Paper Citation Record · LEDGER

Theory, Analysis, and Best Practices for Sigmoid Self-Attention

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 25 inbound Pith citation observations for arXiv:2409.04431.

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

pith.paper-citation-record.v1
2409.04431 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 25 of 25 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T16:15:39.513319Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T21:17:24.595834Z

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 4c4a8870-83d9-4669-b8e3-f76ba36b05fd · inbound

When Attention Sink Emerges in Language Models: An Empirical View cites this paper.

When Attention Sink Emerges in Language Models: An Empirical View Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 42

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T17:41:03.735502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 696ec69e-2f2b-4cef-a77d-81ec2fb280fa · inbound

Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models cites this paper.

Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T16:15:39.513319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dc96183-e38f-4ce2-9f52-f5f2eb4a0572 · inbound

Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspection cites this paper.

Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspection Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T13:42:23.796832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d03266f-9e1e-4f01-b669-d63b7e13e42e · inbound

From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases cites this paper.

From Molecules to Mixtures: Learning Representations of Olfactory Mixture Similarity using Inductive Biases Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T13:41:14.511574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31572126-1d04-47c5-a89a-8b8c22a77a88 · inbound

A Unified Perspective on the Dynamics of Deep Transformers cites this paper.

A Unified Perspective on the Dynamics of Deep Transformers Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T00:04:10.926525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83fe0c0b-b786-43e1-a462-f18671deb5dd · inbound

Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective cites this paper.

Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T19:40:10.082924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54681b64-712b-4e5c-83a1-834e2d45ba3d · inbound

On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach cites this paper.

On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T13:05:31.676260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fbe8f8a-bc61-4074-905e-185e3b70a6d6 · inbound

Systematic Outliers in Large Language Models cites this paper.

Systematic Outliers in Large Language Models Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T15:37:37.515845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c125d649-43ce-4369-910f-d547675c7ca4 · inbound

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization cites this paper.

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:46:59.381114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2737a320-d6ae-4494-b67f-3d9d3bf4cc1d · 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 Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T06:10:19.778678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc2af75-1f8e-4578-b29a-6f39eeb387ac · inbound

Scaling Context Requires Rethinking Attention cites this paper.

Scaling Context Requires Rethinking Attention Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T20:00:43.782864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b93fb8e-4c74-4dcb-aca6-d41795f98465 · inbound

Your Attention Matters: to Improve Model Robustness to Noise and Spurious Correlations cites this paper.

Your Attention Matters: to Improve Model Robustness to Noise and Spurious Correlations Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T13:39:10.426250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e38e9aa0-9fda-4b27-abae-cde295d70edc · inbound

Capacity-Controlled Global Attention for Graph Transformers cites this paper.

Capacity-Controlled Global Attention for Graph Transformers Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:31:30.767360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f86867b3-92f9-4a80-a47b-29f35ab9a31c · inbound

Cubit: Token Mixer with Kernel Ridge Regression cites this paper.

Cubit: Token Mixer with Kernel Ridge Regression Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 63

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:06:10.787346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b7950fc4-5026-4447-862f-bced4a513992 · inbound

Cubit: Token Mixer with Kernel Ridge Regression cites this paper.

Cubit: Token Mixer with Kernel Ridge Regression Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 63

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T22:39:11.009258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a8f9fc8d-b472-4959-8fea-6820f08824cb · inbound

The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity cites this paper.

The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:21:08.516991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b1fd8067-78c2-4245-94e1-f0862b4855c7 · inbound

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models cites this paper.

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:36:40.797845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2ae133e3-518a-4b55-8959-1c2719b83d1e · inbound

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models cites this paper.

A Single Layer to Explain Them All:Understanding Massive Activations in Large Language Models Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:19:29.111658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d20d30e7-4356-401e-b839-9e29cde7c142 · inbound

Complex-Valued Phase-Coherent Transformer cites this paper.

Complex-Valued Phase-Coherent Transformer Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:16:28.147412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d057774a-4e16-460f-8f77-6f7cac95eb0f · inbound

Complex-Valued Phase-Coherent Transformer cites this paper.

Complex-Valued Phase-Coherent Transformer Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T14:31:47.302932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d1e8f8-de0a-4812-82f2-b7527e32b3e9 · inbound

Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor cites this paper.

Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:19:42.072047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 830e1fcf-1c26-46f4-8683-29111e1fc631 · inbound

Towards Understanding Self-Pretraining for Sequence Classification cites this paper.

Towards Understanding Self-Pretraining for Sequence Classification Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 178

Resolution: verified exact; arxiv_id, observed 2026-05-21T05:33:58.908338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9c37073b-4edb-41c7-8e1f-4e2442124a49 · inbound

Forget Attention: Importance-Aware Attention Is All You Need cites this paper.

Forget Attention: Importance-Aware Attention Is All You Need Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:06:21.024853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a2f19bb8-9c0a-4305-87cd-56ab4aabf127 · inbound

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions cites this paper.

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-02T21:17:24.597286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4ea3e01-b25e-48db-861b-8dc620cab92f · inbound

Legible-by-Construction: Attention and End-to-End Transformers cites this paper.

Legible-by-Construction: Attention and End-to-End Transformers Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T20:06:55.102341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.