Paper Citation Record · LEDGER

Provable Knowledge Acquisition and Extraction in One-Layer Transformers

As of 24 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 3 inbound Pith citation observations for arXiv:2508.00901.

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

pith.paper-citation-record.v1
2508.00901 v4

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T23:05:56.687644Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T06:55:10.121913Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T17:35:51.333328Z

Reference resolution

57 of 57 outbound references displayed

verified exact16
verified fuzzy28
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5863d64c-f89d-41e6-89d1-13d758384f0f · outbound

This paper cites Transformers learn to implement preconditioned gradient descent for in-context learning.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Transformers learn to implement preconditioned gradient descent for in-context learning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.207862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9263cb36-40c2-47f6-b769-3111ece9d798 · outbound

This paper cites Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.837889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0b250b3e-629d-4e98-a566-dbccacca7cfe · outbound

This paper cites Physics of Language Models: Part 3.1, Knowledge Storage and Extraction.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.869355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 52ce4e83-416e-4755-9181-98348147bcb4 · outbound

This paper cites Birth of a transformer: A memory viewpoint.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Birth of a transformer: A memory viewpoint

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.205887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 84d2161e-a267-429d-8f19-ece9b342cb19 · outbound

This paper cites Language models are few-shot learners.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Language models are few-shot learners

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.167736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3e4f27d-6cd1-488b-ac03-dc1803f1a87a · outbound

This paper cites Scaling Laws for Associative Memories.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Scaling Laws for Associative Memories

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.862743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 062bd6b0-43a0-4f38-a1a9-a41b7d86e4b3 · outbound

This paper cites Learning Associative Memories with Gradient Descent.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Learning Associative Memories with Gradient Descent

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.879130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bc3e7a8e-b5b9-4dd3-8e8e-5a2025c77776 · outbound

This paper cites Benign overfitting in two-layer convolutional neural networks.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Benign overfitting in two-layer convolutional neural networks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.159784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5ff181a0-5d14-4ec2-a864-d3ac0d70de10 · outbound

This paper cites Towards understanding the mixture-of-experts layer in deep learning.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Towards understanding the mixture-of-experts layer in deep learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.173575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1a7b7cd7-c4d6-4a78-9f4e-10c11430db8b · outbound

This paper cites Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.852070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 82df89cf-70ca-4945-b7ec-772d03367ac6 · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Transformer Feed-Forward Layers Are Key-Value Memories

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-21T23:10:44.875465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c337a012-9ada-484b-bc02-887e77929c3e · outbound

This paper cites Understanding Finetuning for Factual Knowledge Extraction.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Understanding Finetuning for Factual Knowledge Extraction

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.845010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c54b138c-578a-4ea6-9a19-c6b325a07410 · outbound

This paper cites The Llama 3 Herd of Models.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers The Llama 3 Herd of Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-21T23:10:44.885336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c79b9456-d1d4-4a60-80d9-326a67f33907 · outbound

This paper cites In-Context Convergence of Transformers.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers In-Context Convergence of Transformers

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.840921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 17e089b1-a4a6-4f41-adeb-e1763392258c · outbound

This paper cites Vision transformers provably learn spatial structure.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Vision transformers provably learn spatial structure

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.127250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 693b6d58-a4b3-4cb6-aa09-c9b8cd74746d · outbound

This paper cites Unveil benign overfitting for transformer in vision: Training dynamics, convergence, and generalization.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unveil benign overfitting for transformer in vision: Training dynamics, convergence, and generalization

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.177731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7cc9718f-71dd-49ee-89bb-c509c88c97f0 · outbound

This paper cites Optimal memorization capacity of transformers.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Optimal memorization capacity of transformers

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.169591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8a33e6e2-c8c1-41bb-a24d-1498eb4cb55e · outbound

This paper cites Large language models struggle to learn long-tail knowledge.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Large language models struggle to learn long-tail knowledge

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.180067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation efcd39cd-ba49-4196-8bd6-e7193b11aac7 · outbound

This paper cites Provable memorization capacity of transformers.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Provable memorization capacity of transformers

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.140595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d6a51fe-209e-450a-8266-d5203507242a · outbound

This paper cites Benign overfitting in two-layer relu convolutional neural networks.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Benign overfitting in two-layer relu convolutional neural networks

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.143623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c7a0fcf5-efa5-40d6-a60d-f92613bee5aa · outbound

This paper cites Deduplicating Training Data Makes Language Models Better.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Deduplicating Training Data Makes Language Models Better

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-21T23:10:44.865987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cd2cff31-1120-40a7-b9ec-f60124cdf36e · outbound

This paper cites Next-token prediction capacity: general upper bounds and a lower bound for transformers.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Next-token prediction capacity: general upper bounds and a lower bound for transformers

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.882273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98571dc9-753e-4717-8ae1-ea886bd49bf9 · outbound

This paper cites One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.859425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6bdd94b1-7785-4547-9142-481f60980056 · outbound

This paper cites Memorization Capacity of Multi-Head Attention in Transformers.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Memorization Capacity of Multi-Head Attention in Transformers

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.872367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ed10931f-24e5-4a47-b46f-53eed430d8a9 · outbound

This paper cites When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-21T23:10:44.834102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2b5b6738-1257-4614-84fb-2579408cb3cf · outbound

This paper cites Locating and editing factual associations in gpt.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Locating and editing factual associations in gpt

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.148566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f83e290-35b7-4ccd-80a0-69c93bc572ee · outbound

This paper cites How Transformers Learn Causal Structure with Gradient Descent.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers How Transformers Learn Causal Structure with Gradient Descent

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T23:10:44.830980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f6500055-9d8b-49dc-8dcf-2c18cfa67d4d · outbound

This paper cites Understanding Factual Recall in Transformers via Associative Memories.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Understanding Factual Recall in Transformers via Associative Memories

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.855297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3872ae8-077c-42e0-a6ef-ff13c614f70c · outbound

This paper cites Language models are unsupervised multitask learners.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Language models are unsupervised multitask learners

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.153397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation db597d97-b182-46ec-9c2e-1f305677ac0e · outbound

This paper cites Data augmentation as feature manipu- lation.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Data augmentation as feature manipu- lation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.165587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e2280d1c-a3a4-42d7-a954-3856dbd84e58 · outbound

This paper cites Scan and snap: Understand- ing training dynamics and token composition in 1-layer transformer.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Scan and snap: Understand- ing training dynamics and token composition in 1-layer transformer

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.203938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 59d62af1-a3cd-4273-bb39-e1f1000f3757 · outbound

This paper cites JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:10:44.848215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9de1d0b7-1632-483d-a5e2-0f27b96f5bb4 · outbound

This paper cites Rethinking benign overfitting in two-layer neural networks.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Rethinking benign overfitting in two-layer neural networks

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.193881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d245bf62-821a-4499-8cb7-f001155fdc56 · outbound

This paper cites Knowledge circuits in pretrained transformers.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Knowledge circuits in pretrained transformers

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.192034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98967ec6-cae9-4447-a2cc-23f063076a39 · outbound

This paper cites Are transformers universal approximators of sequence-to-sequence functions? International Conference on Learning Representations.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Are transformers universal approximators of sequence-to-sequence functions? International Conference on Learning Representations

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.171530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf517ccc-3fbb-4f49-9f22-7fd04b8cbda4 · outbound

This paper cites Trained transformers learn linear models in-context.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Trained transformers learn linear models in-context

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.132137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b114abe6-ebd9-491d-8722-854deeab8a7a · outbound

This paper cites Towards a theoretical understanding of the’reversal curse’via training dynamics.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Towards a theoretical understanding of the’reversal curse’via training dynamics

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.136569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2d86208f-6a23-4cea-b185-d9698c641861 · outbound

This paper cites The benefits of mixup for feature learning.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers The benefits of mixup for feature learning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.175545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9275d688-f560-42b3-a53c-f2368f50236b · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.138663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d3d1eaeb-e6a3-4c63-8fb3-99ab63d3c1c6 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.146406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 295216a7-5bf3-460f-b129-6ce56fce8e39 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.195818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a625a410-8c41-4c57-bdc4-4e2ae50bf63e · outbound

This paper cites Based on the sentence set T , we construct the pre-training dataset as follows: For each (sj, ri, aj) ∈ T.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Based on the sentence set T , we construct the pre-training dataset as follows: For each (sj, ri, aj) ∈ T

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.190128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98e94caf-d04e-4d28-abd9-8121290fc499 · outbound

This paper cites We construct the fine-tuning dataset and the test dataset as For each (sj, ri, aj) ∈ T.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers We construct the fine-tuning dataset and the test dataset as For each (sj, ri, aj) ∈ T

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.163711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fba0194a-03a7-47c2-9c64-8df93d491ef8 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.155444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dbbb93a2-a461-48f3-9f98-37b7fea1d8a7 · outbound

This paper cites We assume all token embeddings— sj, ri, aj, for all j ∈ [N] and i ∈ R are generated from random Gaussian distributions N (0, σ2I).

Provable Knowledge Acquisition and Extraction in One-Layer Transformers We assume all token embeddings— sj, ri, aj, for all j ∈ [N] and i ∈ R are generated from random Gaussian distributions N (0, σ2I)

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.182199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ee853f0d-b7d9-4e61-b8b9-7532c6fe971b · outbound

This paper cites nX i=1 I(j ∈ A i) ≥ K 2q n # ≤ exp − nK2 2q2 . (44) 25 Proof. In each time i ∈ [n], a number j ∈ [q] has probability K/q to selected. By Hoeffding’s inequality, we have: P.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers nX i=1 I(j ∈ A i) ≥ K 2q n # ≤ exp − nK2 2q2 . (44) 25 Proof. In each time i ∈ [n], a number j ∈ [q] has probability K/q to selected. By Hoeffding’s inequality, we have: P

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.200223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7aa70d31-1560-4218-bea5-e5de6f120a3d · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.209658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7e2e6550-6ab9-478a-9902-e9fcbb57cf09 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.202026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 55e05847-3ee1-459b-8885-5013041cf37f · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.161723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 583ff63e-d385-4041-aa99-d694cde1589f · outbound

This paper cites (70) Proof.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers (70) Proof

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.186290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98690a49-de06-4405-9f29-1755c3d1739b · outbound

This paper cites After 2 iterations, we have 1 m mX k=1 ⟨w(T1) I(aj),k, Ξ(T1)([o s j ri])⟩ = O λη1dKs(j) nm.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers After 2 iterations, we have 1 m mX k=1 ⟨w(T1) I(aj),k, Ξ(T1)([o s j ri])⟩ = O λη1dKs(j) nm

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.197902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 555e56af-0ffe-4acf-8c6a-d9485ad77dfb · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.184027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9fd531e6-32e7-4b0a-ab5c-69c3a89e4746 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.188138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 61a7c4a0-89ef-441d-ae30-9c6c76589b08 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.150586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bd73b812-2074-42fe-857c-c753a89ae53f · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.157677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9de4e054-075a-4007-952f-193140735582 · outbound

This paper cites an unresolved cited work.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-05-21T23:15:45.129836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4f5e8f00-9d7e-4d16-9b23-7fe38d5068fd · outbound

This paper cites dX j=1 σjujv⊤ j # i , [RA1(G(tf ))]i = σ1u1v⊤ 1 i . (216) Taking the L2 norms, we have [G(tf )]i 2 2 =.

Provable Knowledge Acquisition and Extraction in One-Layer Transformers dX j=1 σjujv⊤ j # i , [RA1(G(tf ))]i = σ1u1v⊤ 1 i . (216) Taking the L2 norms, we have [G(tf )]i 2 2 =

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T23:15:45.134512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation fca444f4-1977-4d43-8344-ba420ef3a8f3 · inbound

Procedural Pretraining: Warming Up Language Models with Abstract Data cites this paper.

Procedural Pretraining: Warming Up Language Models with Abstract Data Provable Knowledge Acquisition and Extraction in One-Layer Transformers

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T06:55:10.121913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193e0fc8-0d05-4f64-bd4c-868e6ee334f4 · inbound

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models Provable Knowledge Acquisition and Extraction in One-Layer Transformers

Reference 103

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T17:35:51.334692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 64ea49a1-5f14-4feb-9e8f-c4367f115cea · inbound

Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.

Reference 55

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T09:34:34.439000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.