks and its Practical Implications.

Provably Overwhelming Transformer Models with Designed Inputs On the Bottleneck of Graph Neural Networks and its Practical Implications

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.087949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.087949Z digest=sha256:64240dc6755d77f75bc149a8b63bc746b809a20f523b21b60f0959f4ec30fda0

Observation d5466dec-9b0e-4b49-a49d-2647be1c8bb5 · outbound

This paper cites Transformers need glasses! Information over-squashing in language tasks.

Provably Overwhelming Transformer Models with Designed Inputs Transformers need glasses! Information over-squashing in language tasks

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.091434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.091434Z digest=sha256:faaadf252d24684bb095580e3e8733ed7b8afe0bcc40e0caeaca3e2d5b9ec39d

Observation a5aece25-c258-4a00-9a1b-15ccfe1c6b3c · outbound

This paper cites GPT-NeoX-20B: An Open-Source Autoregressive Language Model.

Provably Overwhelming Transformer Models with Designed Inputs GPT-NeoX-20B: An Open-Source Autoregressive Language Model

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.095155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.095155Z digest=sha256:8aab50a4e2bc11223388d9a3f6b6ef57b297e8e9f16be6ab48a0e2fdb782a96b

Observation f234205d-6574-4b6f-a461-5885867c2a3a · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Provably Overwhelming Transformer Models with Designed Inputs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.099193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.099193Z digest=sha256:3a9c9252dce01d8d4910fa7625e3eceae5876d757dcfec81f06e96e45f71f776

Observation 49121a5c-0600-4de7-8285-8ae70702d00c · outbound

This paper cites H., Gibson, A., Noubir, S., and Chan, L.

Provably Overwhelming Transformer Models with Designed Inputs H., Gibson, A., Noubir, S., and Chan, L

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T17:08:17.255979Z

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.

source=arxiv_source observed=2026-08-08T17:08:17.102427Z digest=sha256:d50badbaab7e050c215cd7ccf3ca560e72b339f821b6b17e5b768a119c17a50a

Observation 8f177e66-173c-4395-92d2-ec3fb7bb780a · outbound

This paper cites Theoretical limitations of self-attention in neural sequence models.

Provably Overwhelming Transformer Models with Designed Inputs Theoretical limitations of self-attention in neural sequence models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.105334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.105334Z digest=sha256:a09b324998e6ada693a6a04eb39435f2a43f681f1994d01eb799818ce2ca5c0d

Observation 10aac83a-5a64-451a-8f48-d3530d40951b · outbound

This paper cites Why are Sensitive Functions Hard for Transformers?.

Provably Overwhelming Transformer Models with Designed Inputs Why are Sensitive Functions Hard for Transformers?

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.108161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.108161Z digest=sha256:f8d3def952baa6b16097150b3af09d99d848b479f3902c9faced188a439723ed

Observation 45d1e2c4-e4aa-4138-b040-bfeab62d6216 · outbound

This paper cites The Lipschitz Constant of Self-Attention.

Provably Overwhelming Transformer Models with Designed Inputs The Lipschitz Constant of Self-Attention

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.111381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.111381Z digest=sha256:8df1ca552b8870998bfec30eaf7cd95dde94765fd9ecc45032481f5d7815ca82

Observation cac65b97-57bf-475b-ac76-066d58a1aa63 · outbound

This paper cites J., Sutherland Robson, E., Kohli, P., de Freitas, N., Kavukcuoglu, K., and Vinyals, O.

Provably Overwhelming Transformer Models with Designed Inputs J., Sutherland Robson, E., Kohli, P., de Freitas, N., Kavukcuoglu, K., and Vinyals, O

Reference 10

Resolution
malformed identifier
no resolver link, observed 2026-08-08T17:08:17.114872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.114872Z digest=sha256:00397aa25ce2f821fcfbbcf36e4227143361e6a831b74e48be13bd924df75419

Observation 92aec055-54d8-46cb-9fe9-4ee1e21d0ca4 · outbound

This paper cites and Sabharwal, A.

Provably Overwhelming Transformer Models with Designed Inputs and Sabharwal, A

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T17:08:17.242874Z

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.

source=arxiv_source observed=2026-08-08T17:08:17.117663Z digest=sha256:5cf228a6fa9edc1ad9b84e7cdaa6b9f57b76bb647d02ee4566d90734a70add01

Observation feb656df-388f-4b0d-a7a9-5dbb0c771b4a · outbound

This paper cites Analysis of boolean functions.

Provably Overwhelming Transformer Models with Designed Inputs Analysis of boolean functions

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.120278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.120278Z digest=sha256:b10ac4f1dfcdf230bebc9aa0c9634eeffa1e6057226d6d683b0948da1711bf0b

Observation e856a9c3-8c10-480d-a9e5-5d74b4a6d0df · outbound

This paper cites GPT-4 Technical Report.

Provably Overwhelming Transformer Models with Designed Inputs GPT-4 Technical Report

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.123174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.123174Z digest=sha256:78dc6fe1d7c76bc32382b6d3487792b8224d00100ad240366d783316b50278da

Observation 2b7578f5-8ad6-4f7f-9d4b-6137c34fc0d1 · outbound

This paper cites On Limitations of the Transformer Architecture.

Provably Overwhelming Transformer Models with Designed Inputs On Limitations of the Transformer Architecture

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.126035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.126035Z digest=sha256:c7f3b799c62e856721ad7ab6350ec150276adc1e36f1a1e5767942ead16c8cfd

Observation 7fd2054c-45c8-480e-bfb3-55c5ceeeb779 · outbound

This paper cites J., and Telgarsky, M.

Provably Overwhelming Transformer Models with Designed Inputs J., and Telgarsky, M

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T17:08:17.230310Z

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.

source=arxiv_source observed=2026-08-08T17:08:17.129074Z digest=sha256:09b8e5ff5771ea547498ab49c104b8d587e133ce57ac96714fbe3b4e6cb8584e

Observation fc77f465-9874-4842-964d-690669f85cc1 · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.

Provably Overwhelming Transformer Models with Designed Inputs Roformer: Enhanced transformer with rotary position embedding

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.131978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.131978Z digest=sha256:f4d52d1b3a82135bd2235a6c9b9aac7ec3610634fc4ee844b94257bc61296b1c

Observation 5034a686-51ad-4a1b-9993-fd573dc2857e · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Provably Overwhelming Transformer Models with Designed Inputs Gemini: A Family of Highly Capable Multimodal Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.135347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.135347Z digest=sha256:1a72c334b05260b517898edd9fd4cb1cac0a25f2dc4f722335046191db65a367

Observation 5099dfdc-37bd-47ce-b10b-edc938eeb7d5 · outbound

This paper cites Attention Is All You Need.

Provably Overwhelming Transformer Models with Designed Inputs Attention Is All You Need

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-08T17:08:17.138254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T17:08:17.138254Z digest=sha256:a2ce693140e18630c6a31b14d382180661bf90d4b54835ecb6f7e408520ad6ba

Pith citing papers

No inbound Pith citation observations are available.