Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links
Paper Citation Record · LEDGER
On the Expressive Power of Self-Attention Matrices
As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2106.03764.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T15:49:15.637004Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-02T16:07:09.244510Z
Reference resolution
0 of 0 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
No outbound reference observations are available for this paper version.
Pith citing papers
Observation e16670d8-40d1-4f20-8134-227a63d0a8e5 · inbound
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models cites this paper.
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models On the Expressive Power of Self-Attention Matrices
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T18:00:50.487379Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation e438c3b7-fe55-4df0-8a73-d28372071b9c · inbound
A Theory for Compressibility of Graph Transformers for Transductive Learning cites this paper.
A Theory for Compressibility of Graph Transformers for Transductive Learning On the Expressive Power of Self-Attention Matrices
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-12T17:05:46.778144Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 41d3ef9c-2de4-41fd-9c7d-7c548ac28b21 · inbound
Transformers Meet In-Context Learning: A Universal Approximation Theory cites this paper.
Transformers Meet In-Context Learning: A Universal Approximation Theory On the Expressive Power of Self-Attention Matrices
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T10:33:40.270823Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dae4161d-c791-40f6-9e6c-693df28b69e8 · inbound
Sample Complexity and Representation Ability of Test-time Scaling Paradigms cites this paper.
Sample Complexity and Representation Ability of Test-time Scaling Paradigms On the Expressive Power of Self-Attention Matrices
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T10:35:36.139688Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a19f856e-914a-4962-bedf-4c7694a05efa · inbound
A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization cites this paper.
A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization On the Expressive Power of Self-Attention Matrices
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T06:10:19.335874Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b1cb341f-a7b4-484e-9edb-60d51ab010aa · inbound
Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation cites this paper.
Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation On the Expressive Power of Self-Attention Matrices
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T15:49:15.637004Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation da8a465b-761c-47b6-bc01-42d036604257 · inbound
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling cites this paper.
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling On the Expressive Power of Self-Attention Matrices
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T12:41:04.835429Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 1ed87fb8-3af5-4121-bb4b-e6d5813b42fa · inbound
Analogies between Transformer Layers and Power Method cites this paper.
Analogies between Transformer Layers and Power Method On the Expressive Power of Self-Attention Matrices
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-06-29T23:04:01.118155Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 799df850-cbc4-4436-8b2d-93ae6a3b9a51 · inbound
Looped Transformers with Layer Normalization Provably Learn the Power Method cites this paper.
Looped Transformers with Layer Normalization Provably Learn the Power Method On the Expressive Power of Self-Attention Matrices
Reference 69
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-28T19:22:35.265340Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation e8c213b2-ba2d-4643-82aa-08986371a909 · inbound
UNIVID: Unified Vision-Language Model for Video Moderation cites this paper.
UNIVID: Unified Vision-Language Model for Video Moderation On the Expressive Power of Self-Attention Matrices
Reference 67
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T16:07:09.246168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.