Pith. sign in

Paper Citation Record · LEDGER

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification

As of 10 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 2 inbound Pith citation observations for arXiv:2509.24901.

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

pith.paper-citation-record.v1
2509.24901 v4

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T13:51:47.139538Z

measured 18 of 18 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:41:17.172433Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T01:53:28.882358Z

Reference resolution

16 of 16 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved15
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5c9991aa-4113-4371-83e7-9dfd0ec48e07 · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification BEiT: BERT Pre-Training of Image Transformers

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:44.534864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:44.534864Z digest=sha256:81e903492df071ad3e9cfa35b814444a8ce8eccbebd2c709eee200ac24154b7f

Observation 483a9fdf-7bb7-4c01-96f0-73ed0886bf1b · outbound

This paper cites FSD50K: An Open Dataset of Human-Labeled Sound Events.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification FSD50K: An Open Dataset of Human-Labeled Sound Events

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:44.964946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:44.964946Z digest=sha256:1b2758a56e63af46817ed3336301242954b18c3561b91043e61629741ee9f047

Observation b9403435-813d-4cd1-b711-585b9cdc84b3 · outbound

This paper cites an unresolved cited work.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:45.073835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:45.073835Z digest=sha256:b8d16564b8d91bcf5a11f6dcc96735c5441983ab6f1024eb8ef69d27f85bc4b9

Observation acf87fba-89c4-4b71-b83b-22b55499c320 · outbound

This paper cites The jump in performance fromJ= 1,J= 5andJ= 10is notable on all datasets, though the impact varies on the task (multi-class vs.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification The jump in performance fromJ= 1,J= 5andJ= 10is notable on all datasets, though the impact varies on the task (multi-class vs

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:46.998603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:46.998603Z digest=sha256:e01bc093490f3c7a0bf0460bd64fd71a4c7ed88d6c4a2b8c9dd65823b28fe105

Observation 2d31acf5-fc77-4ee5-933a-46ffcc4ee100 · outbound

This paper cites Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:45.510904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:45.510904Z digest=sha256:9e950da2d44baca610485a5d3f47af029c1e3fbdd196bccdd6eaadea82ee4e2b

Observation 1126efe5-53a2-4b65-87e5-648bebe1ceef · outbound

This paper cites Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos, and Yannis Avrithis.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos, and Yannis Avrithis

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:45.932701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:45.932701Z digest=sha256:ba8d66d17e2eac94802f8f87543f660d22bd4a0ff9ac658ec2cae3c0726130f9

Observation 939ccac5-4938-4078-8a55-adea5dd32e84 · outbound

This paper cites Attention, please! revisiting attentive probing for masked image modeling.arXiv:2506.10178,.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Attention, please! revisiting attentive probing for masked image modeling.arXiv:2506.10178,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:46.105002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:46.105002Z digest=sha256:f41b8da8349948f9dafaacd86c3f613da0fdd991878cf69c42dba88c1a1fdddf

Observation fa0e470b-4070-421c-ba6d-1b6d1550011b · outbound

This paper cites Can Masked Autoencoders Also Listen to Birds?.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Can Masked Autoencoders Also Listen to Birds?

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:46.257438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:46.257438Z digest=sha256:574a5213508843b76af9abf8ffd958ec9b0aaa9ba1380cbdd92e60e724c59d2d

Observation 92cc30c8-ef08-4fa3-9ed2-37e0f72b5b32 · outbound

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

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:46.603532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:46.603532Z digest=sha256:8094976311b661f1288c0a4527f19e0d58cd5a40f618011cbca821fd839c6b8d

Observation f9cddc22-e859-425f-93d3-30d1bf297250 · outbound

This paper cites an unresolved cited work.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Unresolved cited work

Reference 17

Resolution
malformed identifier
no resolver link, observed 2026-08-04T13:51:46.832485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:46.832485Z digest=sha256:bad35171283d36475ab738bf41110748ce119b13c936b4294acb0801bcf68a10

Observation d8e40391-f916-4f65-87c9-9a6acb77d6d3 · outbound

This paper cites up," "down,.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification up," "down,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:47.139538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:47.139538Z digest=sha256:8c1f9dbbf157182bf187a90212c158fc540ca2d3fd4bc4c49876cfb1aeca48ef

Observation f1de531d-941d-462b-956b-d309b4b07675 · outbound

This paper cites HEAR: Holistic Evaluation of Audio Representations.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification HEAR: Holistic Evaluation of Audio Representations

Reference 1998

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:46.382975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:46.382975Z digest=sha256:ad4c6e287a124f7492aa38bd59f67d7e7f8878ea6bc2fad32951efefe3492982

Observation 61d63d61-a0cd-4ba1-927c-a37d6f3cbadb · outbound

This paper cites DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification DESED-FL and URBAN-FL: Federated Learning Datasets for Sound Event Detection

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:45.181707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:45.181707Z digest=sha256:992c439f839395e36414e5326f924549fe2eeeb87fd1d7d76c0d7321d18a8f4c

Observation 0bb5a247-e98e-45e9-a2fd-f5546afb9ee6 · outbound

This paper cites Leonardo Pepino, Pablo Riera, and Luciana Ferrer.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Leonardo Pepino, Pablo Riera, and Luciana Ferrer

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:45.648135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:45.648135Z digest=sha256:b7b2521e5f89355a3702ab3e993804c60aea30fe6ff99c336c7aa227f9d81c7b

Observation 4bf3bd0f-d82b-46bc-85f3-ce44dff427fd · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:44.715869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:44.715869Z digest=sha256:6cafbd089411302c45fafbc0575a67f5419212550cdb09849b8e6a5222cb0125

Observation 491785a8-3459-4e14-8b06-35b25e30ec36 · outbound

This paper cites Scaling up masked audio encoder learning for general audio classification.

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification Scaling up masked audio encoder learning for general audio classification

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-04T13:51:44.825761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T13:51:44.825761Z digest=sha256:50eb9d1966c75ef76db3fc38135b7736ff7beede3b1d5cf8b726b0c9ee4c5122

Pith citing papers

Observation 6c12c591-c1b3-4fbe-ba14-1d56292205f6 · inbound

BAT: Better Audio Transformer Guided by Convex Gated Probing cites this paper.

BAT: Better Audio Transformer Guided by Convex Gated Probing Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T22:41:17.172433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T22:41:17.172433Z digest=sha256:f1d5833621b2670dcc7c3287c91035c2ad19cc0e012e5f36255d29f93acad590

Observation 05f792ba-a12e-4388-9066-1c2db1efbf8a · inbound

AudioMosaic: Contrastive Masked Audio Representation Learning cites this paper.

AudioMosaic: Contrastive Masked Audio Representation Learning Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-06-01T03:02:52.993424Z

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.

source=pdf_text observed=2026-05-15T01:52:01.164694Z digest=sha256:00cb9fdcb0499fad9a0f860bd00ae5d3916c1bd16cab8527d18fb3720d750db4