Paper Citation Record · LEDGER

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems

As of 18 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2509.09204.

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

pith.paper-citation-record.v1
2509.09204 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:37:20.032674Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:37:19.845568Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9787d61d-9a3c-45ab-8116-b09ea132943a · outbound

This paper cites Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.845568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3db7060-36b3-4c75-910f-bf9efaba2d2c · outbound

This paper cites Despite this limita- tion, previous work [9,12,16] still merges synthesizer subsets into a single test set (e.g.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Despite this limita- tion, previous work [9,12,16] still merges synthesizer subsets into a single test set (e.g

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.851707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5549b5a4-d040-4b5f-90ce-1832c5e098cc · outbound

This paper cites No- tably, bona fide speech types contribute significantly to the challenges faced by ADD systems, whereas traditional ap- proaches primarily focus on the synthesizer type.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems No- tably, bona fide speech types contribute significantly to the challenges faced by ADD systems, whereas traditional ap- proaches primarily focus on the synthesizer type

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.856416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66fc658f-7d89-4b9c-8bd2-ff524975b2c0 · outbound

This paper cites Our approach demon- strates greater robustness and interpretability compared to traditional evaluation methods.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Our approach demon- strates greater robustness and interpretability compared to traditional evaluation methods

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.861172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e76e2344-e44d-42cd-9df5-655893b0e150 · outbound

This paper cites an unresolved cited work.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.865996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09557d06-8825-42f3-a824-06debfc8474b · outbound

This paper cites an unresolved cited work.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.870523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35971a4a-3dd2-4fe1-952b-dfb13ec0de07 · outbound

This paper cites In-The-Wild [25] is not included in the spoof test subsets as it uses unknown number of synthesizers.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems In-The-Wild [25] is not included in the spoof test subsets as it uses unknown number of synthesizers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.875469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ab79dc5-985b-4dea-b109-8e2083bd2c73 · outbound

This paper cites As shown in Figure 2, all models perform well in datasets created in or before 2022.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems As shown in Figure 2, all models perform well in datasets created in or before 2022

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.880369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c8a24be-c891-41da-9065-fda01a072c88 · outbound

This paper cites To support further research, we provide datasets and evaluation codes, aiming to drive the development of more robust and resilient audio deepfake detec- tion models.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems To support further research, we provide datasets and evaluation codes, aiming to drive the development of more robust and resilient audio deepfake detec- tion models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.885440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb266d18-cfed-47f7-96f3-eb3dc146ee46 · outbound

This paper cites an unresolved cited work.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.890791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 983c3f8f-8b96-48ba-ab00-a01b84ff69e1 · outbound

This paper cites Robust audio deep- fake detection using ensemble confidence calibration,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Robust audio deep- fake detection using ensemble confidence calibration,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.895206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57c075d4-d03b-407c-88ac-655fb15cc580 · outbound

This paper cites Asvspoof 2021: Towards spoofed and deepfake speech detection in the wild,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Asvspoof 2021: Towards spoofed and deepfake speech detection in the wild,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.899594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f76eaf6c-5b5c-4348-b130-a09db64bd8a7 · outbound

This paper cites MLAAD: The Multi-Language Audio Anti-Spoofing Dataset.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems MLAAD: The Multi-Language Audio Anti-Spoofing Dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.904207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6824df7e-c28d-4f3f-8f53-165621644c63 · outbound

This paper cites CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.909337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fa0cca7-017f-4d7b-8f75-ac1e819c350b · outbound

This paper cites Asvspoof 2019: A large-scale public database of synthesized, converted and replayed speech,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Asvspoof 2019: A large-scale public database of synthesized, converted and replayed speech,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.913987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04ea983-ab43-4522-9a52-858bfb5a9f92 · outbound

This paper cites Emofake: An initial dataset for emotion fake audio detection,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Emofake: An initial dataset for emotion fake audio detection,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.918450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2235a1cd-3eca-4171-b242-f8943ab8e71a · outbound

This paper cites A method of estimating the equal error rate for automatic speaker verification,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems A method of estimating the equal error rate for automatic speaker verification,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.922923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce114f69-56c5-4d09-961f-778545175844 · outbound

This paper cites Learning a self- supervised domain-invariant feature representation for general- ized audio deepfake detection,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Learning a self- supervised domain-invariant feature representation for general- ized audio deepfake detection,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.927213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68abfeae-89c4-48c8-9d4e-bf5ba4ab9eac · outbound

This paper cites A conformer-based classifier for variable-length utterance pro- cessing in anti-spoofing,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems A conformer-based classifier for variable-length utterance pro- cessing in anti-spoofing,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.931620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ead35a1-9cfb-44d6-87eb-578ac5abd107 · outbound

This paper cites Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.935874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19937532-bc85-40be-9541-54070cc79a19 · outbound

This paper cites Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.940817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4641ff93-3d4a-4de0-93a3-5f11e07fd094 · outbound

This paper cites Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.945682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efd42055-a32a-4f2f-bd0c-fc49fa47825e · outbound

This paper cites Data Quality as Predictor of Voice Anti-Spoofing Generalization.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Data Quality as Predictor of Voice Anti-Spoofing Generalization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.950632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01871008-22a4-4c37-b38d-c67d23532c3b · outbound

This paper cites Maxi- mum error modeling for fault-tolerant computation using maxi- mum a posteriori (map) hypothesis,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Maxi- mum error modeling for fault-tolerant computation using maxi- mum a posteriori (map) hypothesis,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.955432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 988c297d-c9c4-418e-a1f7-3e0986197dd1 · outbound

This paper cites A survey of emerging threats in cybersecurity,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems A survey of emerging threats in cybersecurity,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.959894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ef7dfd8-8bd3-4c75-8949-1ebbbb846952 · outbound

This paper cites Balance, mul- tiple augmentation, and re-synthesis: A triad training strategy for enhanced audio deepfake detection,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Balance, mul- tiple augmentation, and re-synthesis: A triad training strategy for enhanced audio deepfake detection,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.964456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1043bfd-04f7-422c-9eef-2e3c24205464 · outbound

This paper cites Iso/iec 30107: Information technology — biometric presentation attack detection,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Iso/iec 30107: Information technology — biometric presentation attack detection,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.968691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b291277e-0c24-4117-81d5-8050b2b226fb · outbound

This paper cites Range-Based Equal Error Rate for Spoof Localization.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Range-Based Equal Error Rate for Spoof Localization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.972935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda816b9-700b-407e-a6a0-9f9ff500f17e · outbound

This paper cites ASVspoof 2015: the First Auto- matic Speaker Verification Spoofing and Countermeasures Chal- lenge,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems ASVspoof 2015: the First Auto- matic Speaker Verification Spoofing and Countermeasures Chal- lenge,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.978002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c443a2-7cb1-4ccc-be87-1d938569869a · outbound

This paper cites A practical guide to logical access voice presentation attack detection,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems A practical guide to logical access voice presentation attack detection,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.982447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7a061a-76c6-4990-b59f-d3f42ca5d335 · outbound

This paper cites The ami meeting corpus: A pre-announcement,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems The ami meeting corpus: A pre-announcement,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.986677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e24cd58-4836-4cc1-8017-4d659d11411c · outbound

This paper cites Lib- rispeech: an asr corpus based on public domain audio books,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Lib- rispeech: an asr corpus based on public domain audio books,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.990903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 477c57dc-6757-40ba-854e-3bf984d439bc · outbound

This paper cites Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92),.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92),

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.995187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a5aa87-3247-41c7-9ca1-eedc2355aa1d · outbound

This paper cites FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:19.999474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a4f89a1-ed58-40cc-99d3-9d8587560c1e · outbound

This paper cites Does audio deepfake detection generalize?.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Does audio deepfake detection generalize?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.004103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c9c1b0-dd7d-46e4-b8cd-8f37ad2239e2 · outbound

This paper cites Av-deepfake1m: A large-scale llm-driven audio- visual deepfake dataset,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Av-deepfake1m: A large-scale llm-driven audio- visual deepfake dataset,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.008461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 625d0e0e-ebf1-4939-9422-06beeb87ac0f · outbound

This paper cites LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.013526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c8517f-fdd6-4482-b942-b1df29a0b323 · outbound

This paper cites Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.018441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f21fd9cf-646f-4557-bc3c-7db76dac2d92 · outbound

This paper cites Continual learning with embedding layer surgery and task- wise beam search using whisper,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Continual learning with embedding layer surgery and task- wise beam search using whisper,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.023042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cf85bad-79e1-4ec3-b1e6-7086f1eadd6b · outbound

This paper cites Asr model adaptation for rare words using synthetic data generated by multiple text- to-speech systems,.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Asr model adaptation for rare words using synthetic data generated by multiple text- to-speech systems,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.028504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b657f4-015d-434b-b217-61c7c4443fe8 · outbound

This paper cites Unsupervised Cross-lingual Representation Learning for Speech Recognition.

Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Unsupervised Cross-lingual Representation Learning for Speech Recognition

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T19:37:20.032674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9787d61d-9a3c-45ab-8116-b09ea132943a · inbound