{"as_of":"2026-08-10T11:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9670db08f916ab7cba05a21ac9058a798ef4e88e0164fe2a5119e786406255e3","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:32:01.601958Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.15636/citation-record","integrity":"/paper/2507.15636/integrity","json":"/paper/2507.15636/citation-record.json","paper":"/paper/2507.15636"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.860297Z","title":"Deepfakes, misinformation, and disinformation in the era of frontier AI, generative AI, and large AI models,","venue":null,"work_id":"1b4987c6-4134-4fdf-ac95-077e6ca132e0","year":2023},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.755781Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:d6a2fd66c0608f10acf203752b0772a75eb0a433f3347d1ade583d28c9040663","observation_id":"9a627ab2-c0ba-424a-bddd-3645a9e6cff2","resolution":{"observed_at":"2026-08-06T15:32:04.908895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.743239Z","title":"Generative AI and deep fakes in media industry– An innovation resistance theory perspective,","venue":null,"work_id":"9b707280-c756-42be-b8d0-d0213c06df8d","year":2024},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.777419Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:c67f3802b2c78e828906d3ad1ceb1a08b2682c0bd6069dec4d16d5f6f2dd27f9","observation_id":"c61e7d4b-21ef-4892-ac67-5b51abf35dea","resolution":{"observed_at":"2026-08-06T15:32:04.797804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.630877Z","title":"A deepfake compressed video detection method based on dense dynamic CNN,","venue":null,"work_id":"5db04b97-af02-40a9-a581-f895c9b03cf0","year":2022},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.818693Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:99fe0eff4004be6d615e3bc526088a42a52ef535e5929f69b4adf2d92c5fe499","observation_id":"7cb956ca-c71f-4f49-97ce-5519569ea86b","resolution":{"observed_at":"2026-08-06T15:32:04.683738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.481868Z","title":"Detecting compressed deep- fake videos in social networks using frame-temporality two-stream convolutional network,","venue":null,"work_id":"4f199049-f8c7-4083-8aa5-6e92960d1a31","year":2021},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.852926Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:ec71218903d8e1c40df0b0340d0c758fdfa69474321165af2fc809d3cbfac5e8","observation_id":"5cebc89b-55d0-425f-8aa6-6ee15cae7dec","resolution":{"observed_at":"2026-08-06T15:32:04.548324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.313994Z","title":"A lightweight CNN for efficient deepfake detection of low-resolution images in frequency domain,","venue":null,"work_id":"f5f3498d-31d2-44f5-bc09-10b8bc500802","year":2024},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.887499Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:f38d541bae98cd2bd610de6716e2e9d38b90a69294c31c44b6cf3508b9d9f641","observation_id":"1809df61-604a-4abe-9015-57265a979d62","resolution":{"observed_at":"2026-08-06T15:32:04.389483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.161313Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks,","venue":null,"work_id":"fdf91c23-dfed-4503-9503-6ddc47cd1c9d","year":2018},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.919951Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:697c32ba783a13283aaaa46c94a75a7a89c61c35edf4d96e83abb2f715d213da","observation_id":"80b6a7e7-ccf9-4ca1-9c1e-24258a8d0e00","resolution":{"observed_at":"2026-08-06T15:32:04.243019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:04.032968Z","title":"Exploiting deepfakes by analyzing temporal feature inconsistency","venue":null,"work_id":"f28bd475-ad62-4a88-96c2-fb6d4b01ec77","year":2023},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T15:31:59.948383Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:2a455dffa5b514fdbb80abe4d73a71b3e57c5a6e7cc21fa0193e9c4ef45333e0","observation_id":"24efcbe2-929e-4c9f-8322-6a6f42ee5821","resolution":{"observed_at":"2026-08-06T15:32:04.087015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:03.914839Z","title":"MesoNet: a compact facial video forgery detection network,","venue":null,"work_id":"2f9ba809-03af-47f5-a94b-80758fd897e7","year":2018},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.022905Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:daddd9e1930c7aa4c6a3ce6548c38c2d589f615d419ee57ca5f89a5f0112b18d","observation_id":"0cd46256-eb45-4149-9950-fa4e13402b5f","resolution":{"observed_at":"2026-08-06T15:32:03.960847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:00.128614Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.128614Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:cbe6e3abdace166f3559124f93bd89e7b65472509f064654caca79d460db3cda","observation_id":"859a403d-18c2-41b0-9216-a66f5cf0621b","resolution":{"observed_at":"2026-08-06T15:32:00.128614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.09179","last_updated":"2018-03-24T23:12:44Z","snapshot_observed_at":"2026-07-06T06:30:02.787977Z","submitted_at":"2018-03-24T23:12:44Z","title":"FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.09179","snapshot_observed_at":"2026-08-06T15:32:00.236836Z","title":"Faceforensics: A large-scale video dataset for forgery detection in human faces,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.236836Z"},"links":{"cited_paper":"/paper/1803.09179","citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:96c1e7732126d0d61aa107d762d7c610953a8ea9ac4c4dc7db605b92d1840ae3","observation_id":"468a7351-3777-4386-bf42-6f017d25903f","resolution":{"observed_at":"2026-08-06T15:32:00.236836Z","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":"2026-08-06T15:32:03.751569Z","title":"The open images dataset v4: Unified image classi- fication, object detection, and visual relationship detection at scale,","venue":null,"work_id":"46e6da89-a0f5-4cfe-a969-a017cc64fd78","year":2020},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.313781Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:086c566c1318acaf44150a5b06baea2542c11bec8a6de355bd4f099c5c52e054","observation_id":"00b4997a-a6e1-4762-80d2-494aa93968ef","resolution":{"observed_at":"2026-08-06T15:32:03.844398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:03.579967Z","title":"FaceForensics++: Learning to detect manipulated facial images,","venue":null,"work_id":"9ee61523-5780-4a19-91a9-9d50ebac25bf","year":2019},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.416164Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:acd8d4c5a32e3022843a5b74ffb9e4f1923288e57e8910d721bc3ae315a9ed69","observation_id":"cc3c9905-320e-4761-9111-8b266177d6de","resolution":{"observed_at":"2026-08-06T15:32:03.660753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:03.436979Z","title":"Fake- buster: A lightweight solution for deepfake detection,","venue":null,"work_id":"8286da0f-c9b0-4af4-b35b-5cfe7eaea89d","year":2021},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.487825Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:fd7deb87e634b28130b8d62846887aaac277971e8161ae771b5f7fc71830c013","observation_id":"3bcca0f0-7892-46ad-9e94-939ec8151b04","resolution":{"observed_at":"2026-08-06T15:32:03.491527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:03.312346Z","title":"Neural geometric level of detail: Real-time rendering with implicit 3D shapes,","venue":null,"work_id":"be897f96-0d47-461f-b416-6ab8bf1ff89b","year":2021},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.583492Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:9b29f8cddb7f1ff2294b62828be94f01ec6ad83155d6a8a0fc70ed64983127e1","observation_id":"3faac1e1-c845-4565-ba81-c65d9ed92c51","resolution":{"observed_at":"2026-08-06T15:32:03.393538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:03.122647Z","title":"LLM-Pruner: On the structural pruning of large language models,","venue":null,"work_id":"8ced708e-df3f-495d-a0ae-2a8d29355069","year":2023},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.665405Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:8339b76e0cdbbaafc025aee33f3342634464b70b8fa5a76623091207ec62f1ea","observation_id":"84bfad1d-de63-4f98-aacb-bcfe6fee6231","resolution":{"observed_at":"2026-08-06T15:32:03.218202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:02.954737Z","title":"Pruning for robust concept erasing in diffusion models,","venue":null,"work_id":"5ca9ac7f-93a8-4eca-be8c-33f8aefa38b3","year":2024},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.746957Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:63d4c8e467dcc4e354ae285591df109f0f68a744081023f954c329a8f5091912","observation_id":"080eb23b-fa59-49a1-98ed-9978e9002d78","resolution":{"observed_at":"2026-08-06T15:32:03.032096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:02.850519Z","title":"Pruning convolutional neural networks for resource efficient inference,","venue":null,"work_id":"c2c244a0-a7e5-4a7a-915d-06369d5b221a","year":2017},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.830420Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:5c258edb25c15d771ae077c29a06735b1b08364081862ae8a676b97eb9792dc7","observation_id":"d04ad098-35cc-489b-b92c-d030d54ec4d4","resolution":{"observed_at":"2026-08-06T15:32:02.914403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:02.714556Z","title":"RTMobile: Beyond real-time mobile acceleration of rnns for speech recognition,","venue":null,"work_id":"63ac963d-d34f-4371-b0bc-bdc14185c04d","year":2020},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.885877Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:a2d8862e7b4b9f11699ad77660096ed5086a9fc9e00469862e91004efc63f5a4","observation_id":"b15dc78e-0502-45cf-ba52-cdc174acc5a1","resolution":{"observed_at":"2026-08-06T15:32:02.752204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:02.566914Z","title":"3D point cloud network pruning: When some weights do not matter,","venue":null,"work_id":"d3d0073b-1269-4a88-be3f-69900a2bc88a","year":2024},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:00.926767Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:4b0110d51a848989f312de2cf723fc606014c8c534b4354487ceb3abc9bf4a4c","observation_id":"bb244ace-bc73-4883-816f-d8dcf90d2c0e","resolution":{"observed_at":"2026-08-06T15:32:02.642026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:01.035139Z","title":"Deepfake video detection: challenges and opportunities,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.035139Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:2b3b246b3e792362f802cf46b68520562519bbbda70c9b3cf0e3e414f1fcf850","observation_id":"38b89041-da95-476e-a667-b95708aef026","resolution":{"observed_at":"2026-08-06T15:32:01.035139Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.05248","last_updated":"2021-09-06T00:47:17Z","snapshot_observed_at":"2026-08-09T18:57:58.186285Z","submitted_at":"2019-11-13T02:02:19Z","title":"What Do Compressed Deep Neural Networks Forget?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.05248","snapshot_observed_at":"2026-08-06T15:32:01.096012Z","title":"What do compressed deep neural networks forget?","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.096012Z"},"links":{"cited_paper":"/paper/1911.05248","citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:08ac89941f3fd820048820fa6d3876b52c4eee965172a1b1f8a1dc3c6040f619","observation_id":"771deed6-1eea-4371-abac-05632ab067b9","resolution":{"observed_at":"2026-08-06T15:32:01.096012Z","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":"2026-08-06T15:32:02.462176Z","title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":"0fc41cdb-6638-453e-aec9-af1fa71e13ee","year":2020},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.156634Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:17c4b30886380a2ed80bf8bde416f3dbda33ea82e406234d4fd0885a62bfc8c8","observation_id":"52fff454-fa17-4db3-95f3-e2c43f51f90e","resolution":{"observed_at":"2026-08-06T15:32:02.520512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:02.344883Z","title":"Adaptive knowledge dis- tillation for classification of hand images using explainable vision transformers,","venue":null,"work_id":"579644c6-ec9e-4960-8fd3-73567cb9fb33","year":2024},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.277744Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:2598c0863a245b49d30fb8e8e3e89d617ba503e9857971ef9dfbd428420b7828","observation_id":"c35e836d-41d1-472d-a745-c801438f01ed","resolution":{"observed_at":"2026-08-06T15:32:02.376314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:02.199234Z","title":"Celeb-DF: A large- scale challenging dataset for deepfake forensics,","venue":null,"work_id":"7b6f3c6c-8b2e-48f6-8f17-20e2716751a4","year":2020},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.313602Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:8f49f680a27ca49bcaf92fd7199e38c3cd98ca7973426a9badcf4e898c0bfe50","observation_id":"70209da8-d5c3-4b37-9ced-843daadd75ab","resolution":{"observed_at":"2026-08-06T15:32:02.266253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.01611","last_updated":"2020-07-20T16:50:33Z","snapshot_observed_at":"2026-08-04T07:40:59.947811Z","submitted_at":"2019-03-05T00:52:12Z","title":"Stabilizing the Lottery Ticket Hypothesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.01611","snapshot_observed_at":"2026-08-06T15:32:01.367340Z","title":"Stabilizing the lottery ticket hypothesis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.367340Z"},"links":{"cited_paper":"/paper/1903.01611","citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:91e23540c47439b5a8682bc1d193d11f2fc0fc9a925767e0a79cd744b153759d","observation_id":"a8d75596-d751-45bb-9b7c-b689c9dbaa99","resolution":{"observed_at":"2026-08-06T15:32:01.367340Z","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":"2026-08-06T15:32:02.086299Z","title":"Coarsening the granularity: Towards structurally sparse lottery tickets,","venue":null,"work_id":"3942e891-aaba-40c6-936f-43814c958887","year":2022},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.453994Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:1fd3c03a7ea0b56a494c6bab0f232ad3c24c89614d56e1deeed86378a167bdb0","observation_id":"88ff770c-9ecf-4b04-8555-444ac7af7d97","resolution":{"observed_at":"2026-08-06T15:32:02.162514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02340","last_updated":"2019-02-23T07:45:29Z","snapshot_observed_at":"2026-07-06T07:06:10.289386Z","submitted_at":"2018-10-04T17:39:58Z","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02340","snapshot_observed_at":"2026-08-06T15:32:01.547904Z","title":"SNIP: Single-shot network pruning based on connection sensitivity,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.547904Z"},"links":{"cited_paper":"/paper/1810.02340","citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:e3e4a0bced1988905c2946c8d8c8ebd5856de51517914c790ba46663fde7c75b","observation_id":"970327b6-55cf-4069-acbc-0b3116206d9d","resolution":{"observed_at":"2026-08-06T15:32:01.547904Z","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":"2026-08-06T15:32:01.962897Z","title":"Picking winning tickets before training by preserving gradient flow,","venue":null,"work_id":"cc81694d-5a4a-4db6-b043-14aee53fea81","year":2020},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.584605Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:aa37048c4fe77e8438ea4f91a4d734980f624675f54e7be5c758ef7a31a4c329","observation_id":"ba5f4a3b-cf98-4f4c-89be-0a37fcf2642a","resolution":{"observed_at":"2026-08-06T15:32:02.011067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:32:01.819096Z","title":"Shallowing deep networks: Layer-wise pruning based on feature representations,","venue":null,"work_id":"bd70c610-2cf8-4cd5-b8fb-63ae99a02a41","year":2019},"citing_paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T15:32:01.601958Z"},"links":{"citing_paper":"/paper/2507.15636"},"observation_digest":"sha256:abe950b5c323051946b5dba5fa6550f2b7a92d5720698cbe6ca187389e3a2627","observation_id":"c2fc86e9-9f9a-49aa-b21d-b8900aee8b14","resolution":{"observed_at":"2026-08-06T15:32:01.874450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.15636","last_updated":"2025-07-21T13:58:24Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T18:19:49.953174Z","submitted_at":"2025-07-21T13:58:24Z","title":"Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":23},"total_outbound_references":29},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2507.15636."}