{"as_of":"2026-08-13T23:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d44224a9df2533d34d6075ff61b9231ed20959dc53a3a7e1a2994813d8f7884b","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:31:25.780150Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2506.05119/citation-record","integrity":"/paper/2506.05119/integrity","json":"/paper/2506.05119/citation-record.json","paper":"/paper/2506.05119"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:31:26.394739Z","title":"Mesonet: a compact facial video forgery detection network.2018 IEEE International Workshop on Information Forensics and Security (WIFS), pages 1–7, 2018","venue":null,"work_id":"3a0873ca-9f9c-4adb-9bf3-a600398a7479","year":2018},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.608149Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:b188db86976ead201cf0bfae70e0f6903c6ad2b85de367ac7e051ef0b863578d","observation_id":"a35ac7ab-9680-41c3-9a9e-a2e1976ebd4a","resolution":{"observed_at":"2026-08-07T10:31:26.398067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.385093Z","title":"Who inadvertently shares deepfakes? an- alyzing the role of political interest, cognitive ability, and social network size.Telematics and Informatics, 57:101508,","venue":null,"work_id":"518808d2-4643-41ca-baa8-217e9a52851c","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.612002Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:b94dc073ecb844a418a9d6c1c526aa6be19a5cc2cf1b4e6a8cf08abbc21d92c6","observation_id":"203fb46d-047d-46b3-931d-0781b792bbcd","resolution":{"observed_at":"2026-08-07T10:31:26.389064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:25.614999Z","title":"The devil is in the details: Stylefeatureeditor for detail-rich stylegan inversion and high quality image editing,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.614999Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:3f3e222a356ff0651db20475a6aa9c5d294c0f539b61a4070aab950b0409a766","observation_id":"4e9b1281-7ead-4095-8f4c-b80f76bf055c","resolution":{"observed_at":"2026-08-07T10:31:25.614999Z","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":"2026-08-07T10:31:25.618484Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.618484Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:3e6a9a92ba0db5da586ce6413e3fbdf3a2caeababdab68cd7278f4d1ba66f449","observation_id":"113d1aed-5a9e-475a-b568-34585cf660e2","resolution":{"observed_at":"2026-08-07T10:31:25.618484Z","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":"2026-08-07T10:31:26.364811Z","title":"End-to-end reconstruction- classification learning for face forgery detection","venue":null,"work_id":"d679aa3e-563c-49f0-8c15-e2964f4c9930","year":2022},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.621423Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:932e78edf8db05afbe91cc8632a7f2b2a121f3eabcae9b7d43ee4ec129afbea7","observation_id":"e8806a0d-1687-4fc0-8a9c-917a4871b6dc","resolution":{"observed_at":"2026-08-07T10:31:26.368126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.355273Z","title":"Xception: Deep learning with depthwise separable convolutions.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1800–1807,","venue":null,"work_id":"1b44ac5a-6631-4804-b111-a814e3b1986e","year":2017},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.624226Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:631168e1f4db7473c87863b653a21a6d14c31f33a1466187b7129b6c28496163","observation_id":"6f520307-b5ce-445c-82a4-2ef8650d2c4d","resolution":{"observed_at":"2026-08-07T10:31:26.358640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:25.627252Z","title":"Pillow (pil fork) documentation, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.627252Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:b9625cd06383a3429b50a701c488c915c3b6839a9a904ab399d69fec90d4b8fb","observation_id":"c7de6752-85b4-41ca-a6ba-e65df051ace3","resolution":{"observed_at":"2026-08-07T10:31:25.627252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.02510","last_updated":"2019-11-27T10:02:18Z","snapshot_observed_at":"2026-08-10T19:43:35.835757Z","submitted_at":"2018-12-06T13:11:09Z","title":"ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.02510","snapshot_observed_at":"2026-08-07T10:31:25.630285Z","title":"Forensictrans- fer: Weakly-supervised domain adaptation for forgery detec- tion.ArXiv, abs/1812.02510, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.630285Z"},"links":{"cited_paper":"/paper/1812.02510","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:bec3c0c4544cee04b1b8e956e2926444ffdec2cc0982b0c47c16e4932dd0f4d2","observation_id":"d331df6d-2f8b-4a50-8c1b-4cdd3bf61b46","resolution":{"observed_at":"2026-08-07T10:31:25.630285Z","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":"2026-08-07T10:31:26.340450Z","title":"deepfakes faceswap.https://github","venue":null,"work_id":"0265c137-c43b-434e-82c9-22fed26ea06d","year":2019},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.634025Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:f54c4ed423b27f9cf5ff988ef4987b34fc8f60e776483479146ad29239663f16","observation_id":"4204a975-3566-4816-a4a8-6514d74c6761","resolution":{"observed_at":"2026-08-07T10:31:26.343739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.08854","last_updated":"2019-10-23T18:47:35Z","snapshot_observed_at":"2026-08-06T07:27:19.098848Z","submitted_at":"2019-10-19T22:35:52Z","title":"The Deepfake Detection Challenge (DFDC) Preview Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.08854","snapshot_observed_at":"2026-08-07T10:31:25.636883Z","title":"The deepfake detection chal- lenge (dfdc) preview dataset.ArXiv, abs/1910.08854, 2019","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.636883Z"},"links":{"cited_paper":"/paper/1910.08854","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:0c3daf6ff37597d3b48f4802d4361055f977140797206caca572e250744c6363","observation_id":"028d32b2-34da-4874-ba8f-ccb7e6ec854c","resolution":{"observed_at":"2026-08-07T10:31:25.636883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07397","last_updated":"2020-10-28T03:48:28Z","snapshot_observed_at":"2026-07-06T09:28:36.954658Z","submitted_at":"2020-06-12T18:15:55Z","title":"The DeepFake Detection Challenge (DFDC) Dataset","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07397","snapshot_observed_at":"2026-08-07T10:31:25.640179Z","title":"The deepfake detection challenge dataset.ArXiv, abs/2006.07397, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.640179Z"},"links":{"cited_paper":"/paper/2006.07397","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:3407a0adb6972a8170ece55ea3234200c8d4dbbe0a73c6fe20150109f21bb711","observation_id":"222b7063-4ba4-4eee-b77f-71b6b478dd24","resolution":{"observed_at":"2026-08-07T10:31:25.640179Z","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":"2026-08-07T10:31:26.331715Z","title":"Donald trump with boris johnson’s haircut","venue":null,"work_id":"22d160fc-9aab-4a3d-b7ee-5122a73a7f52","year":2020},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.643614Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:bf8aa5f0b251c378072313c7613cc3d3208cc145099215c832d84176f0c7f8e6","observation_id":"871ed51e-4570-4820-8c27-d73e32ddc059","resolution":{"observed_at":"2026-08-07T10:31:26.334891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.322988Z","title":"How ai tools fueled online conspiracy theo- ries after trump assassination attempt.https://dfrlab","venue":null,"work_id":"e24dd0a4-dfe8-4bad-b47e-23dddec2d334","year":2024},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.646399Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:0a7b7c3837839af2ad8028e3f818257fd421a0facfb7ad91df06b84e4b7d0e5c","observation_id":"f8b73f11-2bba-4915-9726-aa9a10791ed7","resolution":{"observed_at":"2026-08-07T10:31:26.326241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.313233Z","title":"Controllable guide-space for generalizable face forgery detection.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 20761–20770, 2023","venue":null,"work_id":"d690a5f1-2449-47da-bf91-38cb731482d0","year":2023},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.649830Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:e5ea506aadd7789a568089b797123b1513afe0f4c6735fd06d393427321f335f","observation_id":"df9645f6-9a2e-4933-b408-eb59ce5e2721","resolution":{"observed_at":"2026-08-07T10:31:26.316908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.304123Z","title":"The social im- pact of deepfakes, 2021","venue":null,"work_id":"69b094c1-fc33-4cfc-972f-c9c2481bbbd9","year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.652609Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:4d94e01109379699ee03084fc24e06241deb7397c02380e50c3846118c5c2eae","observation_id":"73569010-936b-49c8-8246-3116e555d8af","resolution":{"observed_at":"2026-08-07T10:31:26.307202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08625","last_updated":"2024-06-25T13:12:20Z","snapshot_observed_at":"2026-08-12T23:44:09.604177Z","submitted_at":"2024-06-12T20:15:00Z","title":"FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended Images","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08625","snapshot_observed_at":"2026-08-07T10:31:25.655421Z","title":"Fsbi: Deepfakes detection with frequency en- hanced self-blended images.ArXiv, abs/2406.08625, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.655421Z"},"links":{"cited_paper":"/paper/2406.08625","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:ed692e7fabadbcbe0fca44af9b454589e240c29b2b68ac2bb978f3f238f999c6","observation_id":"44456ff5-a3c4-42a4-949b-458562341608","resolution":{"observed_at":"2026-08-07T10:31:25.655421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14376","last_updated":"2021-05-29T21:22:24Z","snapshot_observed_at":"2026-08-13T19:13:57.201955Z","submitted_at":"2021-05-29T21:22:24Z","title":"Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14376","snapshot_observed_at":"2026-08-07T10:31:25.658604Z","title":"Beyond the spectrum: Detecting deepfakes via re-synthesis.ArXiv, abs/2105.14376, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.658604Z"},"links":{"cited_paper":"/paper/2105.14376","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:4c73c38b711fa307873cc8ab2794fe42b05b1ad53b574c93fdc37aced8c8e6f4","observation_id":"e7dccb3b-456a-40b6-9f7c-857b461a444a","resolution":{"observed_at":"2026-08-07T10:31:25.658604Z","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":"2026-08-07T10:31:26.294383Z","title":"Deepvi- sion: Deepfakes detection using human eye blinking pattern","venue":null,"work_id":"8f39a847-63b2-494b-bd38-abc4a6cc32cd","year":2020},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.661814Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:80a778316293639bf38b96c94ea417d06eabc2200fb5471311b1536de12b9f6b","observation_id":"c1cffdd0-0358-43c8-ab2a-f524f01c549a","resolution":{"observed_at":"2026-08-07T10:31:26.298354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.284549Z","title":"Faceswap.https://github.com/ MarekKowalski/FaceSwap, 2018","venue":null,"work_id":"e2f118ee-b967-4f78-bc53-358a2e327bdd","year":2018},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.664943Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:386c2f61154ac8321018b6f2e911bd3daea9e34f71a4f5ff8d0c2a559d1c6985","observation_id":"3406ebff-9e94-46f4-bd49-326b0c18b194","resolution":{"observed_at":"2026-08-07T10:31:26.287804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.274697Z","title":"Seeable: Soft discrepancies and bounded contrastive learning for exposing deepfakes.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 20954–20964, 2022","venue":null,"work_id":"d71797e6-d771-4c11-a33d-08c3cd38b44e","year":2023},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.667828Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:9b9aa1b597e0234e2d5c49a4bbc5e8fb266269de726b6b8c5e9cd8c674fed256","observation_id":"f069dbac-8b37-402b-8a51-f564eb8c1e45","resolution":{"observed_at":"2026-08-07T10:31:26.278082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.265311Z","title":"Face x-ray for more general face forgery detection.2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5000–5009, 2019","venue":null,"work_id":"aaecb2b2-172c-4cfb-8cd5-459a30e2a07c","year":2020},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.670849Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:29efc02db9140dc8723ad035dd94c35c09d86a31837900e4a714b12d319a6566","observation_id":"14ceac88-0ce6-4987-a246-72941a66baaf","resolution":{"observed_at":"2026-08-07T10:31:26.268858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:25.673940Z","title":"Celeb-df: A large-scale challenging dataset for deep- fake forensics.2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3204–3213,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.673940Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:6357b632d17dbcce1eb44dd34cc8e14b0d5126eb6a4bc231473b23e4ce895b24","observation_id":"e76bc701-6a4d-4eb6-a293-433be1750294","resolution":{"observed_at":"2026-08-07T10:31:25.673940Z","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":"2026-08-07T10:31:26.250736Z","title":null,"venue":null,"work_id":"bf7c01ce-7a48-42eb-8e8c-d257e05a3873","year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.677353Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:b4e1c8e3291e5e97be3bcf0b1ef04c41ffee052ba726538b66796645988e89db","observation_id":"4bc33b42-04ab-4f4b-8d0d-2a3feeadd8d5","resolution":{"observed_at":"2026-08-07T10:31:26.253639Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.241909Z","title":"A new approach to im- prove learning-based deepfake detection in realistic condi- tions, 2022","venue":null,"work_id":"805f40ab-42ce-49a3-a0c8-1a30719f2a35","year":2022},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.680339Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:c784d83d2679e4bc56cb8e05485083968db7b5ec90245668536f5a69d727caae","observation_id":"6c3c4e26-73ba-4cd0-9b53-a0dd2f681574","resolution":{"observed_at":"2026-08-07T10:31:26.245117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06125","last_updated":"2023-04-12T19:09:22Z","snapshot_observed_at":"2026-08-13T12:03:59.984746Z","submitted_at":"2023-04-12T19:09:22Z","title":"Assessment Framework for Deepfake Detection in Real-world Situations","version":1},"cited_work":{"arxiv_id":"2304.06125","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.06125","snapshot_observed_at":"2026-08-07T10:31:25.959666Z","title":"Assessment Framework for Deepfake Detection in Real-world Situations","venue":"cs.CV","work_id":"8ce94e83-19fa-4d10-80a7-9330d903a2b2","year":2023},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.683169Z"},"links":{"cited_paper":"/paper/2304.06125","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:160a545ff798355e84b354266307e8883e99ff2fa3601c27d1a96cb20fd7a341","observation_id":"3c947f21-e3e0-4af6-88a3-d8503aab1fc6","resolution":{"observed_at":"2026-08-07T10:31:25.963334Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.233282Z","title":"Gener- alizing face forgery detection with high-frequency features","venue":null,"work_id":"24e85da3-de2f-408d-bfce-e2a4dafb1c97","year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.686439Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:1c9338b4ae6d844b9a08e72399f5acda2fa9c4b194ef6678fed23a37ef9ad041","observation_id":"ee1b6223-7289-4dc1-96f8-fd209cca708f","resolution":{"observed_at":"2026-08-07T10:31:26.236496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03412","last_updated":"2020-09-04T01:03:55Z","snapshot_observed_at":"2026-08-08T04:10:45.536409Z","submitted_at":"2020-08-08T01:38:56Z","title":"Two-branch Recurrent Network for Isolating Deepfakes in Videos","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03412","snapshot_observed_at":"2026-08-07T10:31:25.689195Z","title":"Two- branch recurrent network for isolating deepfakes in videos","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.689195Z"},"links":{"cited_paper":"/paper/2008.03412","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:872a1ba3305094bcb27235cd2d587882766ba74a45a7521a5e1af09459e46174","observation_id":"05427706-a658-4a89-9908-185c43ec50c8","resolution":{"observed_at":"2026-08-07T10:31:25.689195Z","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":"story/8694792","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:31:25.931688Z","title":"Fbi names shooter after trump as- sassination attempt.https://www.moreechampion","venue":null,"work_id":"87742564-3e94-4898-9375-32a4c094c6da","year":2024},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.692611Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:5f27540c99dbdfe866bb52b9b1e4bdb63442fb88ad1b1ec19edd7fb58e766d8f","observation_id":"715065e9-67c3-47ee-ad84-fa6178bfba2d","resolution":{"observed_at":"2026-08-07T10:31:25.939685Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.224038Z","title":"Laa-net: Localized artifact attention network for quality-agnostic and generalizable deepfake de- tection","venue":null,"work_id":"dc7fcd62-6dda-4d60-8214-8520c1ac4154","year":2024},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.695488Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:9cc426df3d49e54c41246d94ad8bf27f86c5df07f41aa6a6741ae8926c6f03c5","observation_id":"245b34e8-67f8-4678-ab99-08255167fbee","resolution":{"observed_at":"2026-08-07T10:31:26.227463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.214759Z","title":"Poisson image editing.ACM SIGGRAPH 2003 Papers, 2003","venue":null,"work_id":"c0f74ca1-921e-4a5b-b3ae-da478bdee196","year":2003},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.698386Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:268248651042a5580e0ea8c232b24c928f97b3cea66fac60bf9e7628425f2c4b","observation_id":"6c3e1ac4-03c0-4ea4-bdd4-a53f659fcc25","resolution":{"observed_at":"2026-08-07T10:31:26.218084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.09355","last_updated":"2020-10-27T04:04:29Z","snapshot_observed_at":"2026-08-12T15:28:24.316474Z","submitted_at":"2020-07-18T07:39:08Z","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.09355","snapshot_observed_at":"2026-08-07T10:31:25.701269Z","title":"Thinking in frequency: Face forgery detection by min- ing frequency-aware clues.ArXiv, abs/2007.09355, 2020","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.701269Z"},"links":{"cited_paper":"/paper/2007.09355","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:07ae9b34aed27f7e52a2c413df817658c49015da8b599df6bdbbc858cc5d8568","observation_id":"75f756af-3ec5-4276-abdf-07fd4320f761","resolution":{"observed_at":"2026-08-07T10:31:25.701269Z","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":"2026-08-07T10:31:26.205421Z","title":"High-resolution image syn- thesis with latent diffusion models, 2021","venue":null,"work_id":"e14bf361-0343-484b-8fdf-3fcfec2072c4","year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.704853Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:9813c9b23f61849e34e19356007587577695fa51ff8e84c69df4ac1cfffc7e0a","observation_id":"7fc4c0ea-5cc5-42dc-b0a3-bbb6268612bb","resolution":{"observed_at":"2026-08-07T10:31:26.208686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.195102Z","title":"FaceForen- sics++: Learning to detect manipulated facial images","venue":null,"work_id":"4e9d282e-f3e4-48bb-aab4-15ee7856ccd8","year":2019},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.707645Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:c7795ef3734194b7164c2b5dc58f4293c53cb72202f404e8f51058ca99ce3a0e","observation_id":"ca312fdf-9e0a-4e22-8dcb-bbcbc7360f7a","resolution":{"observed_at":"2026-08-07T10:31:26.198786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.186082Z","title":"Natarajan","venue":null,"work_id":"9bfed3e3-34da-4329-8b94-dea693e68844","year":2019},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.710632Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:253c5b1c9b147b5f14df58d2d16580f9d8b09a959029e9f8171b2a2df7b64d6e","observation_id":"42e7602d-d022-4846-94b1-42dad5e1c41f","resolution":{"observed_at":"2026-08-07T10:31:26.189230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.176725Z","title":"Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, and Dhruv Ba- tra","venue":null,"work_id":"d0662548-d65f-4779-8859-c5848792410b","year":2016},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.713339Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:57c246ff2baee89fa6116b52f281b99811814dd1f242f7c308cd9f5b51333d0e","observation_id":"e2a49ff7-10dd-48a9-a9bd-e7e30efad7a7","resolution":{"observed_at":"2026-08-07T10:31:26.180042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.166702Z","title":"Yamasaki","venue":null,"work_id":"2eb71a0f-0d6f-4469-93dd-35a7a5678ff1","year":2022},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.717167Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:fe544c3e82f50e79b39a97ff566703672deefd0f35690c2e48407a7d2ff5c5cc","observation_id":"71e65312-eb74-4c89-98a4-6513afad29aa","resolution":{"observed_at":"2026-08-07T10:31:26.170779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-07T10:31:25.720030Z","title":"Erhan, Ian J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.720030Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:e8309a95eeee158fada82fe5e2eee006a5cb5a774caa6c9eda70ef5302a7d64a","observation_id":"1632e447-2706-4f4a-9820-9bb06082685d","resolution":{"observed_at":"2026-08-07T10:31:25.720030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11946","last_updated":"2020-09-11T05:08:01Z","snapshot_observed_at":"2026-08-10T19:44:30.311627Z","submitted_at":"2019-05-28T17:05:32Z","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11946","snapshot_observed_at":"2026-08-07T10:31:25.723341Z","title":null,"venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.723341Z"},"links":{"cited_paper":"/paper/1905.11946","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:804d8af4764ad39716961527725fe821e2ad10f5a61faab2391e8d5914c64646","observation_id":"1a6aca98-4498-4136-8661-ea3d842c9a7e","resolution":{"observed_at":"2026-08-07T10:31:25.723341Z","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":"2026-08-07T10:31:26.157228Z","title":"Face2face: Real-time face capture and reenactment of rgb videos.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2387–2395, 2016","venue":null,"work_id":"aa9dad39-efb3-4c1a-b3e7-6dd687960209","year":2016},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.726512Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:36d44113f66466fa013deace4e95f406449c2b6bbf443cb7daec527569fa7d40","observation_id":"1533d1b9-5c71-4da6-974a-ee4dbff488fc","resolution":{"observed_at":"2026-08-07T10:31:26.160676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.146939Z","title":"De- ferred neural rendering.ACM Transactions on Graphics (TOG), 38:1 – 12, 2019","venue":null,"work_id":"76df79d1-777a-4db8-b984-3357011daaa8","year":2019},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.729274Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:0a319ea9b9f2e3c47c4ce1c2ffe9683c7ec0593f75ea7465085b247cbc226e85","observation_id":"727cca81-8931-404e-b3d3-80f4b8297b4c","resolution":{"observed_at":"2026-08-07T10:31:26.151043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.136998Z","title":null,"venue":null,"work_id":"3626f264-ba77-4cfd-b931-e470270d2d3d","year":2020},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.732194Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:3fe8bf0830d18c508b51700c7b159db425995f058cdcfdf2d2da3e8361eaada5","observation_id":"cc9b0ad4-74e3-4ed7-9c73-d21b3192f491","resolution":{"observed_at":"2026-08-07T10:31:26.140444Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.126579Z","title":"Transcending forgery specificity with latent space augmentation for generalizable deepfake detection","venue":null,"work_id":"e2c834ce-f253-4199-9588-aa82808da147","year":2024},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.735033Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:bd9f056d16b5f2743146d98f2585a523ad3c85123afa052343f024dd98f52eb0","observation_id":"2a9bab7e-5944-4688-97b6-975f126ff2e9","resolution":{"observed_at":"2026-08-07T10:31:26.131135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.116504Z","title":"Ucf: Uncovering common features for generalizable deep- fake detection.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 22355–22366, 2023","venue":null,"work_id":"56a0f96e-0bc6-457b-ae2c-ac94c544a39b","year":2023},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.738572Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:e03bfd229776b7f987b3107363c1a1e4af90e9fa6052525fd215ce77d2284406","observation_id":"9ba06d64-e0f3-40ed-bf24-f29a24b5acb6","resolution":{"observed_at":"2026-08-07T10:31:26.120527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01426","last_updated":"2023-10-28T10:05:52Z","snapshot_observed_at":"2026-08-13T11:03:20.215728Z","submitted_at":"2023-07-04T01:34:41Z","title":"DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01426","snapshot_observed_at":"2026-08-07T10:31:25.741646Z","title":"Deepfakebench: A comprehensive benchmark of deepfake detection.ArXiv, abs/2307.01426, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.741646Z"},"links":{"cited_paper":"/paper/2307.01426","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:d090fec32796f55f29b661024876b39f2bee89db3fc9e6447e8dd02dc2dce547","observation_id":"e5fc4d4d-abe6-42a8-b157-1545d299e4e1","resolution":{"observed_at":"2026-08-07T10:31:25.741646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13495","last_updated":"2024-10-31T09:11:37Z","snapshot_observed_at":"2026-08-12T23:39:16.028605Z","submitted_at":"2024-06-19T12:35:02Z","title":"DF40: Toward Next-Generation Deepfake Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13495","snapshot_observed_at":"2026-08-07T10:31:25.744733Z","title":"Df40: Toward next-generation deepfake detection.arXiv preprint arXiv:2406.13495, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.744733Z"},"links":{"cited_paper":"/paper/2406.13495","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:386df6d61f6ffa8ac1f31c2b3a9351908dd2d1547febc777d90b2a54bbc04367","observation_id":"aa47baec-f3c0-4aab-b757-c2c133ea6115","resolution":{"observed_at":"2026-08-07T10:31:25.744733Z","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":"2026-08-07T10:31:26.106952Z","title":"Zhang, Jingyun Liang, Luc Van Gool, and Radu Timofte","venue":null,"work_id":"3cb83e44-ef3f-4700-b367-efe9259df562","year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.747809Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:7d415bf4ffeaca63b3bd81ef3897f370d936d14d834ba27fc7c0ac8fc9df9ae8","observation_id":"30f41928-16dc-4795-9690-fa06cf58ccd6","resolution":{"observed_at":"2026-08-07T10:31:26.110330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.096827Z","title":"Learning self-consistency for deep- fake detection.2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages 15003–15013, 2020","venue":null,"work_id":"65870090-68aa-4e73-a973-a32f87e5780b","year":2021},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.750671Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:6e1abc300582c5e72dfc475e1911b5e02ada31a79a2486ce526eabb30c7e49bc","observation_id":"94863247-cdab-4029-b8b9-04f24e2cc1ab","resolution":{"observed_at":"2026-08-07T10:31:26.100382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.12752","last_updated":"2022-10-23T15:24:47Z","snapshot_observed_at":"2026-08-13T13:58:49.619815Z","submitted_at":"2022-10-23T15:24:47Z","title":"UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.12752","snapshot_observed_at":"2026-08-07T10:31:25.753489Z","title":"Uia-vit: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection.ArXiv, abs/2210.12752, 2022","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.753489Z"},"links":{"cited_paper":"/paper/2210.12752","citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:186aefc9c547c915116f21ac064009053663423af6e881bf86cf72440e20bfd7","observation_id":"3c6ee288-8fee-4707-896d-5900f05904ae","resolution":{"observed_at":"2026-08-07T10:31:25.753489Z","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":"2026-08-07T10:31:26.087109Z","title":null,"venue":null,"work_id":"6eeb0a08-b773-4957-8b25-34e3f5086f7f","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.757706Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:efa592069616f8ba97ef0887460ef5a5f8060ddc8ca500b65429360b4ea22574","observation_id":"23c4f65d-0b79-47d0-86cb-c4bd98fcd36d","resolution":{"observed_at":"2026-08-07T10:31:26.090348Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.077490Z","title":"Positions outside of the image region result in the text being partially visible","venue":null,"work_id":"df213ac6-3204-42a1-8b56-61627254ffed","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.760837Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:b8775adbd269eb24dea7a06431a14662155f279cc348a3b7658f8ff1d49b0f3b","observation_id":"ee32840e-e2dd-4b77-bcaa-0a40d824e836","resolution":{"observed_at":"2026-08-07T10:31:26.080839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.066899Z","title":null,"venue":null,"work_id":"f5172173-1399-4dda-b9d7-d557214d35dd","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.764070Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:c7f2d69d4476386a47695c5be84579ee99406b15c40b2944affd57ab631ec860","observation_id":"1a8e02ef-62bd-4307-b023-3b0faffcfa85","resolution":{"observed_at":"2026-08-07T10:31:26.070275Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.056378Z","title":null,"venue":null,"work_id":"bad50aee-eaca-4fd4-b935-fb89938c0969","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.767278Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:051b012944dd158074c8d67fa72009c1bd42ec10b474ab82f82c3540a6acc744","observation_id":"feefea4e-3643-4a47-9c89-42cfbecca476","resolution":{"observed_at":"2026-08-07T10:31:26.059616Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.045915Z","title":null,"venue":null,"work_id":"3edf4f2d-ab22-4762-9d81-220f03bfaeed","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.770322Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:35f72806adc6e31cb094e93eeec2897334dcacfe74689ee452eb42a3ab5ad61d","observation_id":"315b27bb-5059-42ed-826e-dcae7795957b","resolution":{"observed_at":"2026-08-07T10:31:26.049847Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.036174Z","title":null,"venue":null,"work_id":"ef14c06d-6966-4f1f-9803-cc009722d8a4","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.773854Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:d3743c093426b31157e9e7df5b1e5608cafd40ab1d7bd4b7b0c08db9b077c93d","observation_id":"e5170d80-ae03-4a14-817b-32f3adc4e7d1","resolution":{"observed_at":"2026-08-07T10:31:26.039431Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.026266Z","title":null,"venue":null,"work_id":"a9b5c26d-f5fd-4b66-9abc-694d5ad67b4a","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.776944Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:bc7880efc85c8f0f78052933f08528d2e29dc8fb1f84424dab1f1ff572defe28","observation_id":"fd841444-884c-4a1e-93cc-01337c46a2f8","resolution":{"observed_at":"2026-08-07T10:31:26.029913Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-07T10:31:26.017176Z","title":"All images are taken from the Celeb- DF-v2 dataset [22]","venue":null,"work_id":"8c285409-e3ab-465d-ae19-df03e58e1689","year":null},"citing_paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T10:31:25.780150Z"},"links":{"citing_paper":"/paper/2506.05119"},"observation_digest":"sha256:4f9c9d26d37c85c5256ea7eac6d15a139f8019d9d0137ec0306753a02286b7cf","observation_id":"f6478399-b110-4ae0-a51c-90be5668407b","resolution":{"observed_at":"2026-08-07T10:31:26.020280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.05119","last_updated":"2025-06-05T15:06:16Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T11:27:18.855093Z","submitted_at":"2025-06-05T15:06:16Z","title":"Practical Manipulation Model for Robust Deepfake Detection"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":2,"verified_fuzzy":30},"total_outbound_references":56},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2506.05119."}