Paper Citation Record · LEDGER

An Uncertainty Principle for Linear Recurrent Neural Networks

As of 8 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2502.09287.

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

pith.paper-citation-record.v1
2502.09287 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T22:10:15.970118Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

19 of 19 outbound references displayed

verified exact0
verified fuzzy4
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 91035583-e0b6-425c-8a0c-e8edfb12ee08 · outbound

This paper cites The Hidden Attention of Mamba Models.

An Uncertainty Principle for Linear Recurrent Neural Networks The Hidden Attention of Mamba Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.869684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5827925-3971-442c-9a96-390106c0129b · outbound

This paper cites We have the following equality: +∞X L=0 L|wl|2 = i 2π Z 2π 0 dW (ω) dω W (ω)dω.

An Uncertainty Principle for Linear Recurrent Neural Networks We have the following equality: +∞X L=0 L|wl|2 = i 2π Z 2π 0 dW (ω) dω W (ω)dω

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:10:16.303931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7b14b8a1-92bd-41d2-b506-46f67cb8ad53 · outbound

This paper cites The loss Ltime(c, d) writes Ltime(c, d) = 1 + +∞X k=0 |ck|2 − 2Re +∞X k=0 ckdk , where ck = PS s=1 ak s bs.

An Uncertainty Principle for Linear Recurrent Neural Networks The loss Ltime(c, d) writes Ltime(c, d) = 1 + +∞X k=0 |ck|2 − 2Re +∞X k=0 ckdk , where ck = PS s=1 ak s bs

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:10:16.288327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a7cf5b77-e311-41f3-a804-2e779bb25e57 · outbound

This paper cites In-context Learning and Induction Heads.

An Uncertainty Principle for Linear Recurrent Neural Networks In-context Learning and Induction Heads

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.893978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f1b5c5-f89a-4c3c-a615-48294aef94ca · outbound

This paper cites Byte Latent Transformer: Patches Scale Better Than Tokens.

An Uncertainty Principle for Linear Recurrent Neural Networks Byte Latent Transformer: Patches Scale Better Than Tokens

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.898992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd148f1-0b79-4d3e-b370-2b16168f3bca · outbound

This paper cites HGRN2: Gated Linear RNNs with State Expansion.

An Uncertainty Principle for Linear Recurrent Neural Networks HGRN2: Gated Linear RNNs with State Expansion

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.909661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a1729de-bea0-4ad2-b717-173cf24fcef0 · outbound

This paper cites Provable Benefits of Complex Parameterizations for Structured State Space Models.

An Uncertainty Principle for Linear Recurrent Neural Networks Provable Benefits of Complex Parameterizations for Structured State Space Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.914320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd7186e-8082-4322-a602-6b3ba074244d · outbound

This paper cites Mimetic Initialization Helps State Space Models Learn to Recall.

An Uncertainty Principle for Linear Recurrent Neural Networks Mimetic Initialization Helps State Space Models Learn to Recall

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.924424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aada7242-859b-493d-97dc-367f16401d11 · outbound

This paper cites Linformer: Self-Attention with Linear Complexity.

An Uncertainty Principle for Linear Recurrent Neural Networks Linformer: Self-Attention with Linear Complexity

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.936398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4861c86-2a08-49fc-a7d7-aec6e08425eb · outbound

This paper cites Parallelizing Linear Transformers with the Delta Rule over Sequence Length.

An Uncertainty Principle for Linear Recurrent Neural Networks Parallelizing Linear Transformers with the Delta Rule over Sequence Length

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.942223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c146fea-16db-43d5-8311-454c600a4fe0 · outbound

This paper cites In particular it fully describes a linear time-invariant system.

An Uncertainty Principle for Linear Recurrent Neural Networks In particular it fully describes a linear time-invariant system

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:10:16.318990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bcd3a544-33af-4ab6-94df-9183db172ee6 · outbound

This paper cites an unresolved cited work.

An Uncertainty Principle for Linear Recurrent Neural Networks Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T22:10:16.271485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 69e8d9a6-0ab4-484e-816b-6a80ff987558 · outbound

This paper cites bu = e−α(e2α−e−2α) 2Kinit × (−1)u bu = e−α(e2α−e−2α) 2Kinit × (−1)u α 1 1 Kinit 1300 1300 Number epochs 60 60 Table E.1: Experimental details for Figure 4 (left).

An Uncertainty Principle for Linear Recurrent Neural Networks bu = e−α(e2α−e−2α) 2Kinit × (−1)u bu = e−α(e2α−e−2α) 2Kinit × (−1)u α 1 1 Kinit 1300 1300 Number epochs 60 60 Table E.1: Experimental details for Figure 4 (left)

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T22:10:16.253661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0a45fa97-2ece-42ec-b781-1eed4021434c · outbound

This paper cites Training Deep Nets with Sublinear Memory Cost.

An Uncertainty Principle for Linear Recurrent Neural Networks Training Deep Nets with Sublinear Memory Cost

Reference 1996

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.875426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 009fcbbb-28da-403e-80c2-4625f72bce77 · outbound

This paper cites Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence.

An Uncertainty Principle for Linear Recurrent Neural Networks Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.904632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d35879dc-01b4-4d26-ab0a-002583bd32b3 · outbound

This paper cites An Empirical Study of Mamba-based Language Models.

An Uncertainty Principle for Linear Recurrent Neural Networks An Empirical Study of Mamba-based Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.930676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 236f1407-e774-4ba7-8909-4d3f38801392 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

An Uncertainty Principle for Linear Recurrent Neural Networks Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.919445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b16394b4-5d9a-4a44-8eae-af6350b2a513 · outbound

This paper cites Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models.

An Uncertainty Principle for Linear Recurrent Neural Networks Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.888345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3631dce4-a96e-4364-9fea-7e859e6418f1 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

An Uncertainty Principle for Linear Recurrent Neural Networks FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T22:10:15.881607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.