Paper Citation Record · LEDGER

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

As of 7 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 11 inbound Pith citation observations for arXiv:2506.01115.

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

pith.paper-citation-record.v1
2506.01115 v3

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:57:22.908318Z

measured 74 of 74 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 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:15:07.096284Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T07:56:47.880747Z

Reference resolution

63 of 63 outbound references displayed

verified exact3
verified fuzzy23
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8363ba87-329c-42c9-9ecc-0a23659bea68 · outbound

This paper cites Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.571092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9abca2d-5c2b-440f-9692-f09073b1fa79 · outbound

This paper cites The Curious Case of Benign Memorization.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer The Curious Case of Benign Memorization

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:57:23.702593Z

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.

Observation 73175888-b0e0-4f1b-a063-df84c3ac5ce3 · outbound

This paper cites Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, and Ruosong Wang.On exact computation with an infinitely wide neural net.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, and Ruosong Wang.On exact computation with an infinitely wide neural net

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.158136Z

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.

Observation e41ea57a-c370-4585-bf0c-5511b8b9b17a · outbound

This paper cites A closer look at memorization in deep networks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer A closer look at memorization in deep networks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.143410Z

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.

Observation 117151e8-5cca-4bda-b64b-6e54be0079b1 · outbound

This paper cites Scaling mlps: A tale of inductive bias.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Scaling mlps: A tale of inductive bias

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.123851Z

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.

Observation 879bb15d-bee3-410b-a93f-0189690761f1 · outbound

This paper cites Mechanistic interpretability for AI safety - a review.Transactions on Machine Learning Research, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Mechanistic interpretability for AI safety - a review.Transactions on Machine Learning Research, 2024

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.599011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ea2cbf4-4bb5-4b85-af8e-f660e06859a4 · outbound

This paper cites Birth of a transformer: A memory viewpoint.Advances in Neural Information Processing Systems, 36:1560–1588, 2023.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Birth of a transformer: A memory viewpoint.Advances in Neural Information Processing Systems, 36:1560–1588, 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.096487Z

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.

Observation 662cb06e-280c-496c-b623-4dc346d22452 · outbound

This paper cites Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:57:23.631525Z

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.

Observation 3191c054-6843-42be-a1a1-84be8dbd1f98 · outbound

This paper cites Transformers generalize differently from information stored in context vs in weights.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Transformers generalize differently from information stored in context vs in weights

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.619625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c7a563-58a0-4209-ae7e-594a24231996 · outbound

This paper cites Distributional associations vs in-context reasoning: A study of feed-forward and attention layers.ICLR, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Distributional associations vs in-context reasoning: A study of feed-forward and attention layers.ICLR, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.082310Z

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.

Observation 68fa1850-9619-4b11-837e-0cf11690ca00 · outbound

This paper cites Knowledge localization: Mission not accomplished? enter query localization! InProceedings of the Thirteenth International Conference on Learning Representations (ICLR), 2025.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Knowledge localization: Mission not accomplished? enter query localization! InProceedings of the Thirteenth International Conference on Learning Representations (ICLR), 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.068319Z

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.

Observation 8ca9d54d-76bd-4019-af87-fba6bb10bc3e · outbound

This paper cites Summing up the facts: Additive mechanisms behind factual recall in llms, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Summing up the facts: Additive mechanisms behind factual recall in llms, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.054015Z

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.

Observation 1e846ff2-6ed8-4deb-8034-b1fb20869d90 · outbound

This paper cites Induction heads as an essential mechanism for pattern matching in in-context learning.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Induction heads as an essential mechanism for pattern matching in in-context learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.040339Z

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.

Observation 83408a97-f0ab-447b-a5e6-c01f0c6a15c1 · outbound

This paper cites Knowledge neurons in pretrained transformers.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Knowledge neurons in pretrained transformers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.655162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cc6a85-ddda-418d-9e36-2645fb4adb39 · outbound

This paper cites Attention is not all you need: Pure attention loses rank doubly exponentially with depth.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Attention is not all you need: Pure attention loses rank doubly exponentially with depth

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.027077Z

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.

Observation 28cc1dae-114a-43c7-a596-2b6d94072207 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.667162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d511882-7077-4c50-b2ab-5aa70f144bfa · outbound

This paper cites Edelman, eran malach, and Surbhi Goel.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Edelman, eran malach, and Surbhi Goel

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:24.008710Z

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.

Observation 6de929e4-298d-4f9f-bd46-dcf17694bbd6 · outbound

This paper cites A mathematical framework for transformer circuits.Transformer Circuits Thread, 2021.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer A mathematical framework for transformer circuits.Transformer Circuits Thread, 2021

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.989975Z

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.

Observation 58bf9a70-406d-4f25-8238-7eedfc9358da · outbound

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

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Transformer Feed-Forward Layers Are Key-Value Memories

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.682505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c47962c0-f560-41db-b6ee-fa5f74c6d609 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Transformer feed-forward layers are key-value memories

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.687732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f87075-542c-4a28-afc8-718b2ecba1d3 · outbound

This paper cites Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.692163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc95dbb-4299-4414-a852-483b5d696015 · outbound

This paper cites Dissectingrecalloffactualassociations inauto-regressivelanguagemodels.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Dissectingrecalloffactualassociations inauto-regressivelanguagemodels

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.696572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e0fa06-aee0-48fa-b920-79811df9a4f2 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.701367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9631f467-18cd-46a7-aa33-fb364dfc04cf · outbound

This paper cites Smith, and Roy Schwartz.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Smith, and Roy Schwartz

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.974388Z

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.

Observation 2849f7ac-531f-4d2e-9980-80ffde91facd · outbound

This paper cites Simplifying Transformer Blocks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Simplifying Transformer Blocks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.710780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20848180-274a-4d69-a981-68c6b2675f35 · outbound

This paper cites Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.716704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 547444a1-677d-4f56-a61f-815b88a3eef3 · outbound

This paper cites What is the best multi-stage architecture for object recognition? In2009 IEEE 12th International Conference on Computer Vision, pages 2146–2153, 2009.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer What is the best multi-stage architecture for object recognition? In2009 IEEE 12th International Conference on Computer Vision, pages 2146–2153, 2009

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.722380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 657d772e-82b4-4721-82b6-807cdc2c3692 · outbound

This paper cites Lexico: Extreme kv cache compression via sparse coding over universal dictionaries, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Lexico: Extreme kv cache compression via sparse coding over universal dictionaries, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.960220Z

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.

Observation 1487f04a-6d72-4d38-87fd-03cc49bd03a7 · outbound

This paper cites Deep Neural Networks as Gaussian Processes.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Deep Neural Networks as Gaussian Processes

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.735092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712c06fc-030a-4711-a0f1-dbb80d30ae53 · outbound

This paper cites FNet: Mixing Tokens with Fourier Transforms.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer FNet: Mixing Tokens with Fourier Transforms

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.740900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2b73b7-af45-463d-9a16-cae3f6618d03 · outbound

This paper cites The neural covariance sde: Shaped infinite depth-and-width networks at initialization.Advances in Neural Information Processing Systems, 35:10795–10808, 2022.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer The neural covariance sde: Shaped infinite depth-and-width networks at initialization.Advances in Neural Information Processing Systems, 35:10795–10808, 2022

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.946050Z

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.

Observation 59b06326-5916-47b7-9a17-d49c8b382d79 · outbound

This paper cites Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.750524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8d18586-9ccc-4f75-92cb-096e3db23870 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Locating and Editing Factual Associations in GPT

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.755732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0aca01b-a1f7-4fd7-a5da-eabfdb3d31f5 · outbound

This paper cites Pointer Sentinel Mixture Models.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Pointer Sentinel Mixture Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.760917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1565742c-8d44-47e6-a5d7-46ce1da0bc03 · outbound

This paper cites Language models implement simple word2vec-style vector arithmetic, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Language models implement simple word2vec-style vector arithmetic, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.927859Z

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.

Observation 80ff018a-334f-4a56-abb3-99e13bcdbd6a · outbound

This paper cites Universal approximation property of random neural networks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Universal approximation property of random neural networks

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.911077Z

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.

Observation 21a9c1d6-595c-4cb0-9df0-32949282d797 · outbound

This paper cites Signal propagation in transformers: Theoretical perspectives and the role of rank collapse.Advances in Neural Information Processing Systems, 35:27198–27211, 2022.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Signal propagation in transformers: Theoretical perspectives and the role of rank collapse.Advances in Neural Information Processing Systems, 35:27198–27211, 2022

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.775855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d5c8a7b-2e2e-4611-8957-ff5225150e0b · outbound

This paper cites The shaped transformer: Attention models in the infinite depth-and-width limit.Advances in Neural Information Processing Systems, 36:54250–54281, 2023.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer The shaped transformer: Attention models in the infinite depth-and-width limit.Advances in Neural Information Processing Systems, 36:54250–54281, 2023

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.880239Z

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.

Observation dbacfc98-69da-4b05-ac89-594e5b700859 · outbound

This paper cites Investigating the Limitations of Transformers with Simple Arithmetic Tasks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Investigating the Limitations of Transformers with Simple Arithmetic Tasks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.784025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0211457a-d6c4-426d-b890-b1f416dfa5b7 · outbound

This paper cites In-context Learning and Induction Heads.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer In-context Learning and Induction Heads

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.788567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a25774c-81d1-49bd-bc77-47473673ab53 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.793335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dcd428a-9b5d-4e5f-987c-30bbdeab8320 · outbound

This paper cites Mechanistic Design and Scaling of Hybrid Architectures.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Mechanistic Design and Scaling of Hybrid Architectures

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.798604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021dc086-0b6c-4db4-8065-c4b2caa7fd2e · outbound

This paper cites Exponential expressivity in deep neural networks through transient chaos.Advances in neural information processing systems, 29, 2016.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Exponential expressivity in deep neural networks through transient chaos.Advances in neural information processing systems, 29, 2016

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.804007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5569d08c-f9ac-48ce-88af-7ae4d248fd97 · outbound

This paper cites Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.808829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd623bde-0640-418a-83e6-52d2867d6da9 · outbound

This paper cites Transformers, parallel computation, and logarithmic depth.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Transformers, parallel computation, and logarithmic depth

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.814818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d2c10c-c4bd-4ca0-97d0-bf2ca5d19531 · outbound

This paper cites Saxe, Pang Wei Koh, Zhenghao Chen, Maneesh Bhand, Bipin Suresh, and Andrew Y.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Saxe, Pang Wei Koh, Zhenghao Chen, Maneesh Bhand, Bipin Suresh, and Andrew Y

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.855012Z

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.

Observation 4aaf9a34-45f3-46e3-bf4c-199425e2134a · outbound

This paper cites Deep Information Propagation.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Deep Information Propagation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.825593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eaae48b-ba2b-486d-a579-8517c8271da9 · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.830990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6875d19-b787-4d3f-a7f3-4611c9930bcd · outbound

This paper cites Synthesizer: Rethinking self-attention in transformer models.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Synthesizer: Rethinking self-attention in transformer models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.827631Z

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.

Observation 63bf97f3-c7f4-429d-99be-880d433f5eb0 · outbound

This paper cites Efficient Transformers: A Survey.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Efficient Transformers: A Survey

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.842653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b34f8d58-6c3e-4c0d-99b8-b42f47b9359d · outbound

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

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Gemini: A Family of Highly Capable Multimodal Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.848934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d52af51-62e5-487e-b502-cf2f62f01f67 · outbound

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

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer LLaMA: Open and Efficient Foundation Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.853190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc020708-d608-41be-92e3-0f469d4e5e57 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.858670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3defb31-0d36-4736-8d53-77758ef0d9be · outbound

This paper cites Efficient streaming language models with attention sinks.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Efficient streaming language models with attention sinks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.862990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 096338b0-aec6-4fa4-8739-8d2059421669 · outbound

This paper cites On layer normalization in the transformer architecture.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer On layer normalization in the transformer architecture

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.867299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e41da55c-0d29-4096-a942-585c53b48eb9 · outbound

This paper cites Mean field residual networks: On the edge of chaos.Advances in neural information processing systems, 30, 2017.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Mean field residual networks: On the edge of chaos.Advances in neural information processing systems, 30, 2017

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.782386Z

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.

Observation 62a6dff9-fa4b-41a5-83b7-798521dfa5b2 · outbound

This paper cites Knowledge Circuits in Pretrained Transformers.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Knowledge Circuits in Pretrained Transformers

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.877534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04f9a6a8-d1a4-4ed3-a4b2-cb39ecf1b7a0 · outbound

This paper cites Locating factual knowledge in large language models: Exploring the residual stream and analyzing subvalues in vocabulary space, 2024.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Locating factual knowledge in large language models: Exploring the residual stream and analyzing subvalues in vocabulary space, 2024

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.768403Z

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.

Observation 56cf4fe1-77de-43a9-a710-6a90ec70ae58 · outbound

This paper cites Are transformers universal approximators of sequence-to-sequence functions? InInternational Conference on Learning Representations, 2020.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Are transformers universal approximators of sequence-to-sequence functions? InInternational Conference on Learning Representations, 2020

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.753867Z

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.

Observation 82e33590-6882-4b6a-9e7f-16ecdf82cd1a · outbound

This paper cites Understanding deep learning requires rethinking generalization.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Understanding deep learning requires rethinking generalization

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.891916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6072648-2491-47d1-9f03-c2373e9c0d1c · outbound

This paper cites Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-08-07T11:57:23.011772Z

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.

Observation 294b2fae-c881-45c7-a025-2371793ba2e9 · outbound

This paper cites Character-level Convolutional Networks for Text Classification.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Character-level Convolutional Networks for Text Classification

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T11:57:22.901611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b1f9f34-206f-4e51-ae70-d8265d664326 · outbound

This paper cites Algorithmic capabilities of random transformers.

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer Algorithmic capabilities of random transformers

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:57:23.740198Z

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.

Pith citing papers

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

Provable Knowledge Acquisition and Extraction in One-Layer Transformers cites this paper.

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 2026-08-07T06:34:17.273281+00:00.

Observation 25956d3d-2ece-4dbc-bcf9-d6d2a8a4b5f6 · inbound

DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers cites this paper.

DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T13:15:07.096284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9087432-cd4e-42a1-8b5b-3fa872b1f2c0 · inbound

Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity cites this paper.

Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:21:19.053632Z

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.

Observation 5cd2c773-03ed-4a2b-a62c-a709c6b164d2 · inbound

Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity cites this paper.

Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-22T11:54:51.174733Z

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.

Observation 2ef29a84-3c61-4c99-a577-712726e622bb · inbound

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

Procedural Pretraining: Warming Up Language Models with Abstract Data Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T06:55:10.047706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3d438d-9afd-463d-93e2-61c7f1e8720e · inbound

Geometry-Calibrated Conformal Abstention for Language Models cites this paper.

Geometry-Calibrated Conformal Abstention for Language Models Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:31:28.657564Z

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.

Observation 3103343d-d627-4c1d-b9a7-94dba112716b · inbound

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination cites this paper.

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:31:08.807728Z

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.

Observation b314efdc-8adb-44b0-8ae0-3031b2ecdab7 · inbound

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination cites this paper.

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:15:11.538789Z

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.

Observation 20037440-1bb0-4963-9551-f74d7b62b213 · inbound

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination cites this paper.

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-15T11:17:06.440358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028dea82-b222-470e-bee6-0ef6955c05fe · inbound

Fixed Universal Transformers cites this paper.

Fixed Universal Transformers Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:50.217756Z

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.

Observation 8dbf2c27-2496-441f-bdef-32e954d60dcf · inbound

Activation-Based Active Learning for In-Context Learning: Challenges and Insights cites this paper.

Activation-Based Active Learning for In-Context Learning: Challenges and Insights Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T07:56:47.882218Z

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.