Paper Citation Record · LEDGER

Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2103.03404.

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

pith.paper-citation-record.v1
2103.03404 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T14:44:17.462254Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T06:19:38.253882Z

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 ee40276e-c170-49cd-a169-82d56a59ebbb · inbound

In-context Learning and Induction Heads cites this paper.

In-context Learning and Induction Heads Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:49:09.744352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a17049bf-b9a5-4ee3-89b5-bda38e0eaa61 · inbound

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration cites this paper.

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T14:44:17.462254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b2b9c30-d6eb-4730-8da0-f488e78e0a60 · inbound

Sinkhorn doubly stochastic attention rank decay analysis cites this paper.

Sinkhorn doubly stochastic attention rank decay analysis Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:05:59.292726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 455cf994-a3e2-4173-9470-ac528c70ac49 · inbound

Dimension-Free Saddle-Point Escape in Muon cites this paper.

Dimension-Free Saddle-Point Escape in Muon Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:01:26.403986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c5a06c32-cc07-4233-b470-32c38fed02ad · inbound

Beyond Similarity: Temporal Operator Attention for Time Series Analysis cites this paper.

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T02:47:07.771417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c848069a-716c-4ff7-84db-0d46c211f43e · inbound

Beyond Similarity: Temporal Operator Attention for Time Series Analysis cites this paper.

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T14:15:46.535388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7d705153-7bd5-422b-8a59-0bc7f4dc7863 · inbound

ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projection cites this paper.

ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projection Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:19:26.891995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 33f1fe56-0821-4c6c-bbed-31e491881822 · inbound

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics cites this paper.

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:26.564575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 00e980be-b3ad-45a5-84bb-b49542d1bf8e · inbound

Dead Directions: Geometric Singular Learning cites this paper.

Dead Directions: Geometric Singular Learning Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-02T11:36:55.170688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 973b3cca-6c30-46c3-a1b0-a28d5625a331 · inbound

Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale cites this paper.

Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:29:15.303921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 07047b52-5e2d-42c1-a43e-3e4e8e6e4a83 · inbound

Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity cites this paper.

Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-04T06:19:38.255657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 73b51d3b-085e-4fac-995c-b1a33fed7b9a · inbound

Transient Reserves, Sink Dampers, and the Failure of Eigenvalue Reasoning in the Attention Propagator cites this paper.

Transient Reserves, Sink Dampers, and the Failure of Eigenvalue Reasoning in the Attention Propagator Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T04:11:56.715045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 822ff1e7-3b2e-4886-8d99-4a2f91d58481 · inbound

Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones cites this paper.

Kernelized Linear Attention: Breaking the Capacity Wall with Symmetric Cones Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T18:06:54.962658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89adde55-6e61-4217-8dfd-febc5b3d8ca6 · inbound

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing cites this paper.

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T11:37:08.732017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54e0922f-11bf-4393-8255-86fb5f61bc3f · inbound

Many-body Tipping Dynamics of ChatGPT-like AIs cites this paper.

Many-body Tipping Dynamics of ChatGPT-like AIs Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T02:56:53.550665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.