Paper Citation Record · LEDGER

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention

As of 17 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2608.07921.

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

pith.paper-citation-record.v1
2608.07921 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:46:12.923935Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

24 of 24 outbound references displayed

verified exact1
verified fuzzy7
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9571e9c8-936b-4993-a546-b02d2972f964 · outbound

This paper cites Attention is all you need,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Attention is all you need,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.818591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffaa6dd1-86fc-4e29-ab75-879b7e201995 · outbound

This paper cites A mathematical framework for transformer circuits,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention A mathematical framework for transformer circuits,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.376120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6df36632-a5b4-4726-b453-4d37bfc58897 · outbound

This paper cites In-context Learning and Induction Heads.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention In-context Learning and Induction Heads

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.828334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc4c0f1-1af0-41bc-9330-f0e1bb4c0aa2 · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention LoRA: Low-rank adaptation of large language models,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.833310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ae4dc3-e53f-493e-b8cb-487804b38312 · outbound

This paper cites Distribution of eigenvalues for some sets of random matrices,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Distribution of eigenvalues for some sets of random matrices,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.837985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa875f8-b8f7-456a-aff7-d05b9934f043 · outbound

This paper cites Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.842982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa812edd-7087-4962-a5eb-600c48a76158 · outbound

This paper cites A Spectral Condition for Feature Learning.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention A Spectral Condition for Feature Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.847768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aa839ff-5760-4f56-a6eb-fcd09ed7ae0d · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention BERT: Pre-training of deep bidirectional transformers for language understanding,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.340844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5271e91f-6d3d-4c87-af8d-f5716557cfc1 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.856561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d90c9779-4b3a-420e-a4e3-be695088610d · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention OPT: Open Pre-trained Transformer Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.861338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b706274c-7db4-411a-b38f-b1f4a7f05a81 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention LLaMA: Open and Efficient Foundation Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.866008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2413c58a-76d3-405a-8d68-922c590bb004 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.870550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbdc865-ee55-4dff-9ef1-746a74c985eb · outbound

This paper cites The Llama 3 Herd of Models.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention The Llama 3 Herd of Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.875200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a788cf-30a9-41a0-9445-0525ed4be4ff · outbound

This paper cites Mistral 7B.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Mistral 7B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.880012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d15885-29bd-4e58-8c34-21e151a7e8e8 · outbound

This paper cites Qwen2.5 Technical Report.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Qwen2.5 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.884531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0576c148-1bb6-462b-904f-d5484ec6e6a5 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.889024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 709b51fb-a74c-4622-87fd-795a82554477 · outbound

This paper cites GQA: Training generalized multi-query transformer models from multi-head checkpoints,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention GQA: Training generalized multi-query transformer models from multi-head checkpoints,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.324435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bb151c8b-b6f2-46c8-8227-f247e94e8f7c · outbound

This paper cites HellaSwag: Can a machine really finish your sentence?,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention HellaSwag: Can a machine really finish your sentence?,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.308951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7b8fb840-ab0f-45c6-a409-f5c229fc15c2 · outbound

This paper cites Measuring massive multitask language understanding,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Measuring massive multitask language understanding,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.294633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 677e8a3c-4f5b-49ad-861d-28f79bb569bc · outbound

This paper cites PIQA: Reasoning about physical commonsense in natural language,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention PIQA: Reasoning about physical commonsense in natural language,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.279462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 59a8edf4-fac9-45ab-bd2a-b2b9f2a985e5 · outbound

This paper cites A framework for few-shot language model evaluation,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention A framework for few-shot language model evaluation,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.910787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5791b5aa-6aaa-4ccc-b43e-cb3b0c46ef0f · outbound

This paper cites What does BERT learn about the structure of language?,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention What does BERT learn about the structure of language?,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:46:13.264492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3b51e1c5-c4c5-4c27-b2a0-d39643dd88ee · outbound

This paper cites Toy Models of Superposition.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention Toy Models of Superposition

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T00:46:12.919561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d513932-740e-473f-8f61-a70b76248cae · outbound

This paper cites LORA-CRAFT: Cross-layer rank adaptation via frozen Tucker decomposition of pre- trained attention weights,.

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention LORA-CRAFT: Cross-layer rank adaptation via frozen Tucker decomposition of pre- trained attention weights,

Reference 24

Resolution: verified exact; raw_fallback, observed 2026-08-12T00:46:13.094666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.