{"as_of":"2026-08-10T09:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aba14f6912450a8262bf2fcb50680e34213f189e3a19170e950481e76954874e","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:20:51.794431Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"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/2506.02857/citation-record","integrity":"/paper/2506.02857/integrity","json":"/paper/2506.02857/citation-record.json","paper":"/paper/2506.02857"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:20:53.603730Z","title":"Cont inuous fake media detection: Adapting deepfake detectors to new generative techniques","venue":null,"work_id":"4c35e460-b1c7-4c55-b8f8-7d4ee074e3de","year":2024},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.352915Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:4f98d9bb0887c929248928c68bae41ec2ce1257f81ef5e867eeee4bdc4c3cb3b","observation_id":"7ba73cb0-2136-44fe-9d6f-66b3ff0aab44","resolution":{"observed_at":"2026-08-07T11:20:53.610699Z","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":"2026-08-07T11:20:53.571239Z","title":"Deep learning for multimedia forensics","venue":null,"work_id":"520f64c4-a7d8-4eca-9c50-8a91c172d91b","year":2021},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.367378Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:0ba88d40d465ba500a8dbe8baeb405f5bb4ea20c756be082265d7d6f6bb78b47","observation_id":"1d40ed13-1d4d-4ab5-b92b-200bfe9b0068","resolution":{"observed_at":"2026-08-07T11:20:53.579020Z","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":"2405.00196","last_updated":"2024-04-30T20:59:53Z","snapshot_observed_at":"2026-08-09T20:13:59.918716Z","submitted_at":"2024-04-30T20:59:53Z","title":"Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet","version":1},"cited_work":{"arxiv_id":"2405.00196","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.00196","snapshot_observed_at":"2026-08-07T11:20:52.250866Z","title":"Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet","venue":"cs.CV","work_id":"aabc8b13-2646-4f51-84de-38e4b82c2ed8","year":2024},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.373784Z"},"links":{"cited_paper":"/paper/2405.00196","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:3d56fdaf0313730dcd7738fa9725c476c1f0858ec058f837e70e5b1799591dba","observation_id":"a1bccc0e-a87c-4f2c-b3f1-352cad12deb7","resolution":{"observed_at":"2026-08-07T11:20:52.296768Z","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":"1812.08247","last_updated":"2018-12-19T21:12:00Z","snapshot_observed_at":"2026-08-04T02:51:32.123690Z","submitted_at":"2018-12-19T21:12:00Z","title":"Detecting GAN-generated Imagery using Color Cues","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.08247","snapshot_observed_at":"2026-08-07T11:20:51.383240Z","title":"Detecting gan-ge nerated imagery using color cues","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.383240Z"},"links":{"cited_paper":"/paper/1812.08247","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:27401e1843f8222c05c2b10daf630140ad7656ab6c520b5568103e5d2302a1ab","observation_id":"6600f809-69fe-4841-9bfa-826720c214ed","resolution":{"observed_at":"2026-08-07T11:20:51.383240Z","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":"2026-08-07T11:20:53.536194Z","title":"Attributing fake images to gans: Learning and analyzing gan finger- prints","venue":null,"work_id":"1f4c5d12-e659-4809-8825-3f7a3900de0e","year":2019},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.392624Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:cd6fe459976a03442630fbe1e897ea198e846cfb07f6f2864eb34e11ebf40ffe","observation_id":"b99fb0a8-d59e-4c3f-a7f2-4526874b71aa","resolution":{"observed_at":"2026-08-07T11:20:53.547056Z","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":"2026-08-07T11:20:53.476548Z","title":"Do gans leave artificial fingerprints? In 2019 IEEE conference on multimedia information processing and retrieval (MIPR) , pages 506–511","venue":null,"work_id":"500b1467-2592-45ff-acb8-40f26be38629","year":2019},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.406146Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:f97570b8d4e5a37fb3e2335a37d9826f69bd3452d8a05fc455926a6003287349","observation_id":"73014ac1-dd99-4236-b9c9-1e92a1eb0037","resolution":{"observed_at":"2026-08-07T11:20:53.493085Z","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":"2026-08-07T11:20:53.439881Z","title":"Deep learning based one-class detection system for fake faces generated by gan network","venue":null,"work_id":"6c3b70a9-7682-4447-b8ac-d56d3154636d","year":2022},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.418348Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:a577c643a3e22592fefa7f87864a821b4e8a30806a1e136f57a977f6e6fa63da","observation_id":"bbf15f53-3398-413c-a229-43372b3aed1e","resolution":{"observed_at":"2026-08-07T11:20:53.448714Z","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":"1909.06122","last_updated":"2020-07-16T06:44:53Z","snapshot_observed_at":"2026-08-10T09:09:10.998465Z","submitted_at":"2019-09-13T10:08:44Z","title":"FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06122","snapshot_observed_at":"2026-08-07T11:20:51.424982Z","title":"Fakespotter: A simple yet robust baseline for spotting ai-synthesized fake faces","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.424982Z"},"links":{"cited_paper":"/paper/1909.06122","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:ec1ac6bf031aad6fa30bb1f6347bdde597bd74dc8f109b37e21ebcd93352046a","observation_id":"5a6e1542-8ae5-4784-abb0-03f581c5cedb","resolution":{"observed_at":"2026-08-07T11:20:51.424982Z","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":"2026-08-07T11:20:53.408333Z","title":"Multimodal forgery detection using ensemble learning","venue":null,"work_id":"1b3d704b-7972-4c39-9f45-51140d05ee4d","year":2022},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.430934Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:dc7f1a7241b18ff1c42be3f57f64a0192e2c465dfc8729680108210b533285d2","observation_id":"3791eed6-2195-4950-8482-cbaede1206f6","resolution":{"observed_at":"2026-08-07T11:20:53.420721Z","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":"2026-08-07T11:20:53.359855Z","title":"Not made for each other-audio-visual dissonance-based deepfake detection and localization","venue":null,"work_id":"d19f9ae9-fd04-4daa-87a9-0288026cf333","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.437735Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:0454d2404de3be3fb89285dbb59a86334e649b5e5de1697f03dbc5d9e454e20e","observation_id":"5cb61392-1738-4e72-90b2-5f9be5735643","resolution":{"observed_at":"2026-08-07T11:20:53.380773Z","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":"2026-08-07T11:20:53.306028Z","title":"Emotions don’t lie: An audio-visual deepfake detection method using affective cues","venue":null,"work_id":"e519ce79-52fd-4827-80e1-bcfc84c3dffb","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.444415Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:77f8e68319a709910dd66d14a9ad559a656fcca85a27f2d706c05e98e1220e7e","observation_id":"7a80b762-2dc2-451a-837b-3cb86bec70cb","resolution":{"observed_at":"2026-08-07T11:20:53.320573Z","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":"2110.11334","last_updated":"2024-01-23T07:36:33Z","snapshot_observed_at":"2026-08-09T19:23:41.731633Z","submitted_at":"2021-10-21T17:59:41Z","title":"Generalized Out-of-Distribution Detection: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.11334","snapshot_observed_at":"2026-08-07T11:20:51.457090Z","title":"G eneralized out-of-distribution detection: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.457090Z"},"links":{"cited_paper":"/paper/2110.11334","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:737aa6661f9d5de61f9c7eda81ba162b362901e52e1541e74f94dd74b8b571bc","observation_id":"5d96461a-b3d5-486a-b49f-6cfe344fc8ed","resolution":{"observed_at":"2026-08-07T11:20:51.457090Z","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":"2026-08-07T11:20:53.273780Z","title":"Multimodal forgery detection using ensemble learning","venue":null,"work_id":"325bb58e-4234-4f31-a791-af6d223ec13e","year":2022},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.469381Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:736da62ab59f27059f46848ab9ffc3fe4f1fe80841b432d759eb25e98deae940","observation_id":"9a939d4c-0849-4440-9a88-8c1cbe98249a","resolution":{"observed_at":"2026-08-07T11:20:53.282352Z","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":"2026-08-07T11:20:53.160945Z","title":"Fakelocator: Robust localization of gan-based face manipulations","venue":null,"work_id":"b31a75f4-70fd-4d9f-b77f-134defc0ab94","year":2022},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.478719Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:acf9ca86194b7e5d514e568fbfabcbfaf94d6a15189bc06786a1fddfce29cd0d","observation_id":"d865bbfa-f7b3-4619-a7ba-516adb2d71a0","resolution":{"observed_at":"2026-08-07T11:20:53.174773Z","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":"2026-08-07T11:20:53.097038Z","title":"Deepfake detection by analyzing convolutional traces","venue":null,"work_id":"02f55d04-0152-4cd9-b3c1-4b0f2316251e","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.497954Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:8af0cf4871f363ea88b8a140a53b72790f4007ae75b2064ac1ba19c338a6ec66","observation_id":"c5137cc2-9ad7-4bcd-8a62-1c134132c3da","resolution":{"observed_at":"2026-08-07T11:20:53.114749Z","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":"2008.12262","last_updated":"2020-08-27T17:04:46Z","snapshot_observed_at":"2026-08-09T03:02:03.676692Z","submitted_at":"2020-08-27T17:04:46Z","title":"DeepFake Detection Based on the Discrepancy Between the Face and its Context","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.12262","snapshot_observed_at":"2026-08-07T11:20:51.504396Z","title":"Deepfake detection based on the discrepancy between the face and its context","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.504396Z"},"links":{"cited_paper":"/paper/2008.12262","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:819b1934bfc370170c6f606807942c8c8010dbb28f4f02bc1c4161492ef70f9f","observation_id":"8f6f3e83-d12f-4c01-a520-5e311357ca98","resolution":{"observed_at":"2026-08-07T11:20:51.504396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.11126","last_updated":"2021-03-11T13:45:17Z","snapshot_observed_at":"2026-08-07T03:50:56.678417Z","submitted_at":"2021-02-22T15:56:05Z","title":"Deepfake Video Detection Using Convolutional Vision Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.11126","snapshot_observed_at":"2026-08-07T11:20:51.516704Z","title":"Deepfake video dete ction using convolutional vision transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.516704Z"},"links":{"cited_paper":"/paper/2102.11126","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:9f826a88bee4a1119b668458691d8a648c8e27172bcaf2d4260c46da4179f598","observation_id":"d10221b5-d7cb-446c-9c54-a0daa77b0316","resolution":{"observed_at":"2026-08-07T11:20:51.516704Z","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":"2026-08-07T11:20:53.059570Z","title":"A siamese-based verification system for open-set architecture attribution of synthetic images","venue":null,"work_id":"dda5bda9-76b4-4b86-8cd6-8d68acf3936f","year":2024},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.524696Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:a0fadb4e5e158e0b5bf22bba85e9644554dbcd4dab3e455037ecb3a7088c2439","observation_id":"d18161a5-c708-4993-ba2b-d78a5548dc08","resolution":{"observed_at":"2026-08-07T11:20:53.066155Z","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":"2026-08-07T11:20:53.040233Z","title":"Syn- thetic image verification in the era of generative artificial intelligence: What works and what isn’t there yet","venue":null,"work_id":"c25888ac-41a3-4327-83db-739db2301c24","year":2024},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.531676Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:35828e810167df6ca70066c7d7125649475ce77847d3164bd9b9412c2cefa348","observation_id":"66dd0339-fa40-47ad-b04a-9d855b50655a","resolution":{"observed_at":"2026-08-07T11:20:53.045259Z","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":"2026-08-07T11:20:53.020010Z","title":"Reliable out-of-dis tribution recognition of synthetic images","venue":null,"work_id":"1a35dc08-229f-44e1-b3fa-3db3d855219b","year":2024},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.540024Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:46da4b3ab9c56248474b813b7813947239a4af17d4a10d3db99dc9abbde04b0d","observation_id":"eb150f31-0d10-45a4-98ad-60eeabd7ba54","resolution":{"observed_at":"2026-08-07T11:20:53.025065Z","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":"2026-08-07T11:20:52.989978Z","title":"Improving gener alization of deepfake detection with data farming and few-shot learning","venue":null,"work_id":"1e118f3f-f244-416d-9bc9-3c314e0567ff","year":2022},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.544778Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:9d2b73292ffa9cde2909056a180ec50f8d1bc1bf7cacceb6b33a2eb6f21752db","observation_id":"dce63e4c-8267-4e0b-8e11-54533db9e5d4","resolution":{"observed_at":"2026-08-07T11:20:52.994745Z","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":"2006.11863","last_updated":"2020-06-21T18:10:52Z","snapshot_observed_at":"2026-07-06T09:31:08.556302Z","submitted_at":"2020-06-21T18:10:52Z","title":"Generalized Zero and Few-Shot Transfer for Facial Forgery Detection","version":1},"cited_work":{"arxiv_id":"2006.11863","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.11863","snapshot_observed_at":"2026-08-07T11:20:52.018525Z","title":"Generalized Zero and Few-Shot Transfer for Facial Forgery Detection","venue":"cs.CV","work_id":"6309e563-76c0-468d-aa90-55e54e39843a","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.549291Z"},"links":{"cited_paper":"/paper/2006.11863","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:8bbfac9095bbdb2ecda6d4df54c10caf71f414b2ef997383211151308f1e5e24","observation_id":"cc66994b-b05c-45c8-a5d6-881697185f3f","resolution":{"observed_at":"2026-08-07T11:20:52.030928Z","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":"1610.02136","last_updated":"2018-10-03T07:32:57Z","snapshot_observed_at":"2026-08-02T06:41:33.803920Z","submitted_at":"2016-10-07T04:06:01Z","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02136","snapshot_observed_at":"2026-08-07T11:20:51.554138Z","title":"A baseline for detectin g misclassified and out-of-distribution examples in neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.554138Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:281b2074ea24ea6af343bd389b80cd444acb12d2d7e2c975f4d89beda38b0981","observation_id":"7fa80688-248d-4b1c-a577-9c6378a21d12","resolution":{"observed_at":"2026-08-07T11:20:51.554138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02690","last_updated":"2020-08-30T16:50:36Z","snapshot_observed_at":"2026-08-05T05:04:04.733091Z","submitted_at":"2017-06-08T17:43:56Z","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02690","snapshot_observed_at":"2026-08-07T11:20:51.558772Z","title":"Enhanc ing the reliability of out-of-distribution image detec- tion in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.558772Z"},"links":{"cited_paper":"/paper/1706.02690","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:7d11a66915abe2d62af6f118c30cbb2f3cf577a024eba88f8e754d560093023c","observation_id":"c6edcce1-003f-4bac-a4e0-2cd9bcf98c81","resolution":{"observed_at":"2026-08-07T11:20:51.558772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.04865","last_updated":"2018-02-13T21:31:36Z","snapshot_observed_at":"2026-08-10T07:32:35.024224Z","submitted_at":"2018-02-13T21:31:36Z","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.04865","snapshot_observed_at":"2026-08-07T11:20:51.584727Z","title":"Learning confiden ce for out-of-distribution detection in neural net- works","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.584727Z"},"links":{"cited_paper":"/paper/1802.04865","citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:4035cac58f25646cb2192c3e42f3fbf3390327364a535ae2951ed644dcb1299b","observation_id":"4f7bd251-a29a-4d8a-a919-5860abc842e5","resolution":{"observed_at":"2026-08-07T11:20:51.584727Z","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":"2026-08-07T11:20:52.953360Z","title":"Can multi-label classification networks know what they don’t know? Advances in Neural Information Processing Systems , 34:29074–29087, 2021","venue":null,"work_id":"014ce2ac-d64a-462b-bcaa-8ed0c990e112","year":2021},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.592225Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:74d5a63937ad5fbaf9e172a896c598a645b134aca85d6dde25b7ad93af85f418","observation_id":"bebaaa0f-2927-49cc-a208-edc3357def6d","resolution":{"observed_at":"2026-08-07T11:20:52.969723Z","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":"2026-08-07T11:20:52.891727Z","title":"En ergy-based out-of-distribution detection","venue":null,"work_id":"39ac1263-3aed-426b-8da2-5eaac843f595","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.598616Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:8808d9c7c034cbe8c0d0d580edd792e5b4dca4e7d634092615cee38b10173a38","observation_id":"8de5a0bb-9057-4f7c-b061-82cb64e114a6","resolution":{"observed_at":"2026-08-07T11:20:52.902693Z","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":"2026-08-07T11:20:52.810960Z","title":"Leveraging visual attention for out-of-distribution detection","venue":null,"work_id":"47767f60-9440-414d-8bef-18078c3d4914","year":2023},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.607994Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:c62fdb26ba5b9acdaf0b5c7aaf47ff8beece2143ee12c1eced220f43a5887bf4","observation_id":"6ab0808c-e287-4e8a-9f0b-e542e2dda555","resolution":{"observed_at":"2026-08-07T11:20:52.842354Z","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":"2026-08-07T11:20:52.763226Z","title":"Cutmix: Regularization strategy to train strong classifiers with lo calizable features","venue":null,"work_id":"bb7355d1-944e-4cb8-ab88-23bafa9c1f04","year":2019},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.620104Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:c2e2427574f4e59e67562eaf4b2fd385de0940fe7617115aff452d4dd0756f7a","observation_id":"2c1ae4ad-9d5c-4fc2-aa4a-f1a474cc3b21","resolution":{"observed_at":"2026-08-07T11:20:52.770821Z","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":"2026-08-07T11:20:52.731611Z","title":"Detecting o ut-of-distribution examples with in-distribution ex- amples and gram matrices","venue":null,"work_id":"1a8a0a66-8c96-47b5-8bfe-c879b6f9a03c","year":1912},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.633546Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:41651c72779446a2cb820b8f7c1790fd626fb46ee1321193a399779a1175d95a","observation_id":"f2394018-355c-4393-b315-461e08ad6896","resolution":{"observed_at":"2026-08-07T11:20:52.740745Z","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":"2026-08-07T11:20:52.695620Z","title":"Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data","venue":null,"work_id":"096c148f-13c3-4278-9568-d6008b0a7a85","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.643717Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:c1e8d68d87e1dcfd6032fe4219fc00979275b7ea4ebe98debd5e201097b71671","observation_id":"a3eab43c-73c4-4c89-bfea-974f02cbe805","resolution":{"observed_at":"2026-08-07T11:20:52.705419Z","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":"2026-08-07T11:20:52.652554Z","title":"A sim ple unified framework for detecting out-of- distribution samples and adversarial attacks","venue":null,"work_id":"f2443e43-7b47-4064-ba27-1b8f46e19c69","year":2018},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.652386Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:ed3d0702dd4431f545ca27711f6472dd41e88542d9b86b48cc03e491a06c7ed0","observation_id":"8fa24d12-df7d-4a11-9740-8f4eb0a0b770","resolution":{"observed_at":"2026-08-07T11:20:52.677754Z","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":"2026-08-07T11:20:52.600194Z","title":"Mixture densities, maximum likelihood and the em algorithm","venue":null,"work_id":"dbdd3b2a-d33d-4fa0-85eb-d187e5ed0a88","year":1984},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.673166Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:9bd55f44490ff2392582ae8ac9f15ab4caab149178641744efb0ffff45d06f35","observation_id":"681a2c14-67a8-4e12-9ca2-fed902dd5780","resolution":{"observed_at":"2026-08-07T11:20:52.610521Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:20:51.700407Z","title":"Bayesian learning for neural networks , volume 118","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.700407Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:d4a1118acb52ac9a33819730e3f4cb9e5028569fff1aba7354feee7e614908e7","observation_id":"34b4a100-2f4d-449c-813a-b2183398791b","resolution":{"observed_at":"2026-08-07T11:20:51.700407Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:20:51.719752Z","title":"Markov chain Monte Carlo: stochastic simulation for Bayesian inference","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.719752Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:ca661e2832c5764ef2cb8123886276011c156b63935f657d5905f96681056eb2","observation_id":"f90f23d1-92ed-4cb1-9a48-1548abad53dd","resolution":{"observed_at":"2026-08-07T11:20:51.719752Z","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":"2026-08-07T11:20:52.500057Z","title":"Mixture outlier exposure: Towards out-of-distribution detection in fine-grained env ironments","venue":null,"work_id":"564b2974-4fb6-45e8-b34a-cf2ba4dd414b","year":2023},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.725875Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:886e178fe6241a36fb2e9d5c5c0c49a713408990797c0b260e024b4315084446","observation_id":"6c6e0003-6b78-47c8-b3ad-f514cf482b35","resolution":{"observed_at":"2026-08-07T11:20:52.507059Z","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":"2026-08-07T11:20:52.461491Z","title":"U- net: Convolutional networks for biomedical image seg- mentation","venue":null,"work_id":"cbfc026c-0f0f-4356-9501-e4ccbd477150","year":2015},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.740194Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:af41d00502da8c111327b8690127a8609e8b2ea1144430864067de2343550448","observation_id":"513b9c79-4f9e-479f-971b-371d33519dc5","resolution":{"observed_at":"2026-08-07T11:20:52.470276Z","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":"2026-08-07T11:20:52.430863Z","title":"Randaugment: Practical automated data augmen- tation with a reduced search space","venue":null,"work_id":"b9152aa5-e2ea-4c36-92c0-3a2710f69abd","year":2020},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.748535Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:3404a5742071fba2a08d23efbb5d513680fb1c123715f8bcd9da57ac5a320eb3","observation_id":"d78e6a53-09c6-440f-a568-3c9c9ff64fe4","resolution":{"observed_at":"2026-08-07T11:20:52.439428Z","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":"2026-08-07T11:20:52.409439Z","title":"Learning representations by back-propagating errors","venue":null,"work_id":"40ced66f-7a4b-4ba9-94e0-2d7f516135ed","year":1986},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.777502Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:ff85c22db9beafde43faea4178aa0ca88069c2f3542ce173fb63b036c9517c76","observation_id":"e57c2716-44bf-425d-a44e-44863d4bb84b","resolution":{"observed_at":"2026-08-07T11:20:52.415440Z","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":"2026-08-07T11:20:52.375947Z","title":"A continual deepfake detection benchmark: Datase t, methods, and essentials","venue":null,"work_id":"fc99711a-b98f-45a4-9b7d-00d3c36f2429","year":2023},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.783713Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:8cef22bc4a0642f96d1ba29d743ceaa3a8fb20fcef3a7154a2f817dab17d0a46","observation_id":"0d7e90c8-a9f3-4bbf-8a66-c267be83e5df","resolution":{"observed_at":"2026-08-07T11:20:52.381993Z","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":"2026-08-07T11:20:52.336283Z","title":"Openood v1.5: Enhanced benchmark for out-of-distribution detection, 2023","venue":null,"work_id":"5f7512e8-5c0b-4771-ae45-63570160a137","year":2023},"citing_paper":{"arxiv_id":"2506.02857","last_updated":"2025-06-03T13:24:33Z","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:20:51.794431Z"},"links":{"citing_paper":"/paper/2506.02857"},"observation_digest":"sha256:27d48e8e20e20cfb7a13bdacc5108569980e486a24252e3ebbeb00828b88df1d","observation_id":"470e676c-4d46-4d68-88e7-1e4bd40ed528","resolution":{"observed_at":"2026-08-07T11:20:52.345750Z","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":"2506.02857","last_updated":"2025-06-03T13:24:33Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T00:30:19.834242Z","submitted_at":"2025-06-03T13:24:33Z","title":"Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":2,"verified_fuzzy":29},"total_outbound_references":41},"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 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2506.02857."}