Paper Citation Record · LEDGER

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training

As of 10 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2505.15548.

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

pith.paper-citation-record.v1
2505.15548 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:19:28.318139Z

measured 37 of 37 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

37 of 37 outbound references displayed

verified exact1
verified fuzzy7
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 054d65b0-fa33-42ec-bcd6-e534fb3c338e · outbound

This paper cites online" 'onlinestring :=.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:25.404015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ce566a-930e-4227-a489-7a5375937b9f · outbound

This paper cites write newline.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:25.482710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26fc62e9-746e-4c87-9797-360732d4bc10 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:31.331862Z

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 14773cb0-1112-4dad-be73-d36e08bc6b25 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:25.662842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e682aa-baed-427d-9a3d-afbed8af30ce · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:31.205156Z

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 5d6e5ef9-e8f4-4662-8f12-6dfbdc749c15 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:31.092473Z

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 d2dce560-f0b3-4198-85e6-3813c5c2adf0 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:31.018932Z

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 3e86184a-1a4d-48ef-9f5d-1e7b093b5797 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:30.911874Z

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 d39a4c2e-c431-4298-af61-f5c2d10179de · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:26.001351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b790a3d6-7acd-4382-8cc2-7cc977ea3ad3 · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher R \' e.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Fu, Stefano Ermon, Atri Rudra, and Christopher R \' e

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:30.795610Z

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 28105b60-63d7-422c-b87b-7cec4f594818 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:30.660538Z

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 19d7fd0a-dd8a-4c31-9f58-4b393407ad50 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:26.318635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaf74979-eb1c-42d8-88ad-6badd3ec3472 · outbound

This paper cites Is Flash Attention Stable?.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Is Flash Attention Stable?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:26.392661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672cf0ab-fd15-48ac-ae4e-0dfd8284a8bb · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:30.530073Z

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 9dcf1a9e-4fcf-43bb-a6f6-e5152750e64a · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:30.389789Z

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 417e3366-1a6c-40a6-89d3-85c113d1f872 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:30.283278Z

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 7993adbf-5b64-42d8-b7c7-9395a04e36a8 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:30.198799Z

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 5e8aa9f8-37d9-4e08-ba48-4ce95a177260 · outbound

This paper cites Kingma and Jimmy Ba.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Kingma and Jimmy Ba

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:30.078253Z

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 760a3f7b-41bf-4277-b85a-4857b90daf43 · outbound

This paper cites The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:26.765813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c43fb6c2-01c4-4711-b161-b0d4b0c68621 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:29.991122Z

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 4ea234c0-12ec-43db-b7e2-571e01cdba3a · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:29.875186Z

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 74046867-4dfe-482b-9ea2-6564d93e23cf · outbound

This paper cites A Theory on Adam Instability in Large-Scale Machine Learning.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training A Theory on Adam Instability in Large-Scale Machine Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:26.981837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ba32e25-49dd-45a4-b14f-44345eae020d · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:29.764298Z

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 780ede76-2e42-4f00-ac88-e52f67d564e6 · outbound

This paper cites Zero-Shot Styled Text Image Generation, but Make It Autoregressive.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Zero-Shot Styled Text Image Generation, but Make It Autoregressive

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:19:28.504324Z

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 191f363c-1d73-4616-b5b6-684eca2c1329 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:29.614678Z

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 e953656a-f92f-4c98-aebd-c18e700b2c85 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:29.486274Z

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 3e7d8ab3-5704-4501-8c11-a09ce095f65e · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:29.375103Z

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 7c48c4b1-cad7-40cf-a5b0-820250eae4dd · outbound

This paper cites Rae, Anna Potapenko, Siddhant M.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Rae, Anna Potapenko, Siddhant M

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:29.259309Z

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 43e1f7e8-0627-4fb9-8c30-ff5677d49970 · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:27.775486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0dabd6c-6963-4e09-9dac-ea748c76ab9e · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Fast Transformer Decoding: One Write-Head is All You Need

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:27.829367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be09dfb-e232-4559-a9c3-d3f1cc12e520 · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:29.138064Z

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 8413a921-310e-4b0b-975d-f730390a50b6 · outbound

This paper cites AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:27.943988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8783920c-56cb-4adf-863e-5fcf32d27f7e · outbound

This paper cites Liu, Lechao Xiao, Katie E.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Liu, Lechao Xiao, Katie E

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:29.020698Z

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 fa20308c-6c33-4e18-b5bd-0f87e03f4ec8 · outbound

This paper cites Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:19:28.124012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9f31fe0-0734-45d9-a363-3579b9247400 · outbound

This paper cites an unresolved cited work.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:19:28.915411Z

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 8080bed0-2763-4d14-b0cc-8b935d451609 · outbound

This paper cites Susskind.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Susskind

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:28.783361Z

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 7b67a9d5-9bf0-4e76-a122-3a10f28f4a7a · outbound

This paper cites Barrett, Zhangyang Wang, and Beidi Chen.

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training Barrett, Zhangyang Wang, and Beidi Chen

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:19:28.674401Z

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.

Pith citing papers

No inbound Pith citation observations are available.