Paper Citation Record · LEDGER

MSCT: Differential Cross-Modal Attention for Deepfake Detection

As of 6 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2604.07741.

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

pith.paper-citation-record.v1
2604.07741 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T18:29:22.711855Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T18:29:22.711855Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T00:30:53.017290Z

Reference resolution

25 of 25 outbound references displayed

verified exact1
verified fuzzy23
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6301efbe-5946-455e-869e-50d463c3344c · outbound

This paper cites an unresolved cited work.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-17T02:31:27.791492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 536436d0-087f-4c3f-8832-9dc1571f79a2 · outbound

This paper cites Chugh et al.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Chugh et al

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.810330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e7530bde-03c6-45a2-aa59-9f40b9c00b51 · outbound

This paper cites MSCT: Differential Cross-Modal Attention for Deepfake Detection.

MSCT: Differential Cross-Modal Attention for Deepfake Detection MSCT: Differential Cross-Modal Attention for Deepfake Detection

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T00:30:53.024395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bab9738a-5374-4fd9-a75e-abe0a469b0c7 · outbound

This paper cites Built on this framework, we focus on detailing our proposed multi-scale self-attention module and differential cross-modal attention module.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Built on this framework, we focus on detailing our proposed multi-scale self-attention module and differential cross-modal attention module

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.800498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 42acbf42-53b2-49e4-8aa4-d1090a00d244 · outbound

This paper cites Datasets We evaluated our method on the public dataset FakeA VCeleb [15].

MSCT: Differential Cross-Modal Attention for Deepfake Detection Datasets We evaluated our method on the public dataset FakeA VCeleb [15]

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.779603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e75680c4-02f5-4cbe-a4f9-f33fafcf8c6b · outbound

This paper cites In addition, each module was analyzed in detail through ablation experiments.

MSCT: Differential Cross-Modal Attention for Deepfake Detection In addition, each module was analyzed in detail through ablation experiments

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.797424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2c30336d-2012-48bc-998b-a1206d7979ce · outbound

This paper cites Specifically, cross-modal differential attention enhances the model’s compatibility with multi-modal deepfake detection tasks by leveraging atten- tion matrix differences.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Specifically, cross-modal differential attention enhances the model’s compatibility with multi-modal deepfake detection tasks by leveraging atten- tion matrix differences

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.785976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aabb139c-2468-491e-b705-d45de3352052 · outbound

This paper cites Auto-encoding variational bayes.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Auto-encoding variational bayes

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.782575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1de6df84-b19b-4a95-a9b6-5de1ff36d9f7 · outbound

This paper cites Generative adversar- ial networks.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Generative adversar- ial networks

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.812486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5cf1ceed-c71e-4d76-8300-c77de76ad17b · outbound

This paper cites Denois- ing diffusion probabilistic models.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Denois- ing diffusion probabilistic models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.769183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f02119b-6b33-4f79-9116-7ad8b7f623a0 · outbound

This paper cites Contin- ual unsupervised domain adaptation for audio deepfake detection.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Contin- ual unsupervised domain adaptation for audio deepfake detection

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.794554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fbab5bbf-7053-4f5b-8c05-32f5adbe884e · outbound

This paper cites Tall: Thumbnail layout for deepfake video detection.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Tall: Thumbnail layout for deepfake video detection

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.777230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5ba35488-438c-4e96-84e4-57ce3540654a · outbound

This paper cites Cross-modality and within-modality regularization for audio-visual deepfake detection.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Cross-modality and within-modality regularization for audio-visual deepfake detection

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.766415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ebad879-2b83-4fe1-a529-57683c644483 · outbound

This paper cites Emotions don’t lie: An audio-visual deepfake detection method using affec- tive cues.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Emotions don’t lie: An audio-visual deepfake detection method using affec- tive cues

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.808112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 991b2096-d18c-4ce7-b200-7e59e02b6ee9 · outbound

This paper cites Not made for each other- audio-visual dissonance-based deepfake detection and localization.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Not made for each other- audio-visual dissonance-based deepfake detection and localization

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.761800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 01e07ba6-c073-4752-a355-6694ec56d03a · outbound

This paper cites Audio-visual temporal forgery detection us- ing embedding-level fusion and multi-dimensional con- trastive loss.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Audio-visual temporal forgery detection us- ing embedding-level fusion and multi-dimensional con- trastive loss

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.815330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a7815d4f-f724-4907-894c-f8c2e6a72b37 · outbound

This paper cites Is someone speak- ing?: Exploring long-term temporal features for audio- visual active speaker detection.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Is someone speak- ing?: Exploring long-term temporal features for audio- visual active speaker detection

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.802983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 854eb134-783b-4a15-9cc8-a68364911d4a · outbound

This paper cites Differential transformer.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Differential transformer

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.763876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5b085bd1-5760-4d7b-88e7-d0c35832e89b · outbound

This paper cites V oice-face homogeneity tells deepfake.

MSCT: Differential Cross-Modal Attention for Deepfake Detection V oice-face homogeneity tells deepfake

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.788811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b503a24a-b51e-4ed4-af11-46eed332e0b5 · outbound

This paper cites Avoid-df: Audio-visual joint learning for detecting deepfake.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Avoid-df: Audio-visual joint learning for detecting deepfake

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.805485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8577dbaa-a277-470b-8e28-a2e729880e05 · outbound

This paper cites Busterx: Mllm-powered ai-generated video forgery detection and explanation.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Busterx: Mllm-powered ai-generated video forgery detection and explanation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.759362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 47c0109a-815b-42c2-83ae-dae2c8540d6c · outbound

This paper cites FakeA VCeleb: A novel audio-video mul- timodal deepfake dataset.

MSCT: Differential Cross-Modal Attention for Deepfake Detection FakeA VCeleb: A novel audio-video mul- timodal deepfake dataset

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.757024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34322b64-f1dc-4144-ae8b-7d476e1d7d91 · outbound

This paper cites Res2net: A new multi-scale backbone architecture.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Res2net: A new multi-scale backbone architecture

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.771940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3645e9d6-7bd2-4eec-9014-51a8481e2c7d · outbound

This paper cites Wavelet convolutions for large receptive fields.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Wavelet convolutions for large receptive fields

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.818107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0fa68169-e2bd-417a-91fc-7f6eb12f57b3 · outbound

This paper cites Cbam: Convolutional block attention module.

MSCT: Differential Cross-Modal Attention for Deepfake Detection Cbam: Convolutional block attention module

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T02:31:27.774502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation e7530bde-03c6-45a2-aa59-9f40b9c00b51 · inbound