{"as_of":"2026-08-08T16:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c23136ea4468d394550a735947cbab7163f70b87ca304eb0c1e9b71339115847","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":"2026-08-08T06:32:00.761636+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/2507.15636/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:ea4318dd29b16eb0d06f6511c1e45488e6cbabe5d6cc1fc6a04d8eb93e67266b","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:04.743239Z","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:fc8aa590022da6d2199d9be0ba13e8e47e7e04977c857f7bcd5af02cc8c3355f","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:04.630877Z","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":"sha256:0da82ec66ec677c8a0a137d60a69ab46f40660b40d21796af06a58c5f3a318c4","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:04.481868Z","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":"sha256:28267072a16b39a1b181f2539e45166d321ed47558728a72e961d7d2fcedb8d1","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:04.313994Z","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":"sha256:0e4575009a311ae29267d81a7821e45624e3623f3444c7b7cff761e9815b191e","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:04.161313Z","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:e678c1aa338a419c9fd71b21fb489be4b72f34bc9aa9f885f75501120bb3669e","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:04.032968Z","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":"sha256:0aedd846c26bbff70ecb3f93e59b3cc03a1fb407ce9a47acbf91fa3a92d7e780","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:03.914839Z","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:bb16cfdcdf6b9ab28198f3eb300633e29437e66e522e9de4560b8f74bfaf98fb","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:00.128614Z","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":"sha256:6d965deff462cb839d2cab51a1e578f7875dfbccdfd4d0b4dbf89dc0bf352c1d","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:03.579967Z","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:d9044e09cda20e1b2f190a66ffacf8ca34094447c79fdb39d6c2ad7a15ed7831","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:03.436979Z","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":"sha256:977bc4d8b7c85344576b51641c39cb5035a375ce786a0486603e27936964f03a","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:03.312346Z","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":"sha256:3d8acfb409b46e160269645f01ad0cc1d0baa68209bf61d6d07207f53da4ee26","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:03.122647Z","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":"sha256:6230063cc37cf322288ebce0618d936f52277d5dbf2a8f1810d3945b907067c2","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:02.954737Z","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":"sha256:05876e3dcae48c997a4a20e3987760eec18207d40f8ef03e570b41f648e54711","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:02.850519Z","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":"sha256:80a55f471deffe3116f7a1a2a4f35c39ba64e7df00187ff22ddf741e46618987","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:02.714556Z","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":"sha256:30aa95bcdfce668b41c6f38fc7ea85bb0f1eceb1286bc9e3006ebfb61115d206","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:02.566914Z","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":"sha256:7c599042f6c47761cc79dd47b06fa9a7dd64a90d05ae579e706b4540ba582471","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:01.035139Z","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":"2026-07-06T08:36:35.767733Z","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:c799fd2a83bca8d2270385655f906a2b92beb3a38cfc0fa1b9155e55e0cae0b2","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":"sha256:1607c1958f36fa7f4ca4a5a329af4134ef75123fd226713f80c326eb4a06b9ed","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:02.344883Z","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:be353ad312d57e2fe5ec3ec3ec85291ce6edc3426a045563b8a482537080ee2c","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:02.199234Z","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":"sha256:3d76f1d60f237117368167c7444a7939a90ab0efc6a7e4487c94bd5db70d3baa","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 2026-08-08T06:32:00.761636+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":"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":"sha256:248a3e3517d0e1c61e5312b4c044a8cc2482dc0f309f9a20190bc1d72588c89a","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 2026-08-08T06:32:00.761636+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":"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":"sha256:2fdaf3a24c02cc059ef3cc9d923d432f5bb5310ef222c596b78ae5b38a9222ca","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 2026-08-08T06:32:00.761636+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":"2026-08-06T15:32:01.819096Z","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":"sha256:5c8e64bcb6503a93cbb114ec5050835ee0c5f95564f25aeda273bf2f6fa18c6f","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 2026-08-08T06:32:00.761636+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"}}],"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":"2026-08-08T06:32:00.761636+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 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2507.15636."}