Paper Citation Record · LEDGER

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition

As of 10 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2509.02167.

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

pith.paper-citation-record.v1
2509.02167 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T11:53:54.547534Z

measured 40 of 40 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T11:53:49.384591Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T11:53:55.094282Z

Reference resolution

39 of 39 outbound references displayed

verified exact2
verified fuzzy21
unresolved14
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5d7b5314-83f6-4df3-8a15-aba6ddc68a21 · outbound

This paper cites AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-05T11:53:55.162555Z

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 536b2a48-c3fd-496c-9a1e-e5c750215264 · outbound

This paper cites It retains the global mod- eling strengths of AST while reducing computational complexity to a linear scale, offering an efficient solu- tion for long-form audio processing.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition It retains the global mod- eling strengths of AST while reducing computational complexity to a linear scale, offering an efficient solu- tion for long-form audio processing

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:54:01.600573Z

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 e20589e9-25bc-4a38-bcf2-9ef89d58f54f · outbound

This paper cites These operators, tailored for spectro- grams, achieve effective and efficient feature aggrega- tion across both local and global scopes.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition These operators, tailored for spectro- grams, achieve effective and efficient feature aggrega- tion across both local and global scopes

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:54:01.330511Z

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 3b4658d1-8e24-4869-b633-3afecb31da47 · outbound

This paper cites an unresolved cited work.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-05T11:54:01.030114Z

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 6739b134-07ab-4f26-8a69-23adfe04159e · outbound

This paper cites an unresolved cited work.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-05T11:54:00.790055Z

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 adf821e6-068d-4222-adbb-adcdfe569f1b · outbound

This paper cites The foundational principle is the systematic replacement of the original 1D token shift operation with a 2D depthwise sep- arable convolution (DWConv2D).

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition The foundational principle is the systematic replacement of the original 1D token shift operation with a 2D depthwise sep- arable convolution (DWConv2D)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:54:00.549003Z

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 8c21b171-5196-4ffd-bf38-f22686050f0a · outbound

This paper cites an unresolved cited work.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Unresolved cited work

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T11:54:00.276406Z

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 90328a63-2305-44ce-8721-212e341adf00 · outbound

This paper cites RWKVTTS: Yet another TTS based on RWKV-7.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition RWKVTTS: Yet another TTS based on RWKV-7

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-05T11:53:54.896036Z

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 5314c450-f05b-4b52-ab70-92516f977913 · outbound

This paper cites an unresolved cited work.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-05T11:53:59.778527Z

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 eb98f675-d7e4-492b-8b2c-e62cd6612d3b · outbound

This paper cites Attention is all you need,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Attention is all you need,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:59.282754Z

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 42ff4c91-f7c9-496b-8361-45e461633d6d · outbound

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

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:50.717517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6ded1af-efc1-4f22-8969-8af1e09bab3e · outbound

This paper cites AST: Audio Spectrogram Transformer.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition AST: Audio Spectrogram Transformer

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:50.790037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40fa1698-b74a-4009-ac77-d67afbeb9e6c · outbound

This paper cites Retentive Network: A Successor to Transformer for Large Language Models.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Retentive Network: A Successor to Transformer for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:50.909936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587e81eb-4990-4095-88ff-3895acba3b16 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:51.063273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25271590-aec1-431f-84a9-a159116c1656 · outbound

This paper cites RWKV: Reinventing RNNs for the Transformer Era.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition RWKV: Reinventing RNNs for the Transformer Era

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:51.201413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b225d98c-e591-464d-9e23-0addb77d22d5 · outbound

This paper cites Exploring re- ceptance weighted key value model for single-channel speech enhancement,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Exploring re- ceptance weighted key value model for single-channel speech enhancement,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:59.023638Z

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 f1c26549-b12b-4c1a-b6e5-8cd91149ec2a · outbound

This paper cites Random erasing data augmentation,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Random erasing data augmentation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:57.694964Z

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 1d20c0d3-b108-4ba0-9cda-289baf706212 · outbound

This paper cites Audio mamba: Bidirectional state space model for audio representation learning,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Audio mamba: Bidirectional state space model for audio representation learning,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:58.770901Z

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 0ced0081-ec59-4c27-8456-a5de5d42075c · outbound

This paper cites Under- standing the differences in foundation models: Atten- tion, state space models, and recurrent neural networks,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Under- standing the differences in foundation models: Atten- tion, state space models, and recurrent neural networks,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:58.518357Z

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 f39e0242-222e-4c32-9dd1-7c7a5d155913 · outbound

This paper cites Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:51.917531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 776d8b07-073e-4d2f-bc8e-45fe0c7dc570 · outbound

This paper cites RWKV-7 "Goose" with Expressive Dynamic State Evolution.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition RWKV-7 "Goose" with Expressive Dynamic State Evolution

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:52.041109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3896f88c-7ce9-44a9-a5f1-855e479a4221 · outbound

This paper cites Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:52.155005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6abc6125-6f2c-4642-9114-de3d469b31b8 · outbound

This paper cites Decoupled weight decay regularization,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Decoupled weight decay regularization,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:58.285027Z

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 4d0d1331-13ba-4d45-a492-6a2660c58d65 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition mixup: Beyond Empirical Risk Minimization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:52.397641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be58aa97-f326-48bb-a47f-c175fc82a4d2 · outbound

This paper cites Cutmix: Regularization strategy to train strong clas- sifiers with localizable features,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Cutmix: Regularization strategy to train strong clas- sifiers with localizable features,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:58.005781Z

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 102a30c9-f669-4f1c-99ed-dafd7ab55219 · outbound

This paper cites Mlp-mixer: An all-mlp architecture for vision,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Mlp-mixer: An all-mlp architecture for vision,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:55.951124Z

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 ef788e8b-619d-4033-a21d-1e57032f8d4e · outbound

This paper cites Deep networks with stochas- tic depth,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Deep networks with stochas- tic depth,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:57.407014Z

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 d9c9adb7-aa6c-4b24-a01a-52f38c393342 · outbound

This paper cites When does label smoothing help?,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition When does label smoothing help?,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:57.143445Z

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 0866b9c4-b61e-4a69-8527-1b6e38a95b33 · outbound

This paper cites Audio set: An on- tology and human-labeled dataset for audio events,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Audio set: An on- tology and human-labeled dataset for audio events,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:56.917985Z

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 6f2149a7-ed3d-4c22-bfc0-237da49634a6 · outbound

This paper cites Esc: Dataset for environmental sound classification,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Esc: Dataset for environmental sound classification,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:56.746656Z

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 e2b2399c-4d38-4ded-bec8-73593f06a801 · outbound

This paper cites Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:53.504502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d16a8a0-c34f-4284-90b1-5573c7e75ab5 · outbound

This paper cites Neural audio synthesis of musical notes with wavenet autoencoders,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Neural audio synthesis of musical notes with wavenet autoencoders,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:56.521139Z

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 1aea9e82-00cf-4c26-9342-6084077be914 · outbound

This paper cites Vggsound: A large-scale audio-visual dataset,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Vggsound: A large-scale audio-visual dataset,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:56.339384Z

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 2aeb2dbd-1388-40db-9017-e91c50dff9bc · outbound

This paper cites Flashattention: Fast and memory- efficient exact attention with io-awareness,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Flashattention: Fast and memory- efficient exact attention with io-awareness,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:56.151062Z

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 80fac33c-0b5c-4142-a06b-644c251fdbf6 · outbound

This paper cites Scaling vision transformers,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Scaling vision transformers,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:55.743021Z

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 bcb77829-516e-40b2-b5ed-6da30fff40a4 · outbound

This paper cites Masked autoencoders are scalable vision learners,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Masked autoencoders are scalable vision learners,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:55.531342Z

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 1ba06d8d-94ec-4f9d-abc4-bd1b78d57ac4 · outbound

This paper cites Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T11:53:54.417924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad199023-d38e-4c33-afb8-b426fe76141a · outbound

This paper cites Localmamba: Visual state space model with windowed selective scan,.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition Localmamba: Visual state space model with windowed selective scan,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T11:53:55.367332Z

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 220a0f42-392c-4f13-bc20-7ea5f3939001 · outbound

This paper cites 2, A-RWKV scales smoothly from tiny to small to base with consistent gains across bench- marks, aligning with our motivation for a stable, linear-time sequence operator.

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition 2, A-RWKV scales smoothly from tiny to small to base with consistent gains across bench- marks, aligning with our motivation for a stable, linear-time sequence operator

Reference 384

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T11:54:00.012263Z

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.

Pith citing papers

Observation 5d7b5314-83f6-4df3-8a15-aba6ddc68a21 · inbound