{"as_of":"2026-08-10T17:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a5e2007dd8513b36803c470fc088d1689c8ddf8c1a1cfc57eb20f41e0ed30595","coverage":[{"denominator":70,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":70,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T14:12:32.909169Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.07993/citation-record","integrity":"/paper/2509.07993/integrity","json":"/paper/2509.07993/citation-record.json","paper":"/paper/2509.07993"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.00500","last_updated":"2024-05-21T10:05:12Z","snapshot_observed_at":"2026-08-01T12:22:23.279517Z","submitted_at":"2023-04-02T10:25:09Z","title":"Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.00500","snapshot_observed_at":"2026-08-05T14:12:26.181975Z","title":"Parents and children: Distinguishing multimodal deepfakes from natural images","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.181975Z"},"links":{"cited_paper":"/paper/2304.00500","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:99b36759d34c4ab2e01be618fbee6ad0fc058af1f7db9486b6ab65b0fcf4ad88","observation_id":"e6184316-4339-41c9-8a93-f82ea25eca36","resolution":{"observed_at":"2026-08-05T14:12:26.181975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12604","last_updated":"2022-05-10T09:32:26Z","snapshot_observed_at":"2026-08-08T23:51:11.208323Z","submitted_at":"2022-01-29T15:15:23Z","title":"Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12604","snapshot_observed_at":"2026-08-05T14:12:26.240457Z","title":"Learn- ing fast, learning slow: A general continual learning method based on complementary learning system","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.240457Z"},"links":{"cited_paper":"/paper/2201.12604","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:21a479b8052cfdb6effbea7f706e0d3ed1557186db9889bd223ee7683c6204f0","observation_id":"f71e46f9-808e-4edd-898d-df836e8ef0a6","resolution":{"observed_at":"2026-08-05T14:12:26.240457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:43.808216Z","title":"Cifake: Image classifica- tion and explainable identification of ai-generated synthetic images","venue":null,"work_id":"4c9537e5-6a0c-404c-a2fa-96d870108c92","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.418649Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:3d3028910b2c34b5e1611d0d3ac8df5ef5b9317c3a1e9249b39460fe2cdc9b3b","observation_id":"87b1fd33-5db2-489c-9a5c-cf6bdf729bb6","resolution":{"observed_at":"2026-08-05T14:12:43.864604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:43.627879Z","title":"Dark experience for general continual learning: a strong, simple baseline","venue":null,"work_id":"9b4c428e-5b5c-4b9f-96f3-19a055842241","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.463343Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:fc3c2f19e96c2a2722ba74356fec6b5ba0fe4d210dd1094ad9c5883d2ce39bc8","observation_id":"80513353-b0b7-4356-87ea-61fe55b29098","resolution":{"observed_at":"2026-08-05T14:12:43.712624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:43.451305Z","title":"Harnessing the power of text-image contrastive models for automatic detection of on- line misinformation","venue":null,"work_id":"45cf5da4-7aed-480c-a2d0-b88a093f9ea6","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.536727Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:8532e3526793149be0e0a774f90504149ab85cba17d89d8dbf865d39eded669b","observation_id":"67f49e8d-f9c1-4049-bd00-ae9d0a8a2aa9","resolution":{"observed_at":"2026-08-05T14:12:43.535004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00541","last_updated":"2024-02-01T12:06:55Z","snapshot_observed_at":"2026-08-08T00:20:05.636939Z","submitted_at":"2024-02-01T12:06:55Z","title":"Masked Conditional Diffusion Model for Enhancing Deepfake Detection","version":1},"cited_work":{"arxiv_id":"2402.00541","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.00541","snapshot_observed_at":"2026-08-05T14:12:33.830196Z","title":"Masked Conditional Diffusion Model for Enhancing Deepfake Detection","venue":"cs.CV","work_id":"0a9c6f64-a007-4f5e-8207-5d94ace14903","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.600974Z"},"links":{"cited_paper":"/paper/2402.00541","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:4bf32ffe15f5f4300d9b8ed05383337d7434cc8f98ef3cbb583d0567b3e7db1c","observation_id":"8fd24f3f-8db1-41c0-a826-813ea4ba2aab","resolution":{"observed_at":"2026-08-05T14:12:33.898243Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:43.297617Z","title":"Fakecatcher: Detection of synthetic portrait videos using biological sig- nals","venue":null,"work_id":"51390d32-b9de-48d5-b060-52f09a67f31c","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.686906Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:369dc07003a4d70d0b365127688362a30799e8f4f076cf0aeabde14611675169","observation_id":"7bd0f2d1-8e8d-4d89-b428-0f4d25d1a44c","resolution":{"observed_at":"2026-08-05T14:12:43.367743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:43.090454Z","title":"Forensictrans- fer: Weakly-supervised domain adaptation for forgery detec- tion","venue":null,"work_id":"caf764e1-7f7f-44a5-bf65-5f7abdee8861","year":2018},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.769988Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:4db0bea0a6077a88893c78dd513d615767ea8ef89d4d76d1278a07ec985d7e18","observation_id":"39015386-96f0-48cd-827f-e2f7fbd9f3d9","resolution":{"observed_at":"2026-08-05T14:12:43.189616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:42.873136Z","title":"On the detection of digital face manipulation","venue":null,"work_id":"78b242a5-d14b-4271-ac89-3005eb783178","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.832060Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:129ec45f4c881e3418068ca4f379159c45608a7629c97437cf75b8920ee21564","observation_id":"4585362d-7c27-4eb0-b087-ad2dbe980d62","resolution":{"observed_at":"2026-08-05T14:12:42.978223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-05T14:12:26.918927Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.918927Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:9a14d9e63b7b92ef5093b2c6b9ca1e2d0e365659fcbdafb7286be866814f67f1","observation_id":"1e9feb2c-205d-4adc-a9dd-ebdef4c11773","resolution":{"observed_at":"2026-08-05T14:12:26.918927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:42.675407Z","title":"Attacking identity semantics in deepfakes via deep feature fusion","venue":null,"work_id":"ffa2ac47-483c-49ea-8bdb-0373f6fce413","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:26.995404Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:de8d67d15b7731291e046484643bf0f5aa5960a3b6ce78177d5003a6d24bb104","observation_id":"db69f514-3b28-44ff-a547-9fe6d91a77f9","resolution":{"observed_at":"2026-08-05T14:12:42.760494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:42.513964Z","title":"Synthesizing black-box anti-forensics deepfakes with high visual quality","venue":null,"work_id":"31c29934-c62a-48ad-ae65-72a5b3436986","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.084931Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:aea6e2dde25b7c211e6bf965c01e843032062446818bac10ffdae58675d79ab3","observation_id":"eeead055-d11c-4e70-a153-cec6cfe84f0d","resolution":{"observed_at":"2026-08-05T14:12:42.581215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.10466","last_updated":"2020-07-20T20:49:34Z","snapshot_observed_at":"2026-08-06T01:11:56.195608Z","submitted_at":"2020-07-20T20:49:34Z","title":"Detection, Attribution and Localization of GAN Generated Images","version":1},"cited_work":{"arxiv_id":"2007.10466","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.10466","snapshot_observed_at":"2026-08-05T14:12:33.708012Z","title":"Detection, Attribution and Localization of GAN Generated Images","venue":"eess.IV","work_id":"430a71d8-73c1-44c0-8f6c-a9c7c3528ce6","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.145108Z"},"links":{"cited_paper":"/paper/2007.10466","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:b8103860e2da8776c9adbc845ef3f06c42ef3711329abc7136309c87009f1cd0","observation_id":"7d12a264-f40b-43f1-a320-e0a09fa6169f","resolution":{"observed_at":"2026-08-05T14:12:33.764134Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6211","last_updated":"2015-03-04T01:43:31Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T06:31:41Z","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6211","snapshot_observed_at":"2026-08-05T14:12:27.230529Z","title":"An empirical investigation of catas- trophic forgetting in gradient-based neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.230529Z"},"links":{"cited_paper":"/paper/1312.6211","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:bee86c6c9cc40b05092a854c1a30f7c2650519a542cbb52dde1abcbe84df237f","observation_id":"56c3fa0d-91d9-4bc5-824d-670a3057b6fa","resolution":{"observed_at":"2026-08-05T14:12:27.230529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:42.342688Z","title":"Studies of mind and brain: Neural principles of learning, perception, development, cognition, and motor control","venue":null,"work_id":"cf00d3f9-bd6e-4cd5-8eac-3557a19cc047","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.318131Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:a88c5b9acd30d85a8cd33f337e2e32b06f714a756fe2268867b70506285a6688","observation_id":"91809140-fb64-40a5-897a-f22e1521d602","resolution":{"observed_at":"2026-08-05T14:12:42.413392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:42.157494Z","title":"Deepfake detection by analyzing convolutional traces","venue":null,"work_id":"d6a8dd05-6bc5-4341-92de-463e4cc98467","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.403415Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:ed4d608db7293a2cc7eca6d1f8476fd5021891b24cc94033167deb27965af9e0","observation_id":"927bbfc9-ff3d-4ea9-9488-8e630ffc7fbb","resolution":{"observed_at":"2026-08-05T14:12:42.260575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:41.986129Z","title":"Robust attentive deep neural network for detecting gan- generated faces","venue":null,"work_id":"371b552b-7a28-44e7-8ec7-9817b9e692c4","year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.466190Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:1305f006991495bf7a8ad8b1c33e5b1cbbbec0ee1d38eab1da1b27189544c3c6","observation_id":"d1a557ab-3a3c-4bac-8bb1-5e4e29f3f29d","resolution":{"observed_at":"2026-08-05T14:12:42.059050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:41.834812Z","title":"Deep fake image detection based on pairwise learning","venue":null,"work_id":"cf707097-8501-424f-ac85-89b4e22b0a25","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.554071Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:b04813779f773e24ce90b7771d9444de862ecaf666524d2a1bdfea48f541e263","observation_id":"ceef609b-acdd-4600-809a-7309f7545fa8","resolution":{"observed_at":"2026-08-05T14:12:41.907466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:41.632482Z","title":"Improving the generalization ability of deepfake detection via disentangled representation learning","venue":null,"work_id":"c58648af-1c81-4278-b631-866d3b8547a4","year":2021},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.639071Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:dc7315bd306e4feadec219c22d8bd8c9ef692a3602fbef2cfe21330b658638b8","observation_id":"ec8a31ec-f622-431e-9fa3-2e0ca0de8fdb","resolution":{"observed_at":"2026-08-05T14:12:41.760315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:41.479564Z","title":"De- tecting cnn-generated facial images in real-world scenarios","venue":null,"work_id":"d6d657ef-007b-4fca-b9dc-27bc645d3115","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.727053Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:d0c14c66e44ee75f601a09938181f953163634cd11a1bbceb3fe750673cc788c","observation_id":"6ce297d2-505e-40a7-ba88-c34edfb12e53","resolution":{"observed_at":"2026-08-05T14:12:41.553114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:41.274209Z","title":null,"venue":null,"work_id":"0fc3fdec-43a3-4ff7-b47c-910e496a89eb","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.818503Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:eba398de9dd6526de996c5a2fd6c107197ab59bcf59162f0bce51b5d572c56a0","observation_id":"82d3f15e-daea-4873-9447-8f4dc64a086d","resolution":{"observed_at":"2026-08-05T14:12:41.378278Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:41.114964Z","title":null,"venue":null,"work_id":"c7088690-bd4e-4dd7-a093-cc1a2ab363e3","year":2021},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:27.932503Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:328b1bcee4b5b9ae9c23455f09f88c9c7c4e7e82d1f5f2b505a73c878c98c06f","observation_id":"f7b833cc-dfa5-400f-9254-ec395e76e02e","resolution":{"observed_at":"2026-08-05T14:12:41.190619Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:40.970155Z","title":"Overcoming catastrophic forgetting in neu- ral networks","venue":null,"work_id":"6759be73-7c79-481f-a715-136c1a10b6ae","year":2017},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.024021Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:b0395b45f4d53ebb5abed1adb8166db95ae65c3012676dc06dfd3c5442ae5e8f","observation_id":"b6db3884-a9f4-4e24-8d5b-32caf1b85a25","resolution":{"observed_at":"2026-08-05T14:12:41.040213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.08685","last_updated":"2018-12-20T16:36:39Z","snapshot_observed_at":"2026-08-09T14:52:48.078687Z","submitted_at":"2018-12-20T16:36:39Z","title":"DeepFakes: a New Threat to Face Recognition? Assessment and Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.08685","snapshot_observed_at":"2026-08-05T14:12:28.116221Z","title":"Deepfakes: a new threat to face recognition? assessment and detection","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.116221Z"},"links":{"cited_paper":"/paper/1812.08685","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:d950a4e94cfddacb83a5ceb49b3881a8c3c30b61773307e1413f768c23186ba6","observation_id":"9b02be46-baf0-4eed-bc40-5101f876ecf1","resolution":{"observed_at":"2026-08-05T14:12:28.116221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:40.804853Z","title":"Towards generalized deepfake detection with continual learning on limited new data","venue":null,"work_id":"a55aeb61-8857-4ca4-8f55-3c72d8480000","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.191517Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:114e6e514d6541a2a7d9c71dd60d2889d6d2809d2e58c3ab63e64be40a544596","observation_id":"eff4da5c-64b2-4d10-aa0b-d91642d884d9","resolution":{"observed_at":"2026-08-05T14:12:40.877988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:40.604830Z","title":"Faster than lies: Real-time deepfake detection using binary neural networks","venue":null,"work_id":"ad2ea85d-e127-4a52-aaa3-a07e2174232f","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.256722Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:c8766c0648cd96a40632fc0330c96efa02ccd3e1220138454cea5fbe652fb9ca","observation_id":"9476d7ba-dcf3-4c4d-aa97-b76eb83abaad","resolution":{"observed_at":"2026-08-05T14:12:40.674572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.04177","last_updated":"2024-08-03T06:05:56Z","snapshot_observed_at":"2026-07-06T16:03:50.994118Z","submitted_at":"2023-08-08T10:30:34Z","title":"How Generalizable are Deepfake Image Detectors? An Empirical Study","version":2},"cited_work":{"arxiv_id":"2308.04177","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.04177","snapshot_observed_at":"2026-08-05T14:12:33.521699Z","title":"How Generalizable are Deepfake Image Detectors? An Empirical Study","venue":"cs.CV","work_id":"8449fca8-716a-49fb-a190-91dc1b1f3f06","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.320559Z"},"links":{"cited_paper":"/paper/2308.04177","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:733d5d5e0e00f83cdef63fee46ec52cf0fe66d68a439e7b51d85fa7b3f667ee2","observation_id":"93cd8171-a897-4e4e-aefe-0d8b71528c53","resolution":{"observed_at":"2026-08-05T14:12:33.593189Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:40.374808Z","title":"A continual deepfake detection benchmark: Dataset, meth- ods, and essentials","venue":null,"work_id":"779efb38-1082-4e1f-b634-f05a56d6186f","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.381806Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:8c4e7c81261034844de3c6006a295cc5d9c3e1525c16cba5f902bddecd7ab347","observation_id":"93cf09d5-901f-4fef-935f-fb13d26caafe","resolution":{"observed_at":"2026-08-05T14:12:40.499030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:40.145124Z","title":"In ictu oculi: Exposing ai created fake videos by detecting eye blinking","venue":null,"work_id":"c807c417-1d5b-423c-99dd-8b2d5bf37be7","year":2018},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.416893Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:17251e9925958897faa576c900fbb4796576f7859baeda35685403b73b81b3e4","observation_id":"18baa06a-612f-4f43-9995-7641f5c381b5","resolution":{"observed_at":"2026-08-05T14:12:40.260050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:39.929422Z","title":"Celeb-df: A large-scale challenging dataset for deep- fake forensics","venue":null,"work_id":"954d7aae-6311-46ce-ac81-1bc0dcdd3eb6","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.477083Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:e7f2e0e06b4af761e752026f0d7671c604ee8b0fad3672c5a55e77d82748b3d2","observation_id":"d5ffdd39-82d0-4efa-9dbf-0d5d2c28392f","resolution":{"observed_at":"2026-08-05T14:12:40.030430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:39.711130Z","title":"Exploring disentangled content information for face forgery detection","venue":null,"work_id":"bdf1e2d3-2a0a-4e65-b616-41e4cf7a51ec","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.557532Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:8258412818c99ce74548e7bd277027aed1e25c182308241c1e24b1c8fafd724f","observation_id":"f965fe47-db1c-409d-aa2a-457b6f90749b","resolution":{"observed_at":"2026-08-05T14:12:39.822606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00045","last_updated":"2025-07-26T02:37:03Z","snapshot_observed_at":"2026-08-09T21:04:47.829242Z","submitted_at":"2024-01-22T15:08:19Z","title":"Detecting Multimedia Generated by Large AI Models: A Survey","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00045","snapshot_observed_at":"2026-08-05T14:12:28.646194Z","title":"Detecting multimedia generated by large ai models: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.646194Z"},"links":{"cited_paper":"/paper/2402.00045","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:efc4ae816ff5ee2c5ca82c9d2c18d0567695db8c8663d47dac7cd1693f4e96dd","observation_id":"750526d9-08f9-48d9-a637-00b5bf7a07f6","resolution":{"observed_at":"2026-08-05T14:12:28.646194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:39.499525Z","title":"Preserving fairness generalization in deepfake detec- tion","venue":null,"work_id":"4cc911ea-4aaf-4d6f-99e6-6e5e66577f9b","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.732240Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:b484cc1e4052be2bde2625420e9f73eb2ff66895afc3c97b87343c6c00508f9c","observation_id":"8370bc55-a7c8-4d3b-9062-83947a51afa3","resolution":{"observed_at":"2026-08-05T14:12:39.598781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:39.329131Z","title":"Global tex- ture enhancement for fake face detection in the wild","venue":null,"work_id":"40fc3de6-80a8-4fd6-ad6b-b6f335b2b8ef","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.816575Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:8037518efcd271592e7b1ac7c62a526c340521b449314473e086bc8c36e53101","observation_id":"04edbe94-2e7c-4a68-9e91-0b9f1c0f5e6d","resolution":{"observed_at":"2026-08-05T14:12:39.414654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:39.133271Z","title":"Gradient episodic memory for continual learning","venue":null,"work_id":"143c8ae1-76b9-47da-9f60-5c0ae216b24a","year":2017},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.877058Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:e196b703c4949bbc357d6b51c4f4e4971331504ea5102b905b67c51a0ea592f5","observation_id":"d61917a2-fab9-4ce0-9e68-4bf5365e2d01","resolution":{"observed_at":"2026-08-05T14:12:39.244407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:38.922108Z","title":"Detecting images generated by deep diffusion models using their lo- cal intrinsic dimensionality","venue":null,"work_id":"7426a3e2-e5e4-4b3e-82ef-b8de69c01ac0","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:28.931810Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:52704136a93303089b83f5ebfc307cd79ec7403063db06f0b23abb4c2d455f7a","observation_id":"0f62b40c-fbfe-4e5f-b239-87b668d1f2e9","resolution":{"observed_at":"2026-08-05T14:12:39.014779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:38.712779Z","title":"Incremental learning for the detection and clas- sification of gan-generated images","venue":null,"work_id":"bf8c5234-cd58-4c46-91fa-486b9e639a38","year":2019},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.034904Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:470db8e2d6a1d20bdd756836386511e18c6b46aec6beb7239bb74e768f91598c","observation_id":"85968d59-d128-4791-a74d-987a6eb5a38d","resolution":{"observed_at":"2026-08-05T14:12:38.778894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:38.476135Z","title":"Deepfakes genera- tion and detection: State-of-the-art, open challenges, coun- termeasures, and way forward","venue":null,"work_id":"bf5159e7-6b57-4036-96d7-5d3d8a7a0cf2","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.096734Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:32ed12a78b969111e9bf4c6a5c3b200148b4751337b493e7f320d7088dabe875","observation_id":"301bd7c3-c57e-4ebc-ba5d-1593232bbf9e","resolution":{"observed_at":"2026-08-05T14:12:38.604646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.10246","last_updated":"2022-07-21T01:00:40Z","snapshot_observed_at":"2026-07-06T13:33:39.335167Z","submitted_at":"2022-07-21T01:00:40Z","title":"GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.10246","snapshot_observed_at":"2026-08-05T14:12:29.226417Z","title":"Gbdf: gender balanced deepfake dataset towards fair deepfake detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.226417Z"},"links":{"cited_paper":"/paper/2207.10246","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:121e5cc4395586eb672ded6f20627c23108d45e8bc8deea9f197a0993f797df0","observation_id":"66a9ed58-e97a-472e-8dac-1ed239a75cb4","resolution":{"observed_at":"2026-08-05T14:12:29.226417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:38.098404Z","title":"Multi-task learning for detecting and segment- ing manipulated facial images and videos","venue":null,"work_id":"d771f0f0-1856-4079-91e0-4b95ad3b3c2c","year":2019},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.324504Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:de5af173f1a620a56e050abe58e56e2eeecb3e10088866fc482ee9e5c85f3172","observation_id":"132e6df7-9975-49a9-b14b-d709a4cc33e0","resolution":{"observed_at":"2026-08-05T14:12:38.305770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10741","last_updated":"2022-03-08T18:18:49Z","snapshot_observed_at":"2026-08-07T12:21:17.790675Z","submitted_at":"2021-12-20T18:42:55Z","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10741","snapshot_observed_at":"2026-08-05T14:12:29.417039Z","title":"Glide: Towards photorealistic image genera- tion and editing with text-guided diffusion models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.417039Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:7bc4cb718717cb7a44b55e184539cca27a882ae27d67199b1b52ed073dfa2591","observation_id":"fde01c05-c11d-446d-840a-033443824deb","resolution":{"observed_at":"2026-08-05T14:12:29.417039Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:37.792099Z","title":"Dfil: Deepfake incremental learning by exploiting domain-invariant forgery clues","venue":null,"work_id":"1e1d0baa-788d-43bb-9274-4fde181af2e2","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.509985Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:ab9d8135fdc5686770ab2dc081f60e0c43fdde7b7348e4336285032d509e7a69","observation_id":"1c9e0e42-e22f-4156-bfce-bea5056c5c81","resolution":{"observed_at":"2026-08-05T14:12:37.937304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:37.480414Z","title":"Learning a deep dual-level network for robust deepfake detection","venue":null,"work_id":"351c4276-6110-4d7d-8055-e135baf30da2","year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.603827Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:c1dc7f17880f762e34e12ca77f3f4c2921023893fdd8e35175f9229bce825770","observation_id":"127cd40e-5128-4963-a58d-ede83acb2c55","resolution":{"observed_at":"2026-08-05T14:12:37.655348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:37.228072Z","title":"Mobilenetv4: universal models for the mobile ecosystem","venue":null,"work_id":"0ef67c69-1b46-46df-9214-8f0317cbcdea","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.724525Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:ff95eb162a86901413897c712a19d0c25a226470ad489c2b6fcca9bb6c9a648e","observation_id":"1d9f813e-c364-4e7e-a537-081ad00f257b","resolution":{"observed_at":"2026-08-05T14:12:37.350343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-05T14:12:29.826405Z","title":"Hierarchical text-conditional image gener- ation with clip latents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.826405Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:bb6f01b3f01cc452afee947871a3cda2b2aac0ebfc32f6dc919f02e49cb5c102","observation_id":"09e5c09a-f111-4bb7-9a8c-0dd28f626f73","resolution":{"observed_at":"2026-08-05T14:12:29.826405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10972","last_updated":"2021-08-05T15:04:28Z","snapshot_observed_at":"2026-08-06T21:17:51.553405Z","submitted_at":"2021-04-22T10:10:14Z","title":"ImageNet-21K Pretraining for the Masses","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10972","snapshot_observed_at":"2026-08-05T14:12:29.948773Z","title":"Imagenet-21k pretraining for the masses","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:29.948773Z"},"links":{"cited_paper":"/paper/2104.10972","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:ef2e2cee3d967357e46b716a53b05a1ece7f7b547ece0edf1ed74ca046b36e35","observation_id":"40f2d71d-1d61-46c5-8a1f-6909817928e5","resolution":{"observed_at":"2026-08-05T14:12:29.948773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:37.213899Z","title":"Experience replay for continual learning","venue":null,"work_id":"50d07674-f5a5-42e0-9239-2d31e5fc6225","year":2019},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.055959Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:5f37fe18276116a1ee64ef73979b421ee1063a775f27fc5b26ba30e2e7bbfe9f","observation_id":"ee41bcc1-259b-433a-b2cf-69e99303d36f","resolution":{"observed_at":"2026-08-05T14:12:37.217150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:37.006487Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"29b77b99-7ce4-42eb-a924-88a99515963f","year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.166115Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:9a8ca3798e6256fe411e2fca6b4509c952ca6edb1c88dcfa155a9a47171173d6","observation_id":"6eeb57f4-15ed-4ef1-bebb-69d276f3e468","resolution":{"observed_at":"2026-08-05T14:12:37.071014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:36.795924Z","title":"Faceforen- sics++: Learning to detect manipulated facial images","venue":null,"work_id":"adf71d6e-32f3-43ad-9a98-761256835c93","year":2019},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.227737Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:6a171a6277386f80befe67d2c8d6fc2bd7abc1939da50fc56ae19af6965c7771","observation_id":"114039ec-82cf-4a5f-8204-cb7d2f2833da","resolution":{"observed_at":"2026-08-05T14:12:36.896590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:36.633599Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":"3187be30-8d14-44f2-95e1-a7e485214bc9","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.430587Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:cd724b000429400d6a0ddd1bdee8ad45f10ccae7a0f91f4b4978905bd9151a12","observation_id":"2788461b-afe7-4f9f-82ef-92c074de5421","resolution":{"observed_at":"2026-08-05T14:12:36.722304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:36.461029Z","title":"Error sensitivity modulation based experience replay: Mitigating abrupt representation drift in continual learning","venue":null,"work_id":"fa012870-0b11-4c52-8fad-37e9bdf3fbf5","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.611992Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:53972b763728f8cc3fbc74d5bf242c36b9a78255aa0f6f4f67e85ddb22a55fb0","observation_id":"40806fdb-3cff-4534-8e8e-aa8f49a7cf28","resolution":{"observed_at":"2026-08-05T14:12:36.542597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:36.310989Z","title":"Con- tinuous fake media detection: Adapting deepfake detectors to new generative techniques.Comput","venue":null,"work_id":"a9de0ba4-04a4-4ccb-8a8f-0144ca4edfd1","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.789173Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:438a25ea6893f6071ad4e76b0830f43eb057228efbb5212827cf5be42c36f6e5","observation_id":"8a18fa8b-8382-474f-9777-dd54caaa9939","resolution":{"observed_at":"2026-08-05T14:12:36.399200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:36.127672Z","title":"An examination of fairness of ai models for deepfake detection","venue":null,"work_id":"43a126de-2e39-4e16-b069-7e8ae6d8145c","year":2021},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.961889Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:8e1716f53f967fbb3fc7c582588e8adda787b92065699152c12c3130802d6f1a","observation_id":"b2f01995-ce8f-4266-a2bc-171e9bf68be2","resolution":{"observed_at":"2026-08-05T14:12:36.224251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:35.980522Z","title":"En- hancing generalization ability in deepfake detection via con- tinual learning","venue":null,"work_id":"4377b844-25f3-4b26-9efa-f46d8470842d","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:30.997427Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:6089e06c979f12229ebf5f8efd5107c163eed6f84cd14c86cb1c3b86c6c7f5a4","observation_id":"4fdce8f3-4a48-4974-a0d5-f1b04e001aa7","resolution":{"observed_at":"2026-08-05T14:12:36.045485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.07734","last_updated":"2019-04-15T12:22:36Z","snapshot_observed_at":"2026-07-06T07:46:29.188511Z","submitted_at":"2019-04-15T12:22:36Z","title":"Three scenarios for continual learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.07734","snapshot_observed_at":"2026-08-05T14:12:31.009858Z","title":"Three scenar- ios for continual learning","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.009858Z"},"links":{"cited_paper":"/paper/1904.07734","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:8b81cb3710d34c1ed1b34c64c6854d92b69de4fd9fb399004f7102ac2f904ab7","observation_id":"a337adb3-2a39-42bc-a370-f08f22dff0bf","resolution":{"observed_at":"2026-08-05T14:12:31.009858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:35.833588Z","title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","venue":null,"work_id":"05cc5793-c528-4610-924d-7ee4e6d1b6fb","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.119882Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:1d62783f529882f031de6195b31f9cab66bdda0a1c3ce5b554d4563232a33af6","observation_id":"f56a4823-4d5e-4d28-ae6d-1ea7758719ba","resolution":{"observed_at":"2026-08-05T14:12:35.898760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:35.689394Z","title":"Cnn-generated images are sur- prisingly easy to spot","venue":null,"work_id":"985975f7-2ef4-493a-abdc-58ec0bb63be8","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.253748Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:cabcf69841000dede69b6454c9ed5590ed596b5f2c555ea0394322db435d640c","observation_id":"898775ad-5d33-4de2-b7ce-3a725da5ec28","resolution":{"observed_at":"2026-08-05T14:12:35.763339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:35.427076Z","title":"Deepfake detectors and datasets exhibit racial and gender bias, usc study shows","venue":null,"work_id":"1a06000d-6696-4c6f-b282-8f65c0945e8d","year":2021},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.354516Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:5faa0d77918f854b67bbded71a2e2c29bed612a16b51fb82b4dff4c4a9818ce8","observation_id":"305ea4b2-6abb-4bc6-9bc5-47c78a85d9d4","resolution":{"observed_at":"2026-08-05T14:12:35.575903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:35.098835Z","title":"Con- vnext v2: Co-designing and scaling convnets with masked autoencoders","venue":null,"work_id":"647d077d-cbec-42cf-ad34-b7873672f087","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.505456Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:598eab61283289403c99e073a7bf57488b57498f8c62cb1842a3af0490df6d8b","observation_id":"babfd60e-8e06-42a9-ba9a-a2eebe1dfd05","resolution":{"observed_at":"2026-08-05T14:12:35.257418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.05845","last_updated":"2024-03-11T11:17:36Z","snapshot_observed_at":"2026-07-06T13:40:58.960056Z","submitted_at":"2022-08-11T14:28:21Z","title":"Analyzing Fairness in Deepfake Detection With Massively Annotated Databases","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.05845","snapshot_observed_at":"2026-08-05T14:12:31.623379Z","title":"A comprehensive analysis of ai biases in deepfake de- tection with massively annotated databases","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.623379Z"},"links":{"cited_paper":"/paper/2208.05845","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:2c777826de4bc81001f0542dd46bb5023f676b6ce5080a4d4234064e012af6dd","observation_id":"46ca9dcc-d945-46e4-9d1c-d074de562001","resolution":{"observed_at":"2026-08-05T14:12:31.623379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:35.075662Z","title":"Yan et al","venue":null,"work_id":"ef953b92-4915-490f-8e83-7cdf85b10746","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.749058Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:d023702020fd69fc4414c0ef15f7dcb1078f39236181dcc1ff07eb3fa4b18356","observation_id":"87bb33af-79b3-4fc7-8040-e914a09d8a50","resolution":{"observed_at":"2026-08-05T14:12:35.083867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:34.885827Z","title":"Ucf: Uncovering common features for generalizable deep- fake detection","venue":null,"work_id":"5a028c6f-575f-498a-b757-d2c155073237","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:31.873986Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:103a527b42ee7e80ee2f87b1b1dd5f1ea0730f6178b14c7fb22d99b9551a8583","observation_id":"8615148c-2404-44fc-ab30-611c30dc34b7","resolution":{"observed_at":"2026-08-05T14:12:34.962084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.17065","last_updated":"2024-11-30T10:48:35Z","snapshot_observed_at":"2026-08-08T19:43:47.155729Z","submitted_at":"2024-08-30T07:49:57Z","title":"Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.17065","snapshot_observed_at":"2026-08-05T14:12:32.011950Z","title":"Generalizing deep- fake video detection with plug-and-play: Video-level blend- ing and spatiotemporal adapter tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.011950Z"},"links":{"cited_paper":"/paper/2408.17065","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:75748a814b9f5e63bbf60a0b5467218c166a572e73bb70a5c911c8b064f65381","observation_id":"ea7c3680-82eb-4d01-b48e-372642163c85","resolution":{"observed_at":"2026-08-05T14:12:32.011950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00359","last_updated":"2024-10-20T15:06:55Z","snapshot_observed_at":"2026-07-06T16:25:54.621792Z","submitted_at":"2023-09-30T12:30:25Z","title":"CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition","version":3},"cited_work":{"arxiv_id":"2310.00359","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.00359","snapshot_observed_at":"2026-08-05T14:12:33.262050Z","title":"CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition","venue":"cs.CV","work_id":"65379e58-b683-4569-9f6c-0c3a7b9b83fd","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.092246Z"},"links":{"cited_paper":"/paper/2310.00359","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:80ec7cd86664967a867f553f5726af194be6bb1da09535eb3ac8ec895671896d","observation_id":"9c862119-69f1-4eef-abdc-db1d2985d5d5","resolution":{"observed_at":"2026-08-05T14:12:33.337559Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:34.697156Z","title":"Exposing deep fakes using inconsistent head poses","venue":null,"work_id":"334eb232-7488-4909-b6ee-aaceb888e288","year":null},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.225393Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:2bfea530c1ff18ffbd7e11c6411b2adb61629e9a1126c5ce60de4a930a001d41","observation_id":"10557148-736a-41b6-aa0a-ac9e6c774970","resolution":{"observed_at":"2026-08-05T14:12:34.765690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:34.514954Z","title":"Towards understanding the generalization of deepfake detectors from a game-theoretical view","venue":null,"work_id":"7439bd4a-f066-4391-aea4-f93ed96a1b83","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.322754Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:9b74cf381458ce603f336c2cb1b23d1d351ad871bcb36ebb0c2f7df54f89bd04","observation_id":"51b69acc-9a1d-46d9-ba42-b848babf0d56","resolution":{"observed_at":"2026-08-05T14:12:34.594145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:34.371191Z","title":"Face anti-spoofing via disentangled represen- tation learning","venue":null,"work_id":"f98b6f36-f0b9-420a-b9d3-e7e4936f2e60","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.470660Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:b8255de7fa0b210b23ea94a5d6c3bc8c0be052a1ab13c0c3987664b405bdf751","observation_id":"68a815cf-a726-4810-a0b6-54b7845a1f83","resolution":{"observed_at":"2026-08-05T14:12:34.449101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04639","last_updated":"2024-01-30T05:18:06Z","snapshot_observed_at":"2026-08-03T23:02:35.651388Z","submitted_at":"2023-10-07T01:23:49Z","title":"X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection","version":2},"cited_work":{"arxiv_id":"2310.04639","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.04639","snapshot_observed_at":"2026-08-05T14:12:33.050473Z","title":"X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection","venue":"cs.CV","work_id":"f1387f5a-5eb0-4533-92d0-7dccc2e1f290","year":2023},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.649109Z"},"links":{"cited_paper":"/paper/2310.04639","citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:c9b76049297d51a1a91048599921ece2669167f39359ed0e64475f017ee83721","observation_id":"9bb6214b-8c08-4965-916c-7d35b9f882a9","resolution":{"observed_at":"2026-08-05T14:12:33.140915Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:34.198195Z","title":"Few-shot learning for misinformation detection based on contrastive models","venue":null,"work_id":"828a3b98-5027-46d4-8a41-8892f17badb4","year":2024},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.800390Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:998444f72299dc056f0b6a2c81c9bb68f051ae94cafe66ab3f3bb9144c7202a7","observation_id":"d8621a67-31d3-48d8-9a93-a8f2cde6482c","resolution":{"observed_at":"2026-08-05T14:12:34.290802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:12:34.017716Z","title":"Wilddeepfake: A challenging real-world dataset for deepfake detection","venue":null,"work_id":"83006ffd-48e8-421b-8c87-5833153602e1","year":2020},"citing_paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T14:12:32.909169Z"},"links":{"citing_paper":"/paper/2509.07993"},"observation_digest":"sha256:2c4e8d48f239f02d2ae474697faad6e19276a20cad62984ac00d9587a83e155b","observation_id":"3e63e9d9-5872-4137-aa3f-e08611ca5edc","resolution":{"observed_at":"2026-08-05T14:12:34.105465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.07993","last_updated":"2025-08-29T13:34:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T16:07:24.855062Z","submitted_at":"2025-08-29T13:34:21Z","title":"Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization"},"reference_resolution":{"displayed":70,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":5,"verified_fuzzy":50},"total_outbound_references":70},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 0 inbound Pith citation observations for arXiv:2509.07993."}