Pith. sign in

Paper Citation Record · LEDGER

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection

As of 21 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2607.21776.

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

pith.paper-citation-record.v1
2607.21776 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T06:48:03.541866Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

26 of 26 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved26
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7f0f3ed5-57b4-4bb9-9108-dfdd8a885a77 · outbound

This paper cites Deepfake video detection through optical flow based CNN.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Deepfake video detection through optical flow based CNN

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.455510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.455510Z digest=sha256:9e8f730fcedc5b2ec1e70fdc789bfa48b28138389b7b1a4b48f179720cf0e804

Observation 2f11b0c3-665f-492c-a3e9-e6b505c18d59 · outbound

This paper cites EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.459550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.459550Z digest=sha256:6d57af5bd8745ca3826feaa2313f1e0b14fb2e02c16aba50da37dd247fc739c1

Observation cc8af810-c996-4339-92b1-28d416358865 · outbound

This paper cites Fake- Catcher: Detection of synthetic portrait videos using bio- logical signals.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Fake- Catcher: Detection of synthetic portrait videos using bio- logical signals.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.463218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.463218Z digest=sha256:12fb75abbc18a392d0f7db08bfb755d87d9707bd8f736383cb099d2468cb858b

Observation ecaa123b-73ff-4e0b-a55c-50113bf215b2 · outbound

This paper cites Detecting Lip-Syncing Deepfakes: Vision Temporal Transformer for Analyzing Mouth Inconsistencies.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Detecting Lip-Syncing Deepfakes: Vision Temporal Transformer for Analyzing Mouth Inconsistencies

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.466587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.466587Z digest=sha256:b5ee52836d5f3fce1de1d1eb3cf8ec489fe41ee847beb1be2195250f697a635c

Observation 8621aec8-57e0-4e83-b4dc-6bb03b716440 · outbound

This paper cites Robust pulse rate from chrominance-based rPPG.IEEE Transactions on Biomedical Engineering, 60(10):2878–2886, 2013.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Robust pulse rate from chrominance-based rPPG.IEEE Transactions on Biomedical Engineering, 60(10):2878–2886, 2013

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.470222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.470222Z digest=sha256:bbb7cc2ec39288a4a3302b37b8a168d01b8433d2007a5e8f63c6dc81f329bb33

Observation 1987efdf-ec5f-4b7c-a575-b31f3e87c03e · outbound

This paper cites Lips don’t lie: A generalisable and robust approach to face forge detection.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Lips don’t lie: A generalisable and robust approach to face forge detection

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.473490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.473490Z digest=sha256:8979d3184d9ba8690da1873e8b9aa07fb1aa07c491fd65df3e988a55dfd828f6

Observation c1f1307a-eba6-4414-acb3-4520e61ae6f6 · outbound

This paper cites DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.477158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.477158Z digest=sha256:a40f72aa32986bed71c8d9e0c20727b04e950d7d5cbacdbeeff6fb1176479fcd

Observation e8e4a241-0ef9-4515-8e8b-37b622195797 · outbound

This paper cites FLOAT: Generative motion latent flow matching for audio-driven talking portrait.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection FLOAT: Generative motion latent flow matching for audio-driven talking portrait

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.480494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.480494Z digest=sha256:15b3a532c03a930a75acfed4d800ecc2c46473c6193a9987abf1b14550619637

Observation 8e46388c-bccd-48af-b611-5ffebbf8fe61 · outbound

This paper cites Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.483584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.483584Z digest=sha256:6455c0c980e6aef980e201778f89ff88fbf645c5e9b015f4c629978530ec98fb

Observation fcefb468-d3e6-433c-83e7-b2bf7ba7eecc · outbound

This paper cites Unsupervised identification of Floquet topological phase boundaries.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Unsupervised identification of Floquet topological phase boundaries

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.486789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.486789Z digest=sha256:7da5700f06c0c7fde91ba3aab22039e2fb432aaef1553a4e42a920492a1cc325

Observation ef6e7761-77a9-46f0-97bf-40ad2e8e55b9 · outbound

This paper cites AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.490547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.490547Z digest=sha256:cbe9cd7819ec921ecae6bb2ecf1655e00514b6a1957203c3e9d664e7054e719d

Observation f61ca08a-d20f-4b68-9658-dcff3920d678 · outbound

This paper cites Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.493723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.493723Z digest=sha256:e71af6db4c26c0595cbda07b23227bd83cfcad328f2c5dd5c53c07b9e354c90d

Observation 11846db5-050a-4269-b26b-1e473e8332e0 · outbound

This paper cites A meta-analysis of the impact of skin tone and gender on non-contact photoplethysmography measurements.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection A meta-analysis of the impact of skin tone and gender on non-contact photoplethysmography measurements

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.497009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.497009Z digest=sha256:f6b1b4092b33474f0e27a7a730e2035ac2b36e23eaae3d1f17dc64ef432adf29

Observation e1a33ee0-44ea-448c-9725-751bb661e9ee · outbound

This paper cites SpecAugment: A simple data augmen- tation method for automatic speech recognition.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection SpecAugment: A simple data augmen- tation method for automatic speech recognition

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.499887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.499887Z digest=sha256:fb2175a104db1dccf0150441a549b8356358f63f1c9aae8b0ca23dfbbd9d5270

Observation b038cd2d-aadd-49eb-8d09-37fb9a7dbf49 · outbound

This paper cites DeepRhythm: Exposing deepfakes with attentional visual heartbeat rhythms.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection DeepRhythm: Exposing deepfakes with attentional visual heartbeat rhythms

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.503021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.503021Z digest=sha256:35a2e540c72bef7402d496cce7c17eda45a21166677a34ca4b0bd3fdf4b867f4

Observation 97e2892c-82a7-43df-86e2-2ab4d39a9de9 · outbound

This paper cites EDTalk: Efficient disentanglement for emo- tional talking head synthesis.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection EDTalk: Efficient disentanglement for emo- tional talking head synthesis

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.507014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.507014Z digest=sha256:dab8a8ce09ab7fbd98326f1f0bbf21b978e32fbebf60a390e5ba820e77a76dfb

Observation 6672cdca-35d4-4682-bb7d-2eda49d66d1a · outbound

This paper cites Re- mote plethysmographic imaging using ambient light.Optics Express, 16(26):21434–21445, 2008.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Re- mote plethysmographic imaging using ambient light.Optics Express, 16(26):21434–21445, 2008

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.510225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.510225Z digest=sha256:a53ce5ce93703674250d3a0c479e5be1a0fdd823d504040cb93af527e6083618

Observation d4fbd6dc-8830-417d-a8cf-869304ec067b · outbound

This paper cites Algorithmic principles of remote PPG.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Algorithmic principles of remote PPG

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.514031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.514031Z digest=sha256:4ed7b15fb879d3dece1f7b3a7a0c624e842436d346ba8f513f81122a7fef0142

Observation 188a1a05-fbc9-4978-bb3e-a9d6814c40c1 · outbound

This paper cites Detecting deepfake videos with temporal dropout 3DCNN.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Detecting deepfake videos with temporal dropout 3DCNN

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.520615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.520615Z digest=sha256:569305a9092ead9f0fc72f40da27445d20d978646fbba8cc01a8ee79305e3242

Observation 82352335-e8b5-4a14-823b-2c9363c515a7 · outbound

This paper cites Orthogonal subspace decom- position for generalizable AI-generated image detection.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Orthogonal subspace decom- position for generalizable AI-generated image detection

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.523522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.523522Z digest=sha256:f894be777d6762ec49b161e7a0344290d63e1dda9675379a7a588d9e42c8aade

Observation 63938b20-5d8e-4fca-a1ed-a27e15b699b8 · outbound

This paper cites Real3D-Portrait: One-shot realistic 3D talking portrait synthesis.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Real3D-Portrait: One-shot realistic 3D talking portrait synthesis

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.526915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.526915Z digest=sha256:b6e87082829f5ca21d37e7d08f48f94ea70a177d26aa9139ef252dda66b0116c

Observation 8ce972ed-3bac-464f-9578-161900900de1 · outbound

This paper cites Remote photoplethysmograph signal mea- surement from facial videos using spatio-temporal networks.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Remote photoplethysmograph signal mea- surement from facial videos using spatio-temporal networks

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.529961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.529961Z digest=sha256:e2e153751cb3bb25e4378fed724bde87e06f2ce0d22fe3afe2b466db73722979

Observation 1692d5d2-4cbc-48d5-99bf-740396afd962 · outbound

This paper cites PhysFormer++: Facial video-based phys- iological measurement with slowfast temporal difference transformer.Int.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection PhysFormer++: Facial video-based phys- iological measurement with slowfast temporal difference transformer.Int

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.532774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.532774Z digest=sha256:e6d660ace2ac8e6f5127ab54d688470d9b75b8c3277e36892296565091816985

Observation 3cd0213d-3493-43b8-81eb-ada290f1c49c · outbound

This paper cites SadTalker: Learning realistic 3D mo- tion coefficients for stylized audio-driven single image talk- ing face animation.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection SadTalker: Learning realistic 3D mo- tion coefficients for stylized audio-driven single image talk- ing face animation

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.535724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.535724Z digest=sha256:89bd46de926dac7c9d3123508988940a4933471dc55064c928eeb418268efec1

Observation 89b23c36-0fc4-415e-b39f-acdbae9704cd · outbound

This paper cites Identity-preserving talking face gen- eration with landmark and appearance priors.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection Identity-preserving talking face gen- eration with landmark and appearance priors

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.538737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.538737Z digest=sha256:b9682fd060c370f455d4c99c634f8c44155f5d8e450d96a10764923d600ee917

Observation cf15bd78-a7d3-470d-b6d6-2bd80fbd0613 · outbound

This paper cites RhythmFormer: Extracting patterned rPPG signals based on periodic sparse attention.Pattern Recognition, 164, 2025.

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection RhythmFormer: Extracting patterned rPPG signals based on periodic sparse attention.Pattern Recognition, 164, 2025

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T06:48:03.541866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T06:48:03.541866Z digest=sha256:600111536798f92e1c41bd582d0baf57a6000e949fdbff1ca1dbbf964c0d7b56

Pith citing papers

No inbound Pith citation observations are available.