{"as_of":"2026-08-08T13:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2744954ce31529d1431da04b41f869d17b8bce133e303e351d53a084bba23c4","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:15:57.484222Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2507.05996/citation-record","integrity":"/paper/2507.05996/integrity","json":"/paper/2507.05996/citation-record.json","paper":"/paper/2507.05996"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:15:58.532158Z","title":"Deepfakes: Deceptions, mitigations, and opportunities,","venue":null,"work_id":"0035c218-ffae-49b6-9dd1-5e29306bb93c","year":2023},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.147024Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:534c3c06c4ec8d00c3510ca2f84664765e065f4cb0397fb64bae43904bfbaa40","observation_id":"ef800b58-258c-43e9-91f8-878f0be0d8bd","resolution":{"observed_at":"2026-08-06T19:15:58.628391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T19:15:58.378259Z","title":"Unmasking deepfakes: A systematic review of deepfake detection and generation techniques using artificial intelligence,","venue":null,"work_id":"6508343b-a8a5-4bf6-a04b-73327aa7cea9","year":2024},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.236247Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:fa31a855f21153ad7abd507538da1f99351f38e8df021ddaf4e3f3f445c46601","observation_id":"e5c51fca-4c7a-4821-ba31-6b1c07e0c888","resolution":{"observed_at":"2026-08-06T19:15:58.440248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18866","last_updated":"2024-10-24T15:51:04Z","snapshot_observed_at":"2026-07-06T19:39:10.669393Z","submitted_at":"2024-10-24T15:51:04Z","title":"The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.18866","snapshot_observed_at":"2026-08-06T19:15:56.312329Z","title":"The cat and mouse game: The ongoing arms race between diffusion models and detection methods,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.312329Z"},"links":{"cited_paper":"/paper/2410.18866","citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:635f3149a48a8498dfe6b1a6665d9dde7392bc9d83fa989f4d75e7c990b1a5de","observation_id":"795aa029-d8b2-426b-846a-c2223c032143","resolution":{"observed_at":"2026-08-06T19:15:56.312329Z","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":"2026-08-06T19:15:56.376597Z","title":"Deepfake generation and detection: A benchmark and survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.376597Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:efbaa58bd21d236c016d1555e7df0469b1fdb143538b858e50677b03dba5a60d","observation_id":"65a9667d-ed05-4258-b3bb-47162d1966ed","resolution":{"observed_at":"2026-08-06T19:15:56.376597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01426","last_updated":"2023-10-28T10:05:52Z","snapshot_observed_at":"2026-08-07T23:00:53.322063Z","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":"2026-08-06T19:15:56.458455Z","title":"Deepfakebench: A comprehensive benchmark of deepfake detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.458455Z"},"links":{"cited_paper":"/paper/2307.01426","citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:b090fbcbdf9fece90f7e15e2ff4d1fb36c542256e8988c0775406041509347a9","observation_id":"1d0e947f-9ecd-47c9-b34b-6bb87d21b61c","resolution":{"observed_at":"2026-08-06T19:15:56.458455Z","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":"2026-08-06T19:15:56.538491Z","title":"Mesonet: a compact facial video forgery detection network,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.538491Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:d08448e87edc34c41211560b78996654d2e394b969f86b7f634b0d1933b338eb","observation_id":"4970f777-1991-4a0a-b4f3-9330efa0ce22","resolution":{"observed_at":"2026-08-06T19:15:56.538491Z","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":"2026-08-06T19:15:56.612826Z","title":"Faceforensics++: Learning to detect manipulated facial images,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.612826Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:d73d077b99ded9ef3cd4df6adce09518888e55dd5eba90e52ccaa172448447ec","observation_id":"e64f754f-7653-408c-a758-b047eb8fa49e","resolution":{"observed_at":"2026-08-06T19:15:56.612826Z","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":"2026-08-06T19:15:56.686840Z","title":"Core: Consistent representation learning for face forgery detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.686840Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:75b610cd0ccf28b260e14229b2228ed1d6984bc0b10f606285c9d66b8b4e1f3c","observation_id":"e68e6e9d-cd67-4229-b857-cf3a5cb71018","resolution":{"observed_at":"2026-08-06T19:15:56.686840Z","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":"2026-08-06T19:15:58.193579Z","title":"On the detection of digital face manipulation,","venue":null,"work_id":"d5237d68-8875-48f5-ad32-1818ad16ab20","year":2020},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.801342Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:b10be3fb1362633161debf6f7e9d7a881444fc568fba32d509601eaf9eb3f2d5","observation_id":"a9971957-5377-4db0-aa57-0a4a965ca576","resolution":{"observed_at":"2026-08-06T19:15:58.234952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T19:15:58.042794Z","title":"Generalizing face forgery detec- tion with high-frequency features,","venue":null,"work_id":"371a58b8-ab56-4c93-9505-26afdf1006da","year":2021},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:56.952456Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:c54f979642188e18b98ad2448237b1c9a50258e41692366a8ac14130a732fbe6","observation_id":"8fec832c-ffc8-4f5b-878f-aee303ba978d","resolution":{"observed_at":"2026-08-06T19:15:58.110464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T19:15:57.080613Z","title":"Ucf: Uncovering common features for generalizable deepfake detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:57.080613Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:a00b78f57401a76e3ddf6c4e607311fa5b9de3a3dbe3ad4cf8a14282800682b7","observation_id":"8e38e556-16f7-4e02-ad46-09e8c68f7f18","resolution":{"observed_at":"2026-08-06T19:15:57.080613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.17391","last_updated":"2025-03-17T13:20:52Z","snapshot_observed_at":"2026-08-07T23:04:22.778666Z","submitted_at":"2025-02-24T18:16:23Z","title":"The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE","version":2},"cited_work":{"arxiv_id":"2502.17391","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.17391","snapshot_observed_at":"2026-08-06T19:15:57.620778Z","title":"The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE","venue":"cs.LG","work_id":"2cad1c0f-8312-49f4-b0ed-f23c30ddce9c","year":2025},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:57.206712Z"},"links":{"cited_paper":"/paper/2502.17391","citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:eaf8fbee01245e4ddeec3b72dbe448a601e6ff56b70faa5caa511b38b750bf77","observation_id":"24a8d08f-5566-4965-ab8b-f59eab699ecf","resolution":{"observed_at":"2026-08-06T19:15:57.675651Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-06T19:15:57.332051Z","title":"Face2face: Real-time face capture and reenactment of rgb videos,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:57.332051Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:6cbfb8286b88662877003e35ece2824429a0b08f387320446dcb9928d7a69479","observation_id":"f25617f1-4fc0-4f80-9d27-fb0b8ead7fe3","resolution":{"observed_at":"2026-08-06T19:15:57.332051Z","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":"2026-08-06T19:15:57.414836Z","title":"Deferred neural rendering: Image synthesis using neural textures,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:57.414836Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:684110a3c97f4b006ccce41b77ca6425dd6b20b0f4818db2c7af1c0e9ab81005","observation_id":"a3b2f516-2df6-4559-add5-8de5163baa63","resolution":{"observed_at":"2026-08-06T19:15:57.414836Z","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":"2026-08-06T19:15:57.484222Z","title":"Dlib-ml: A machine learning toolkit,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:15:57.484222Z"},"links":{"citing_paper":"/paper/2507.05996"},"observation_digest":"sha256:40cd3b36c963fb701a47b355346e272e075a3df9e30640c6922911ea9b957209","observation_id":"88e851f4-3581-4dfd-8f5f-303aa92585db","resolution":{"observed_at":"2026-08-06T19:15:57.484222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.05996","last_updated":"2025-07-08T13:54:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T23:01:06.530302Z","submitted_at":"2025-07-08T13:54:48Z","title":"Ensemble-Based Deepfake Detection using State-of-the-Art Models with Robust Cross-Dataset Generalisation"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":4},"total_outbound_references":15},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2507.05996."}