Paper Citation Record · LEDGER

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation

As of 11 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2505.18787.

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

pith.paper-citation-record.v1
2505.18787 v2

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:31:13.022953Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

43 of 43 outbound references displayed

verified exact0
verified fuzzy37
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 13380e54-8115-4503-9584-7e1de0c9b94f · outbound

This paper cites Parameter-free on- line test-time adaptation.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Parameter-free on- line test-time adaptation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:19.275122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6ec7a860-67d9-4624-b223-de1e737ba33d · outbound

This paper cites Ost: Improving general- ization of deepfake detection via one-shot test-time train- ing.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Ost: Improving general- ization of deepfake detection via one-shot test-time train- ing

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:19.023873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 99981fbc-a89c-46c2-977c-82126f076af0 · outbound

This paper cites Xception: Deep learning with depthwise separable convolutions.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Xception: Deep learning with depthwise separable convolutions

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:18.834958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5dbe77bc-4748-4fb5-8814-3422002333b9 · outbound

This paper cites an unresolved cited work.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:31:13.462173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9ccc47be-8165-47fd-be93-d5464a2e8e9f · outbound

This paper cites Contributing data to deepfake de- tection research,.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Contributing data to deepfake de- tection research,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:18.007348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4a067d62-880a-43c8-9199-012ea2c9264d · outbound

This paper cites Joint physical-digital facial attack detection via simulating spoofing clues.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Joint physical-digital facial attack detection via simulating spoofing clues

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:17.786296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7d7858a1-5fb1-4b80-8bbe-abe11cc9e183 · outbound

This paper cites Benchmarking neural network robustness to common corruptions and perturbations.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Benchmarking neural network robustness to common corruptions and perturbations

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:17.547018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 02c90891-2ad9-4f33-946a-5246aa8d8499 · outbound

This paper cites Nlnl: Negative learning for noisy labels.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Nlnl: Negative learning for noisy labels

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:17.318798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 447e0ac9-04d9-472d-98ad-92130945246d · outbound

This paper cites Joint negative and positive learning for noisy labels.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Joint negative and positive learning for noisy labels

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:17.116445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 545072f5-b000-4347-bd83-69992f6c1980 · outbound

This paper cites In ictu oculi: Exposing ai created fake videos by detecting eye blinking.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation In ictu oculi: Exposing ai created fake videos by detecting eye blinking

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:16.533559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dc698853-e8c2-4925-acc7-7aee2b326fbd · outbound

This paper cites A comprehensive survey on source- free domain adaptation.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation A comprehensive survey on source- free domain adaptation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:16.245681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c733655d-98ae-41a2-83de-c08fa341bcad · outbound

This paper cites A comprehensive survey on test-time adaptation under dis- tribution shifts.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation A comprehensive survey on test-time adaptation under dis- tribution shifts

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:16.031118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0868a0b6-bc05-4e77-8be8-b8a7b138eb57 · outbound

This paper cites Spatial-phase shallow learning: rethinking face forgery detection in frequency domain.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Spatial-phase shallow learning: rethinking face forgery detection in frequency domain

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:15.838098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dccb1dbf-fa5a-4b10-a523-4c1632868c9c · outbound

This paper cites Cfpl-fas: Class free prompt learning for general- izable face anti-spoofing.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Cfpl-fas: Class free prompt learning for general- izable face anti-spoofing

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:15.675098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8169d0c8-dc16-4768-a2e7-9857a3d4d37d · outbound

This paper cites Nor- malized loss functions for deep learning with noisy labels.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Nor- malized loss functions for deep learning with noisy labels

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:15.448889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1b534cf2-085d-4582-a1fe-41d291515fda · outbound

This paper cites Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:10.525306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31a0acb6-b50f-4def-92a2-b1fab86fce26 · outbound

This paper cites Core: Consistent representation learning for face forgery detec- tion.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Core: Consistent representation learning for face forgery detec- tion

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:15.225171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 79dbc84e-2f13-4be8-a2cf-f79431151467 · outbound

This paper cites Efficient test-time model adaptation without forgetting.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Efficient test-time model adaptation without forgetting

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:15.107483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b59878fd-450f-490c-acb5-c0304a95bfb3 · outbound

This paper cites Towards stable test-time adaptation in dy- namic wild world.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Towards stable test-time adaptation in dy- namic wild world

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.986587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1daeb6a8-d3f6-463f-b990-36802b2aaa96 · outbound

This paper cites Towards universal fake image detectors that gen- eralize across generative models.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Towards universal fake image detectors that gen- eralize across generative models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.843614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d5796a18-f94d-403c-8a32-0fa2b7983238 · outbound

This paper cites Dfil: Deepfake incremental learning by exploiting domain-invariant forgery clues.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Dfil: Deepfake incremental learning by exploiting domain-invariant forgery clues

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.731342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 338f3530-06f3-4802-816f-9a54f41e754c · outbound

This paper cites Thinking in frequency: Face forgery detection by mining frequency-aware clues.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Thinking in frequency: Face forgery detection by mining frequency-aware clues

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.614726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5570c7c4-8649-4754-b7af-958d24a8aed1 · outbound

This paper cites Focal loss for dense object detection.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Focal loss for dense object detection

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.525336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4aab185f-4601-4668-8a5b-2d2e49a266a1 · outbound

This paper cites Faceforensics++: Learning to de- tect manipulated facial images.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Faceforensics++: Learning to de- tect manipulated facial images

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.412027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2e72182d-1c12-4336-99f8-22eb50e7f9fb · outbound

This paper cites Improving robustness against common corruptions by covariate shift adaptation.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Improving robustness against common corruptions by covariate shift adaptation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.308486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d5de10dd-82d2-46f9-9926-595c000bbaab · outbound

This paper cites Detecting deepfakes with self-blended images.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Detecting deepfakes with self-blended images

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.200607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0ef941a2-e099-42e2-8f1f-b9aaa83876ca · outbound

This paper cites Efficient- net: Rethinking model scaling for convolutional neural networks.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Efficient- net: Rethinking model scaling for convolutional neural networks

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:14.096228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c2b6d504-1b8e-4c47-b686-6f56dcf43cc2 · outbound

This paper cites Tent: Fully Test-time Adaptation by Entropy Minimization.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Tent: Fully Test-time Adaptation by Entropy Minimization

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:11.969554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca833d8b-4d61-4c94-baef-6c6039ac9c1b · outbound

This paper cites Continual test-time domain adaptation.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Continual test-time domain adaptation

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:13.995750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e0336237-e0c3-4129-8b6f-0b543279a7b7 · outbound

This paper cites DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:12.205648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10519a93-51c5-4081-bdca-13cba28bded5 · outbound

This paper cites Transcending forgery specificity with latent space augmentation for generaliz- able deepfake detection.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Transcending forgery specificity with latent space augmentation for generaliz- able deepfake detection

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:13.899994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7dcb9da9-2ef6-46b6-8dd4-0b2dcccc46ef · outbound

This paper cites Active negative loss functions for learning with noisy labels.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Active negative loss functions for learning with noisy labels

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:13.798059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 94b93870-6e8a-4c83-ac5d-f5e2c3bdcf35 · outbound

This paper cites Memo: Test time robustness via adapta- tion and augmentation.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Memo: Test time robustness via adapta- tion and augmentation

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:13.700736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 73befd2c-332f-4646-a8e0-fe4690730086 · outbound

This paper cites COME: Test-time adaption by Conservatively Minimizing Entropy.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation COME: Test-time adaption by Conservatively Minimizing Entropy

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:12.706051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc41dbb6-12bb-4947-a457-ce6f8f89b752 · outbound

This paper cites Asymmetric loss func- tions for learning with noisy labels.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Asymmetric loss func- tions for learning with noisy labels

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:13.566654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 64884d40-409e-4783-8330-cc0935b09d18 · outbound

This paper cites For color contrast operation, we modify image contrast across 5 intensity levels by manipulating pixel values around their mean while applying channel-wise enhancements.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation For color contrast operation, we modify image contrast across 5 intensity levels by manipulating pixel values around their mean while applying channel-wise enhancements

Reference 128

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:13.311424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 83726b2d-6dd9-4749-ba26-76ac09a29131 · outbound

This paper cites Intrigu- ing properties of synthetic images: from generative adver- sarial networks to diffusion models.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Intrigu- ing properties of synthetic images: from generative adver- sarial networks to diffusion models

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:18.657173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fb43d931-b8f5-48d7-8d2c-3b1f9ceb66c4 · outbound

This paper cites Uni- fied physical-digital face attack detection.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Uni- fied physical-digital face attack detection

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:18.501540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4107526e-afc2-4f64-b903-ee76dffdc1dc · outbound

This paper cites Robust loss functions under label noise for deep neural networks.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Robust loss functions under label noise for deep neural networks

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:18.202123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7c768a85-2c2b-40a3-ab9b-f45220cec057 · outbound

This paper cites {SoK}: The good, the bad, and the unbalanced: Measur- ing structural limitations of deepfake media datasets.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation {SoK}: The good, the bad, and the unbalanced: Measur- ing structural limitations of deepfake media datasets

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:16.856712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e8692f17-c85d-4853-8d52-37b6409b40f3 · outbound

This paper cites End-to-end reconstruction-classification learning for face forgery de- tection.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation End-to-end reconstruction-classification learning for face forgery de- tection

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:19.161237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e21f301b-5df9-4151-9278-5eb1bd6736aa · outbound

This paper cites The Deepfake Detection Challenge (DFDC) Preview Dataset.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation The Deepfake Detection Challenge (DFDC) Preview Dataset

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:08.640061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14a411c-ecb1-4c97-a548-ad7035bd3199 · outbound

This paper cites Leveraging frequency analysis for deepfake im- age recognition.

Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation Leveraging frequency analysis for deepfake im- age recognition

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:18.349608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

No inbound Pith citation observations are available.