{"as_of":"2026-08-07T18:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c441d387021bede46aeabb3122c584339b63d51b755d8430a43af38dde32a8cb","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T11:46:33.518128Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2607.26641/citation-record","integrity":"/paper/2607.26641/integrity","json":"/paper/2607.26641/citation-record.json","paper":"/paper/2607.26641"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T11:46:31.987799Z","title":"Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:31.987799Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:956243283b6521f7f69e23ba7ce4efedb92c182e4650da9582822d28070166ed","observation_id":"9fdb5675-95d8-45c5-af46-a50119342047","resolution":{"observed_at":"2026-08-01T11:46:31.987799Z","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":"2026-08-01T11:46:32.106658Z","title":"Deepfakes and Beyond: A Survey of Face Manip- ulation and Fake Detection,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.106658Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:07000388841d4b53f699906e16929debf9759c63255a1e565ef39efdd26fece5","observation_id":"44a73a97-949e-4520-a816-af6c9e3849a0","resolution":{"observed_at":"2026-08-01T11:46:32.106658Z","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":"2026-08-01T11:46:32.176634Z","title":"Face Morphing Attack Generation and Detection: A Comprehensive Survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.176634Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:35d9608d32c0a11efa9874036ebb391032c8b8a80733e396712eea7b9b7b08a9","observation_id":"f22b400d-3dc9-4778-af37-b0b50b5119fc","resolution":{"observed_at":"2026-08-01T11:46:32.176634Z","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":"2026-08-01T11:46:32.232510Z","title":"Character-Aware Models Improve Visual Text Rendering,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.232510Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:5928b0a611b366cede780e83648089c43665ca3ee3e9d98f774eecdfa5f4bf92","observation_id":"afb0211d-f92f-4fc5-a197-ee7b263c1287","resolution":{"observed_at":"2026-08-01T11:46:32.232510Z","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":"2026-08-01T11:46:32.295758Z","title":"Focus on Finding Deepfakes: A Robust Proactive Detection Method Based on Orthogonal Moment Watermarking,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.295758Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:decfc29f3227a51f2ddc9576fc3ff2a430780540efb3843be8a847fbe526f520","observation_id":"1a080d34-c5b3-40ae-823a-b9d7e3d31bd4","resolution":{"observed_at":"2026-08-01T11:46:32.295758Z","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":"2026-08-01T11:46:32.413280Z","title":"Toward Generalizable Forgery Detection and Reasoning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.413280Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:b34d16da463f87252b26051e940e21763c447b9bf6ceb6a188fde29bd9de142a","observation_id":"aae7d5e1-364b-4e7f-891a-6f83a5d05993","resolution":{"observed_at":"2026-08-01T11:46:32.413280Z","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":"2026-08-01T11:46:32.529449Z","title":"Unsupervised Domain Adaptation-Based Cross-Type Deepfake Image Detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.529449Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:39f090a1d1faff3e04df06d081e4620755a5cc2827e3d20663db763a4a01bfa7","observation_id":"e3e0e484-bbc6-4229-967d-fe2565809d0b","resolution":{"observed_at":"2026-08-01T11:46:32.529449Z","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":"2026-08-01T11:46:32.599275Z","title":"FantasyID: A Dataset for Detecting Digital Manipulations in ID-Documents,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.599275Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:d50b5b6458303fad8b4c62e8dee894aad1f284474eaaa926dba5d4fbdfec4dce","observation_id":"8f470b5d-e1aa-43da-b7bc-f794c0b286f2","resolution":{"observed_at":"2026-08-01T11:46:32.599275Z","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":"2026-08-01T11:46:32.645184Z","title":"DeepID Challenge of Detecting Synthetic Manipulations in ID Documents,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.645184Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:758539b1c043bf41d79b770f20b35a4ef67981f3c42d68eed6676a03fb3ed0af","observation_id":"42015388-3593-4bab-bb87-7c0f971ba07f","resolution":{"observed_at":"2026-08-01T11:46:32.645184Z","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":"2026-08-01T11:46:32.705564Z","title":"Second Competition on Presentation Attack Detection on ID Card,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.705564Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:91c6d7a9b24720537320d2826b093afe91035c99b516fde310b5484e66740b97","observation_id":"02397a8e-dffb-40cc-8edf-8cfe9c972d17","resolution":{"observed_at":"2026-08-01T11:46:32.705564Z","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":"2026-08-01T11:46:32.775290Z","title":"FakeIDet: Exploring Patches for Privacy- Preserving Fake ID Detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.775290Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:4a891a4630b4798b797d0bb543766a05e3fe22feadf0e16445ec0fe5da1cee59","observation_id":"44fc91be-1c46-4d40-b661-369c9d1e0ecb","resolution":{"observed_at":"2026-08-01T11:46:32.775290Z","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":"2026-08-01T11:46:32.845583Z","title":"Privacy-Aware Detection of Fake Identity Documents: Method- ology, Benchmark, and Improved Algorithms (FakeIDet2),","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.845583Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:f1a80ce72c4095b086fc558a175ad41d805f33951651f40f5a8bc0459cc096f8","observation_id":"214296d8-191a-416d-bbce-5937ad17d3d1","resolution":{"observed_at":"2026-08-01T11:46:32.845583Z","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":"2026-08-01T11:46:32.870472Z","title":"Data Balancing Method for Training Segmentation Neural Networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.870472Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:6d4d5184934877f5c321df715f72f489ab7ab4641cc8a1ebc40c3a652da7c42d","observation_id":"479b45fe-cbcb-4ee8-be92-6d0a183e56db","resolution":{"observed_at":"2026-08-01T11:46:32.870472Z","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":"2026-08-01T11:46:32.939937Z","title":"KID34K: A Dataset for Online Identity Card Fraud Detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.939937Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:0c1268e2630d1e1d65cecc2ac1e180861714b8c69de882db4f1e21830ca03462","observation_id":"9bbfb5b5-e1d1-4cc4-ad90-d93079ba452f","resolution":{"observed_at":"2026-08-01T11:46:32.939937Z","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":"2026-08-01T11:46:32.973916Z","title":"MIDV-2019: Challenges of the Modern Mobile-Based Document OCR,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:32.973916Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:351172259ac5260c9f53f18cc375e640897f526e9161b2ad00b692a90d2176f8","observation_id":"923239b8-0ddc-4003-8271-15e7ff46e131","resolution":{"observed_at":"2026-08-01T11:46:32.973916Z","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":"2026-08-01T11:46:33.090086Z","title":"MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.090086Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:7e477d329b27d00f5e8152c87d4b5abc1faa331cc090fd5587693287829497fd","observation_id":"1af42bb8-9df9-48e5-8a4e-b4c3b2897ea0","resolution":{"observed_at":"2026-08-01T11:46:33.090086Z","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":"2026-08-01T11:46:33.160510Z","title":"MIDV-500: A Dataset for Identity Document Analysis and Recognition on Mobile Devices in Video Stream,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.160510Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:d4a18714c45b7458f64f5bdc6fe0407a3f3778710dac8d7839ae41a64c12505f","observation_id":"5b82c521-6cfd-4d2d-885f-1659e2f216e0","resolution":{"observed_at":"2026-08-01T11:46:33.160510Z","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":"2026-08-01T11:46:33.229894Z","title":"Document Liveness Challenge Dataset (DLC- 2021),","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.229894Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:57ab7cbf299a93b08789f05da8797b4b7173932b9d05c3236e4286ca225c13e7","observation_id":"94ccdb9d-796f-41d4-904e-486be2007855","resolution":{"observed_at":"2026-08-01T11:46:33.229894Z","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":"2026-08-01T11:46:33.299896Z","title":"IDNet: A Novel Identity Document Dataset via Few- Shot and Quality-Driven Synthetic Data Generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.299896Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:3cf71dc34309711238c60d689e74bd7a5889660b2e188f2523d8b6d1ad453240","observation_id":"337ccf8f-2469-4920-a8dd-870cc1990203","resolution":{"observed_at":"2026-08-01T11:46:33.299896Z","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":"2026-08-01T11:46:33.397805Z","title":"Detecting Presentation Attacks on ID Cards Using Feature Refinement,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.397805Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:5b6148f858653ef20004b57cb975de69fca80edc52bdc3e99cd520f4f8026b26","observation_id":"85c41ebb-4000-4e54-98e3-dad8435aced1","resolution":{"observed_at":"2026-08-01T11:46:33.397805Z","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":"2026-08-01T11:46:33.423474Z","title":"Synthetic ID Card Image Generation for Improv- ing Presentation Attack Detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.423474Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:7491a4d76ec53e88ab725dac5fc70b2b328ab938d252ef05795cb7cad94013db","observation_id":"2d45795b-d8c1-4dfa-bdbc-3343390e35f6","resolution":{"observed_at":"2026-08-01T11:46:33.423474Z","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":"2026-08-01T11:46:33.427149Z","title":"PatchMatch: A Randomized Correspondence Algo- rithm for Structural Image Editing,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.427149Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:bcf4e12eb83cb60f767b853c26ebdf3b704159ad26bd34cd58e81bafe9815efb","observation_id":"20916bd1-8dc8-45f1-a82c-c73de78d008c","resolution":{"observed_at":"2026-08-01T11:46:33.427149Z","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":"2026-08-01T11:46:33.430564Z","title":"Scaling In-Context Segmentation with Hierarchical Supervision,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.430564Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:9a9490d997770860e1cd4bc79bd49206cc57fb7912209cfad2191a00fd7f9989","observation_id":"34fa796a-82c4-47eb-8bf1-70b87c911f06","resolution":{"observed_at":"2026-08-01T11:46:33.430564Z","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":"2026-08-01T11:46:33.433875Z","title":"Image forgery detection,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.433875Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:735c7a62a87926ed3d1296edbd92c8719537611183ca59c130d23c2ece545071","observation_id":"010dd3c8-0a0b-45bc-a233-33e78fb62aa1","resolution":{"observed_at":"2026-08-01T11:46:33.433875Z","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":"2026-08-01T11:46:33.437173Z","title":"Diffusion Models in Vision: A Survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.437173Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:e4bbe0d745000df1f9e4908b20dd3b3c7ad5e508e2ed22fe3022ff1abfd75f17","observation_id":"93065ee5-8f71-4125-9b11-a3c0bb61236e","resolution":{"observed_at":"2026-08-01T11:46:33.437173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05568","last_updated":"2023-04-12T02:08:34Z","snapshot_observed_at":"2026-08-05T11:31:30.187976Z","submitted_at":"2023-04-12T02:08:34Z","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05568","snapshot_observed_at":"2026-08-01T11:46:33.440645Z","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.440645Z"},"links":{"cited_paper":"/paper/2304.05568","citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:466f95faaa0f50fa45885156085177938dce7432c20c00f958f3fa52b45af364","observation_id":"dc1c1152-a5eb-472b-accb-14601bfabf6e","resolution":{"observed_at":"2026-08-01T11:46:33.440645Z","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":"2026-08-01T11:46:33.444245Z","title":"UDiffText: A Unified Framework for High-Quality Text Synthesis in Arbitrary Images via Character-Aware Diffusion Models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.444245Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:18acd952a1907256b40f75644ecc2bbe4ea99a2d7673c4b118993dea6d374442","observation_id":"70bcd0da-cd05-4bf9-80b2-ce439b885eec","resolution":{"observed_at":"2026-08-01T11:46:33.444245Z","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":"2026-08-01T11:46:33.447648Z","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.447648Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:fdc6b2d3109a454b5556cbf4b49cc3bc8d3683777d6ea01eef20af1b90598d3a","observation_id":"476e7292-1017-471a-996d-ae07b5650353","resolution":{"observed_at":"2026-08-01T11:46:33.447648Z","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":"2026-08-01T11:46:33.450835Z","title":"Recognition-Synergistic Scene Text Editing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.450835Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:1733616866efc93512486a388bb70ab080a83eea6b4856691083219895c5f44c","observation_id":"efb92b59-d88e-4160-8485-67c4d0235875","resolution":{"observed_at":"2026-08-01T11:46:33.450835Z","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":"2026-08-01T11:46:33.454309Z","title":"DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.454309Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:f6a18e5b0e5e8fb2208b095d6f741393e761605f7db4662bdaa7b46a6aee05d0","observation_id":"32b75655-5f43-465e-9d1d-ff44e4e9a87c","resolution":{"observed_at":"2026-08-01T11:46:33.454309Z","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":"2026-08-01T11:46:33.457656Z","title":"FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.457656Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:37871de3bcdcfd1e1e4e4db8cda85b674eb1b8e7e7d82ff8352b767b53d33311","observation_id":"648a6d5f-d1f2-431f-a09d-46505cb582ae","resolution":{"observed_at":"2026-08-01T11:46:33.457656Z","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":"2026-08-01T11:46:33.460851Z","title":"Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.460851Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:c73c1391e544c3221efc6af787bcd171a6cd437493e765d6b7adaa7e096415e2","observation_id":"7523f959-e46e-430a-9a85-15f467e37636","resolution":{"observed_at":"2026-08-01T11:46:33.460851Z","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":"2026-08-01T11:46:33.464174Z","title":"A Review on Generative Adversarial Networks: Al- gorithms, Theory, and Applications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.464174Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:ba9573260c8f9571f560b95b9b3be329370ca2891161e8918181278469a67b85","observation_id":"4007a6ca-f220-4eb7-b838-d6eeb01c75f1","resolution":{"observed_at":"2026-08-01T11:46:33.464174Z","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":"2026-08-01T11:46:33.467587Z","title":"FaceDancer: Pose- and Occlusion-Aware High Fi- delity Face Swapping,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.467587Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:cfbdcae88afc93f8bfb816c483d92d1f0f970f0e76b1060f7b92ee2819e41632","observation_id":"f38b613b-ae51-4ea3-84e6-873e0e238223","resolution":{"observed_at":"2026-08-01T11:46:33.467587Z","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":"2026-08-01T11:46:33.471039Z","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.471039Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:2263f821dd0babf629447b15b43a94ed81510a5de4961f77dd0bcffacee240ca","observation_id":"713f7718-cbd6-4a9f-941d-9337be437889","resolution":{"observed_at":"2026-08-01T11:46:33.471039Z","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":"2026-08-01T11:46:33.474460Z","title":"CNN-Generated Images Are Surprisingly Easy to Spot... for Now,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.474460Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:d3981acd110fc966c747f0a0534a2f6c207166605843259ce5b968a3eb49cc6c","observation_id":"73dd17b1-1330-48b0-ba70-5a4e505ff340","resolution":{"observed_at":"2026-08-01T11:46:33.474460Z","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":"2026-08-01T11:46:33.477878Z","title":"Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.477878Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:100f54bf6abc56aafa0077559863f1b85eefd843ff9a6b15424bc54b4e0fe0a3","observation_id":"fdf7b642-0210-4812-be6a-65ab17dc2b36","resolution":{"observed_at":"2026-08-01T11:46:33.477878Z","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":"2026-08-01T11:46:33.481245Z","title":"GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.481245Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:e1357574b334de1a3f135131396c249f119fe381d6cfb001b2537880db94edaa","observation_id":"f0733014-7a03-47a4-8cc3-f86efa357143","resolution":{"observed_at":"2026-08-01T11:46:33.481245Z","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":"2026-08-01T11:46:33.484569Z","title":"Hi-SAM: Marrying Segment Anything Model for Hier- archical Text Segmentation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.484569Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:2ae70bc192325b3d5875f423baeab011fe19f7effdfe817d04a863ac4daaa3ba","observation_id":"e9e3637a-aef9-48cf-ba8f-f00fa1d52f3b","resolution":{"observed_at":"2026-08-01T11:46:33.484569Z","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":"2026-08-01T11:46:33.487962Z","title":"SAM 2: Segment anything in images and videos,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.487962Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:9b51153aa3f1476e7d5d685fc31aae487d256b7e37154bd3f081c76a83aff2ef","observation_id":"f2a2392e-0f4b-4f48-a0d5-1f83ab4ead1a","resolution":{"observed_at":"2026-08-01T11:46:33.487962Z","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":"2026-08-01T11:46:33.491253Z","title":"Learning Patch-Channel Correspondence for Interpretable Face Forgery Detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.491253Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:467047236ad1c8dc6e32280ae39d0fcb407d8b6f553dc869daca4131290aad59","observation_id":"9d667984-ca46-4dfc-9f9a-3c7fd31fe9dd","resolution":{"observed_at":"2026-08-01T11:46:33.491253Z","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":"2026-08-01T11:46:33.494648Z","title":"What Makes Fake Images Detectable? Understanding Properties that Generalize,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.494648Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:de6e3f3a3fa8a0c30dc396878b224893cbc59c7c8125856d02abf51e37aa5fab","observation_id":"f2c1eb7c-91e8-4141-a772-4341f51e854a","resolution":{"observed_at":"2026-08-01T11:46:33.494648Z","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":"2026-08-01T11:46:33.498250Z","title":"Sequential Operations in Digital Picture Processing,","venue":null,"work_id":null,"year":1966},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.498250Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:039bf0511287d1baba5bff9e21821cee20e9a2b078be222fb80f6fb9fd0d50cd","observation_id":"86d0cd43-57e3-47a1-8eca-8eb02c5fc0ea","resolution":{"observed_at":"2026-08-01T11:46:33.498250Z","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":"2026-08-01T11:46:33.501479Z","title":"Distance Functions on Digital Pictures,","venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.501479Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:c86948db5fd9b91e65a0589e6089347361ef5cd42e60e41f7c78c3064473a667","observation_id":"02094057-a755-47d8-be59-8dd1a811182e","resolution":{"observed_at":"2026-08-01T11:46:33.501479Z","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":"2026-08-01T11:46:33.504960Z","title":"First Competition on Presentation Attack Detection on ID Card,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.504960Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:52b3ca6973dce1ef23d0da540f2659cde1348d34220f968accbf0e421a8e5b3d","observation_id":"80b687ca-639a-412d-b570-b0a130ee8438","resolution":{"observed_at":"2026-08-01T11:46:33.504960Z","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":"2026-08-01T11:46:33.508401Z","title":"TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.508401Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:96c9b8ab7793f3784189d7d71479c55ab46bbd6e1a86dde76c55c271304045e5","observation_id":"d8f97718-6e1e-4cae-9782-aca286ea0fd0","resolution":{"observed_at":"2026-08-01T11:46:33.508401Z","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":"2026-08-01T11:46:33.511529Z","title":"DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.511529Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:e63e8d49df66eeb4eb0c149e6d098ee9a82cc81ca3b6798f70b57cf0d6bd8262","observation_id":"44c373c8-d8be-44c5-bef5-b7540af59d08","resolution":{"observed_at":"2026-08-01T11:46:33.511529Z","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":"2026-08-01T11:46:33.514668Z","title":"Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.514668Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:36cd874182716cd6f5692177c83f6740471b408142b4356426538444fdb05d32","observation_id":"1b098ec5-ea3a-43a5-9ca6-07ff21b1c9cc","resolution":{"observed_at":"2026-08-01T11:46:33.514668Z","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":"2026-08-01T11:46:33.518128Z","title":"Can We Get Rid of Handcrafted Feature Extractors? Spar- seViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization Through Spare-Coding Transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T11:46:33.518128Z"},"links":{"citing_paper":"/paper/2607.26641"},"observation_digest":"sha256:f5d84f8cff8ac8a7a9adf8831dcc394b12d252151881afeab44fe94512d17b8b","observation_id":"e63ca685-8cb1-42f9-9f67-876307a90660","resolution":{"observed_at":"2026-08-01T11:46:33.518128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.26641","last_updated":"2026-07-29T09:03:29Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T08:25:36.625302Z","submitted_at":"2026-07-29T09:03:29Z","title":"FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":49,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":49},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2607.26641."}