{"as_of":"2026-08-21T10:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c4e4af55ac04c24b628c55e64b1371b236a2f7056bfacd68ee1f69e65bb702fb","coverage":[{"denominator":78,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":78,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T07:59:44.436264Z","state":"measured"},{"denominator":79,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":79,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-30T11:00:38.755973Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.30062","snapshot_observed_at":"2026-07-30T11:00:38.755973Z","title":"Fakevlm-r1: Internalizing physical laws via cot for synthetic image detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.27113","last_updated":"2026-07-29T16:43:59Z","snapshot_observed_at":"2026-08-18T17:08:04.319885Z","submitted_at":"2026-07-29T16:43:59Z","title":"Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-30T11:00:38.755973Z"},"links":{"cited_paper":"/paper/2605.30062","citing_paper":"/paper/2607.27113"},"observation_digest":"sha256:d0e868a1625db3f24be5ee49351dd363f247593a9ee944503de0456da25cd22a","observation_id":"301d7eb9-935f-4efb-bb75-6077fab37fad","resolution":{"observed_at":"2026-07-30T11:00:38.755973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.30062/citation-record","integrity":"/paper/2605.30062/integrity","json":"/paper/2605.30062/citation-record.json","paper":"/paper/2605.30062"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T07:59:44.436264Z","title":"Generative adversarial nets,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:609b8e9ca01fc53fe57fa6e0b08e65db03df6dc4d3f7b1e382da64837deef7b4","observation_id":"90cb1b5c-2f61-4c11-ade8-06535f65176c","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11239","last_updated":"2020-12-16T21:15:05Z","snapshot_observed_at":"2026-08-10T05:21:27.485481Z","submitted_at":"2020-06-19T17:24:44Z","title":"Denoising Diffusion Probabilistic Models","version":2},"cited_work":{"arxiv_id":"2006.11239","doi":"10.48550/arxiv.2006.11239","metadata_source":"pith","pith_arxiv_id":"2006.11239","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Denoising Diffusion Probabilistic Models","venue":"cs.LG","work_id":"dc023f4e-7c79-471c-b713-deeb559ba010","year":2020},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2006.11239","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:627c4ccaac8d9e117e547abd732eb58067f78e90e61ce02e37ad6433645da270","observation_id":"f4334d7c-03a4-4fe0-a9fe-1e2e3491893d","resolution":{"observed_at":"2026-06-29T08:03:14.170047Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-07-13T15:50:06.511104+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T15:50:06.511104+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Improving image generation with better captions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:b00e66d3db5c65aa92586a8720828c092ea5969d86c9b789846bcf2ba99e7584","observation_id":"7cd98e7a-7bad-4595-9fe6-342988dbf508","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Z-image: An efficient image generation foundation model with single-stream diffusion transformer,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:33928d8e399ad103fb71664e02839948e2ddf3cfdc99e59121f93fd5341790af","observation_id":"8155c72b-e2cc-4bb6-8665-2aac173ad74f","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.22699","last_updated":"2026-07-06T06:19:03Z","snapshot_observed_at":"2026-08-16T18:20:01.123890Z","submitted_at":"2025-11-27T18:52:07Z","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","version":5},"cited_work":{"arxiv_id":"2511.22699","doi":"10.48550/arxiv.2511.22699","metadata_source":"pith","pith_arxiv_id":"2511.22699","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","venue":"cs.CV","work_id":"f1080a62-48e1-4255-b023-7556be57370d","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2511.22699","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:f9721c3491bef5f6980c9c1b49a5e271785e7846e0405f726aa1429010a9149e","observation_id":"8fa55d78-00bc-496d-8704-a3ffb4032cf9","resolution":{"observed_at":"2026-06-29T08:03:14.172762Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-15T14:08:11.489191+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-15T14:08:11.489191+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Diffusion models beat gans on image synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:83ac064acaf740c715e6e345a6a41bfc1e54ae70fc88ab0ac3df3ab6614d48a8","observation_id":"c0365c7a-19fc-4ca1-b79b-01a888d2d7b0","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:c8f461c664a04407f4640020e4d2e24c1a5bc2e6a634652ec344c7fc47609570","observation_id":"b062e9cc-5e64-43da-b35c-1b98f6468ba8","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Diffusion models in vision: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:d93b6fe71763e959dba623053946a22df44b73740ba084d62e4e07f7dfca7620","observation_id":"fe47d8a1-993a-4662-bd80-d43f28af4c70","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2512.00473","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T13:29:50.878943Z","title":"Realgen: Photorealistic text- to-image generation via detector-guided rewards","venue":null,"work_id":"7ef1b26c-1276-46f7-92ac-3bfc13648f49","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:2fd67db40d13e3e9345975e8492ba58af8bfffddadcac27cc342c5c8941cf063","observation_id":"69afdfa5-cf3f-4b9b-a5b5-a0ad6696c6f0","resolution":{"observed_at":"2026-06-29T08:03:14.167299Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08772","last_updated":"2025-02-27T03:19:48Z","snapshot_observed_at":"2026-08-16T13:43:30.667941Z","submitted_at":"2024-06-13T03:04:28Z","title":"MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs","version":3},"cited_work":{"arxiv_id":"2406.08772","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.08772","snapshot_observed_at":"2026-07-04T17:29:59.904451Z","title":"Mmfakebench: A mixed-source mul- timodal misinformation detection benchmark for lvlms","venue":null,"work_id":"b05365d5-74b1-42e3-b009-d723fc339f5f","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2406.08772","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:4da926c821d2f734d334765ac6ccb254b4a507373d7767d56e7563c5f72ada74","observation_id":"d20fdc83-d91f-410e-9248-57b23476e84c","resolution":{"observed_at":"2026-06-29T08:03:14.164592Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Deepfakes: Deceptions, mitigations, and opportunities,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:73903a751d40bd4674b255cf59c83a053745e4a5b558287523ef16a26f5b5efe","observation_id":"2bd0ee09-c45e-4b27-9fa0-be919d7c4800","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Leveraging representations from intermediate encoder-blocks for synthetic image detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:c69eeda75243ff837d0ccb01cd610dc3a0e651181b0776e44235de2379df2740","observation_id":"62e0da64-24af-4736-8925-f43c3c43dcd3","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2509.25502","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T19:03:51.765929Z","title":"Seeing before reasoning: A unified frame- work for generalizable and explainable fake image detection","venue":null,"work_id":"1b229f92-7414-47aa-b917-94809c9a40f9","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:dcd1a162a53e08253a9680f76fc7c403848480ae0f8af2fa27a31809c86aa729","observation_id":"d335d59e-83c3-4a35-bde2-33cb48a7cbdc","resolution":{"observed_at":"2026-06-29T08:03:14.083841Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00979","last_updated":"2026-05-05T13:47:19Z","snapshot_observed_at":"2026-08-15T18:12:55.391464Z","submitted_at":"2025-06-01T12:20:22Z","title":"Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection","version":6},"cited_work":{"arxiv_id":"2506.00979","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.00979","snapshot_observed_at":"2026-07-01T22:56:20.973905Z","title":"Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection","venue":"cs.CV","work_id":"f28a8b39-972c-46e1-85e2-94c11302493e","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2506.00979","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:1b0beb93cfd454c7b4df5c95af4613381d907fc40b11200089ae5acc969434d8","observation_id":"764130cc-c9df-4b7c-a278-b194d35b679d","resolution":{"observed_at":"2026-06-29T08:03:14.092545Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.08423","last_updated":"2026-07-20T08:31:09Z","snapshot_observed_at":"2026-08-10T18:57:41.616541Z","submitted_at":"2025-11-11T16:33:49Z","title":"OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild","version":4},"cited_work":{"arxiv_id":"2511.08423","doi":null,"metadata_source":"pith","pith_arxiv_id":"2511.08423","snapshot_observed_at":"2026-07-09T03:05:55.359747Z","title":"OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild","venue":"cs.CV","work_id":"d7f5ad2c-8b98-4728-89b8-eb1bfc5131ca","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2511.08423","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:7ee8c76c6f08461dadfc713cec4165a343043af729c44efe83a45143b2acc5b1","observation_id":"09129206-9d1b-40e5-8b81-726fbd553db2","resolution":{"observed_at":"2026-06-29T08:03:14.111793Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Forgerynet: A versatile benchmark for comprehensive forgery analysis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:1aa414d689fcce953f1b3665630b1f187df50098065e47f94bc8be5e970e68c1","observation_id":"14e610bd-63b2-483b-b5bf-811c3cc02405","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Genimage: A million-scale benchmark for detecting ai- generated image,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:17feac07c0245df261dce43324b894e1878f38be706af3aacad12fe0daf6ea71","observation_id":"1d6f4a5a-d33a-44f2-96ba-39ff1a8f37ef","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Drct: Diffusion reconstruction contrastive training towards universal detection of diffusion generated images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:af7a6cb8a844ce4413b736b51a619d3a34ff61c987a40f7689ad7fa2860d6228","observation_id":"c28bbe51-0b24-42c7-a45a-733b271bbee9","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Wildfake: A large-scale and hierarchical dataset for ai-generated im- ages detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:22fe55101654013bbe2370ca4f0557fb45b8e8d066fc7df33d233f8b9689d304","observation_id":"a5aaa5d4-52ce-4b39-bb08-01660c19923f","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Frepgan: robust deepfake detection using frequency-level perturbations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:9f0f0c63c93f7eceec621dd06c09ebf4d29001ca95aedd5077f54b7ba6ac0b73","observation_id":"969170c7-79ed-4d11-9b72-5a95764cd372","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01123","last_updated":"2024-04-20T04:38:35Z","snapshot_observed_at":"2026-08-16T14:22:16.812375Z","submitted_at":"2024-02-02T03:50:45Z","title":"A Single Simple Patch is All You Need for AI-generated Image Detection","version":2},"cited_work":{"arxiv_id":"2402.01123","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.01123","snapshot_observed_at":"2026-07-01T22:16:15.829228Z","title":"A single simple patch is all you need for ai-generated im- age detection","venue":null,"work_id":"47bad58d-d846-4a0f-ac0b-85b00488ab9a","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2402.01123","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:a98564923bf2ff3188cfbf616bbe5ff1b3c04fb15651c7cddc8bf740d0c525d8","observation_id":"bf494dfb-b7fe-4bfc-84ee-c8e4ad750127","resolution":{"observed_at":"2026-06-29T08:03:14.118417Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.24267","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T08:03:14.148596Z","title":"Fakescope: Large multimodal expert model for transparent ai-generated image forensics","venue":null,"work_id":"681eb747-f747-483f-a675-c7782eb0a2d1","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:fab4f537f4f20f8cf1a852cad4a90076cc2c2abfd7006c98d43db4f4724ae4dc","observation_id":"ad597bb8-e11d-4235-ad69-cf64b26d5614","resolution":{"observed_at":"2026-06-29T08:03:14.150134Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Legion: Learning to ground and explain for synthetic image detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:0fbcb620bf3f4275f276eae97c9d360e4122da7e7211d96f63a432a155321d3f","observation_id":"5b502b2b-797a-4b71-a39c-cef04b56f3e5","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Can chatgpt detect deepfakes? a study of using multimodal large language models for media forensics,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:764710504eb1519a4117f0c2154f2449dfbe1ac3af47a141d0225af9d591ee85","observation_id":"e0619ebe-961a-4747-b9d3-4612b46d67d7","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09732","last_updated":"2025-04-21T02:36:09Z","snapshot_observed_at":"2026-08-19T13:47:20.286379Z","submitted_at":"2024-10-13T05:26:36Z","title":"LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models","version":2},"cited_work":{"arxiv_id":"2410.09732","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.09732","snapshot_observed_at":"2026-07-05T07:10:46.035138Z","title":"Loki: A comprehensive synthetic data de- tection benchmark using large multimodal models","venue":null,"work_id":"c9619c83-e779-496e-82c6-87e2c157a8cf","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2410.09732","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:71d09c601ae39e4d8e88f1f86665ae711d3f240bd82b670237352d5bcc186bfe","observation_id":"6099b895-e1b0-43ce-9129-36a22e311265","resolution":{"observed_at":"2026-06-29T08:03:14.161507Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Fakebench: Probing explainable fake image detection via large mul- timodal models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:258dc28a3af0564bbca7a6d0440be9dd6802a27872a7ee2259e4e32646804ba8","observation_id":"feeb5e46-1070-4f5b-b996-58985151555c","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06126","last_updated":"2025-05-29T03:20:42Z","snapshot_observed_at":"2026-08-16T13:11:27.340051Z","submitted_at":"2024-10-08T15:28:33Z","title":"X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection","version":4},"cited_work":{"arxiv_id":"2410.06126","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.06126","snapshot_observed_at":"2026-06-29T18:53:51.140867Z","title":"X2-dfd: A framework for explainable and extendable deepfake detection","venue":null,"work_id":"5393279a-a92b-400a-8e95-3539e24a207a","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2410.06126","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:0356052d11edb9827d54473a7cd493b578f011596f297a9a1d27854eeced87bb","observation_id":"4364bf9b-9111-49f5-8d41-72df3f4f8639","resolution":{"observed_at":"2026-06-29T08:03:14.134635Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Aigi-holmes: Towards explainable and generalizable ai-generated image detection via multimodal large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:051e053a0b8eb99cc0d1c9af9474ee774d7bdc5d71bf1b62eb2f386221e990aa","observation_id":"89a006a7-49af-477e-935f-31873bfcb361","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2503.14905","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-05T07:10:46.070613Z","title":"Spot the fake: Large multimodal model-based synthetic image detection with artifact explanation","venue":null,"work_id":"62e780c0-8673-4a26-af94-9e355e02cf58","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:5d8f0e7fe80660b9a0905d5550789c529b0a65874543bc44b3f335459d08b38e","observation_id":"2a756def-6d1e-4cf9-bafc-504d93f623ab","resolution":{"observed_at":"2026-06-29T08:03:14.132392Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17703","last_updated":"2025-03-29T15:21:55Z","snapshot_observed_at":"2026-08-16T12:58:20.378242Z","submitted_at":"2025-01-29T15:20:30Z","title":"Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate","version":4},"cited_work":{"arxiv_id":"2501.17703","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.17703","snapshot_observed_at":"2026-07-08T17:55:20.815322Z","title":"Critique fine-tuning: Learning to critique is more effective than learning to imitate.arXiv preprint arXiv:2501.17703, 2025b","venue":"cs.CL","work_id":"4d553c59-1475-446a-9584-d19f823ffa39","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2501.17703","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:b56663c39372d55a7e5054a52ff55942fa2747cdf6daa0a1aaf1336987f837b9","observation_id":"eb71130f-ce3b-4a68-b831-1d10a5fb60da","resolution":{"observed_at":"2026-06-29T08:03:14.132009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:6a42b8a6695ff7ff934ec97bd2df4df00b8be564dee2cbde4796fb909fb8907b","observation_id":"4242dd8e-c300-451e-b413-a591eeb46da1","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.09987","last_updated":"2025-08-13T17:59:28Z","snapshot_observed_at":"2026-08-19T18:52:45.346695Z","submitted_at":"2025-08-13T17:59:28Z","title":"Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation","version":1},"cited_work":{"arxiv_id":"2508.09987","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.09987","snapshot_observed_at":"2026-07-04T21:10:09.706550Z","title":"Echo-4o: Harnessing the power of gpt- 4o synthetic images for improved image generation","venue":null,"work_id":"03495384-0569-439e-a1d4-067ad2d077a1","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2508.09987","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:28505b82b1fbbe3c68876a54f3f1ab9868c6d6897e5cefb9e733846ddc3c9748","observation_id":"c0059742-8e6d-4142-a723-dbbc63bd864c","resolution":{"observed_at":"2026-06-29T08:03:14.105435Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02782","last_updated":"2025-05-02T04:42:06Z","snapshot_observed_at":"2026-08-19T08:04:06.044525Z","submitted_at":"2025-04-03T17:23:16Z","title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation","version":3},"cited_work":{"arxiv_id":"2504.02782","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.02782","snapshot_observed_at":"2026-07-05T11:41:02.715765Z","title":"Gpt-imgeval: A comprehen- sive benchmark for diagnosing gpt4o in image generation","venue":"cs.CV","work_id":"80b0a285-2676-4088-8aec-195dac7e8ceb","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2504.02782","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:ecc7fef08ee83021279ee6ece147024d2521aa94579bc80c66af13de7f488e9c","observation_id":"9473925c-7c64-4d67-91a0-00120a4efe12","resolution":{"observed_at":"2026-06-29T08:03:14.101035Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.01756","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T13:19:50.670368Z","title":"Mind-brush: Integrating agentic cognitive search and reasoning into image generation","venue":null,"work_id":"95f61c7f-3f8a-460d-bd3e-fd1de498ef4e","year":2026},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:1069fba1be6acbb6c602b8b8726562febd898247512a19fc45d153f55cf5cd08","observation_id":"7336c536-2a78-4aa9-9ac5-435b3ef3755d","resolution":{"observed_at":"2026-06-29T08:03:14.155844Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Cnn- generated images are surprisingly easy to spot... for now,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:eef5a27141655fe55bc8f5adc91dca74d47b08415a87d000c82c84b6af0b0043","observation_id":"8fccfff4-7ae0-41f8-b4be-852428e012ab","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Towards universal fake image detec- tors that generalize across generative models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:8240404ea39dca04c3ed541ace89f17f76fa8c6a886bfe2538ba53ed995fb542","observation_id":"88d487ce-f1e6-4d3d-bf0a-622ca525e1ba","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.00962","last_updated":"2023-11-02T03:09:37Z","snapshot_observed_at":"2026-08-16T14:46:40.721649Z","submitted_at":"2023-11-02T03:09:37Z","title":"Detecting Generated Images by Real Images Only","version":1},"cited_work":{"arxiv_id":"2311.00962","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.00962","snapshot_observed_at":"2026-06-29T08:03:14.089932Z","title":"Detecting generated images by real images only","venue":null,"work_id":"9fb72825-f886-4adc-be60-969e97a6cf13","year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2311.00962","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:c9fabf42d4db166e2815af22eedc077623bc0954990ba0c1a1cd2f5ddc59730e","observation_id":"254a7253-5384-4838-b7a4-7b86e47f80a3","resolution":{"observed_at":"2026-06-29T08:03:14.091558Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Generative adversarial networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:9434b4aa2429f28b18a45e05da79a5777ec11d7762953b24ea5998bc924d054f","observation_id":"30ab31bb-efd9-47da-bb8c-5bb24113383f","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12397","last_updated":"2024-03-07T14:26:32Z","snapshot_observed_at":"2026-08-16T14:41:35.850097Z","submitted_at":"2023-11-21T07:12:40Z","title":"PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection","version":3},"cited_work":{"arxiv_id":"2311.12397","doi":"10.48550/arxiv.2311.12397","metadata_source":"pith","pith_arxiv_id":"2311.12397","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Patchcraft: Exploring texture patch for efficient ai-generated image detection","venue":"cs.CV","work_id":"f5883221-d53f-4bba-94d4-bcc918a6f4e9","year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2311.12397","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:5a05ef2230614bae8dc78d19946ba00a420d882c52e1ee140466001b64dff07d","observation_id":"ee265c3a-23dd-4b1b-b5aa-129f425849e4","resolution":{"observed_at":"2026-06-29T08:03:14.110519Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Fakecatcher: Detection of synthetic portrait videos using biological signals,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:dc35f8cf092db8f87673a2f13a5fdef72a1ca17931295e245ca4af7f2843773a","observation_id":"b1ae7d38-cfd3-4d8c-9610-47ddfede2039","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Wavelet-packets for deepfake image analysis and detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:5222a3ba8466f3726422cb39a0002243069cfc2becd42d0fad9550ed36114faa","observation_id":"1ff3f7d2-081d-478e-bda2-1f1b75aa2728","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Rethinking the up- sampling operations in cnn-based generative network for generalizable deepfake detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:4c19c76669e996387bcf78cce7b589e7cbededf846d07c053bdb5a5a33115e57","observation_id":"cd8b8329-984c-45e1-831f-def4dd15ab7d","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Visual veracity: Advancing ai-generated image detection with convolutional neural networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:63976a2b088aade4a0f28305604c1b240079d666b3b4214458e85e7e01595404","observation_id":"e126eaa4-b37b-412b-8379-3906baad1f5c","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Compar- ative analyais of cnn architectures for deep fake detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:a5fbb782db165ddf2ac267202e49e2517c0a623c7366eee23ea30e6b1771a865","observation_id":"14368e87-3caf-4f53-8880-72ab4b3b8449","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Detec- tion of ai-generated synthetic images with a lightweight cnn,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:1f4e5bd093a9cf389485d66931a471cfeaf75e08cbb23815f0362bf9d56d7cd2","observation_id":"16db207d-c463-4560-9621-3fc5362f88f9","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Advancing ai-generated image detection: Enhanced accuracy through cnn and vision transformer models with explainable ai insights,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:5cc1a4b87d6c426b024d9e421d6220ccafe30349e2ca487c6558dddd7dead7f5","observation_id":"8ff2f72d-e201-4ced-b5cc-2e70920fb741","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17419","last_updated":"2024-08-21T07:42:02Z","snapshot_observed_at":"2026-08-18T02:00:01.519309Z","submitted_at":"2023-10-26T14:23:45Z","title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","version":3},"cited_work":{"arxiv_id":"2310.17419","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.17419","snapshot_observed_at":"2026-07-01T14:35:46.449691Z","title":"Antifakeprompt: Prompt- tuned vision-language models are fake image detectors","venue":null,"work_id":"eca729a0-30c6-48d7-8c34-03e336d90d07","year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2310.17419","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:f268d87d71c47abc994e3e40c90218c11e8378e234313b3b391a0d9895a91bd4","observation_id":"c49e502f-9ec7-4405-bafc-0728ddb6193c","resolution":{"observed_at":"2026-06-29T08:03:14.104112Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Fad-net: Fake images detection and generalization based on frequency domain transformation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:218049d6ba9788b723fe8c6a6f40c7d242e6247ec5c9d1266437b73733ab1869","observation_id":"cbf4c9bb-5928-4ee9-be40-641db7026547","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Frequency-aware deepfake detection: Improving generalizability through frequency space domain learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:8b001215b2202a3b39e97b77834926d6f7b944434863084179a4b8a3edabbe51","observation_id":"a44a0414-ff0f-4aa1-9671-1cd8623ed5b1","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Dynamic graph learning with content-guided spatial-frequency relation reasoning for deepfake detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:5666ffe47f0eb06ac517b896e6d8cd1cc2ea9c06b15210b343b5b8e652246f5c","observation_id":"c370916b-ced7-4e87-88b2-c5d240c5a7ea","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:442d078138048985e3b475e4055bdcf63d6f68427709af39ac5a769bfd0b6f13","observation_id":"c9947770-2873-468b-b82f-1b81b07a13fe","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Gemini 2.5 pro,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:2cb3deb04108d6213195235120ef6fa7dbbde9b1c48ef94ed226cd82eb954c38","observation_id":"0f98e4fa-0b67-4cef-866f-e518a02024e6","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Visual instruction tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:b5538e7f3c53492a21c39e3a4e3f5c7349854926fa98dcd68716313356b07e3b","observation_id":"b657680d-886f-461b-95f0-e9c75da18489","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-08-14T04:17:22.593941Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":"2502.13923","doi":"10.48550/arxiv.2502.13923","metadata_source":"pith","pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen2.5-VL Technical Report","venue":"cs.CV","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:e4d0c4f33536a94e540ec8eb255142ded393bf6f6f3535f331901828170f4b7c","observation_id":"c72acc55-2be5-4c34-a8b1-87a968bd6f5f","resolution":{"observed_at":"2026-06-29T08:03:14.147532Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-08T16:08:16.864468+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-08T16:08:16.864468+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.14181","last_updated":"2024-01-01T14:48:48Z","snapshot_observed_at":"2026-08-18T22:49:12.570713Z","submitted_at":"2023-09-25T14:43:43Z","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","version":3},"cited_work":{"arxiv_id":"2309.14181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.14181","snapshot_observed_at":"2026-06-30T13:34:40.544825Z","title":"Q-bench: A benchmark for general-purpose foundation models on low-level vision","venue":null,"work_id":"5cc0bbca-7cce-4f8c-bd9d-7b44a68d9062","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2309.14181","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:3caa7ec3b8d16322043eb5b2c878a600563c702d080703cc47001ccf78d017d3","observation_id":"47474e1b-89ee-4079-99a1-68f079ed7a45","resolution":{"observed_at":"2026-06-29T08:03:14.129255Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Why are visually-grounded language models bad at image classification?","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:cfb3e723aa0494fe231081f536bc7c2c1cffd6d43ed64dc9e121e301b30ca60e","observation_id":"fc759154-1dbc-46a4-b87c-d42f9cd33273","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02761","last_updated":"2025-04-12T08:08:04Z","snapshot_observed_at":"2026-08-20T00:58:27.664818Z","submitted_at":"2024-10-03T17:59:34Z","title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","version":4},"cited_work":{"arxiv_id":"2410.02761","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.02761","snapshot_observed_at":"2026-07-04T19:40:06.975646Z","title":"Fakeshield: Explainable image forgery detection and localization via multi-modal large language models","venue":null,"work_id":"e858234f-ab78-4d18-ba23-2a4627f60023","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2410.02761","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:8c3724a840aab4b2d094f774b58526e9e839879a6924438bb19b2b1294080ed1","observation_id":"748d961b-87e0-4c69-974c-ba8c66d45ca4","resolution":{"observed_at":"2026-06-29T08:03:14.077799Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Common sense reasoning for deepfake detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:b6cccf128ad6dafe1f32f8505640aa82fbb0975b6be860a8820bc9e37a359502","observation_id":"89d73619-3926-4d62-b88a-09f54201bab8","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10072","last_updated":"2024-11-21T14:37:25Z","snapshot_observed_at":"2026-08-16T13:25:29.450101Z","submitted_at":"2024-08-19T15:15:20Z","title":"FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant","version":2},"cited_work":{"arxiv_id":"2408.10072","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.10072","snapshot_observed_at":"2026-07-01T14:35:46.433831Z","title":"Ffaa: Multimodal large language model based explainable open-world face forgery analysis assistant","venue":null,"work_id":"d737582c-3a30-4101-a8ab-20899f36d87a","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2408.10072","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:89195c9c41006c14cadd6419765ac03964d92a37a5be1fa73c3452c710a263f3","observation_id":"2dc22535-7bcc-49b1-9692-36565716264a","resolution":{"observed_at":"2026-06-29T08:03:14.142644Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.14632","last_updated":"2026-06-15T21:10:39Z","snapshot_observed_at":"2026-08-19T22:01:02.194039Z","submitted_at":"2025-07-19T14:05:33Z","title":"BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM","version":4},"cited_work":{"arxiv_id":"2507.14632","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.14632","snapshot_observed_at":"2026-07-05T07:10:46.077762Z","title":"Busterx++: Towards unified cross-modal ai-generated content detection and explanation with mllm","venue":"cs.CV","work_id":"32b950ac-fdec-457d-a4cf-a52fac9f648a","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2507.14632","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:354e7dde133dc6d9f6b2180ba35b733b5ba5ac5e756731e52bef337810bd96b2","observation_id":"8f4c0406-e867-48aa-98bf-742f54babe6a","resolution":{"observed_at":"2026-06-29T08:03:14.120575Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.15693","last_updated":"2026-05-15T14:16:03Z","snapshot_observed_at":"2026-08-15T17:06:50.376155Z","submitted_at":"2025-12-17T18:48:26Z","title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","version":2},"cited_work":{"arxiv_id":"2512.15693","doi":null,"metadata_source":"pith","pith_arxiv_id":"2512.15693","snapshot_observed_at":"2026-07-01T13:55:45.231419Z","title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","venue":"cs.CV","work_id":"a14600d5-f852-4fcd-85a6-99df6b60325b","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2512.15693","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:b1d7f7db383a666457b48479cc11da6104d8295d3c58827884ff03baa8a34a36","observation_id":"f01430db-4270-4354-beba-f61a7e1697a8","resolution":{"observed_at":"2026-06-29T08:03:14.152909Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10238","last_updated":"2026-04-07T07:54:13Z","snapshot_observed_at":"2026-08-13T18:55:54.784748Z","submitted_at":"2024-10-14T07:56:51Z","title":"ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization","version":4},"cited_work":{"arxiv_id":"2410.10238","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.10238","snapshot_observed_at":"2026-07-05T07:10:46.062561Z","title":"ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization","venue":"cs.CV","work_id":"c6803fdd-49dd-4514-b255-3353f1c40f85","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2410.10238","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:9c286f4880d1892ff0b5af07bed42b037ba7476eda46ee7fe74316e7d5ce8865","observation_id":"e30b255b-4673-442b-aa7d-d7cd6f4b2d3a","resolution":{"observed_at":"2026-06-29T08:03:14.074457Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18660","last_updated":"2026-07-31T15:32:37Z","snapshot_observed_at":"2026-08-16T00:11:17.593628Z","submitted_at":"2025-05-24T11:53:35Z","title":"So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection","version":5},"cited_work":{"arxiv_id":"2505.18660","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18660","snapshot_observed_at":"2026-08-03T03:15:17.929242Z","title":"So-fake: Benchmarking and explain- ing social media image forgery detection","venue":null,"work_id":"fc6205cc-ee4b-4cc4-af94-3608fdb0514b","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2505.18660","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:00c72cca3d6db6a5bebc17abed493b973b9ead8369e8850c423e2fa3be718234","observation_id":"053141ef-af96-4d27-bba0-fb12c75fbb3f","resolution":{"observed_at":"2026-08-03T03:15:17.929242Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Sida: Social media image deepfake detection, localization and explanation with large multimodal model,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:062c1220590faae0605efebf28ad3efc8b157a954020b49ca5e9939dbb802ec2","observation_id":"d7f50cb7-cc2c-4666-8e35-2172f433ba72","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"10.1007/s11263-020-01316-z","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"International Journal of Computer Vision 128(7), 1956–1981 (Mar 2020)","venue":"International Journal of Computer Vision","work_id":"62ef6473-874f-4e95-8846-5210fe18eeab","year":1956},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:b17db9c02eb5419f854f38204e307915c1456912354ad85bcabfcf4dbe43b9bd","observation_id":"58cc4f53-35da-4001-bb63-1841114ba6c8","resolution":{"observed_at":"2026-06-29T08:03:13.656774Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-07-12T23:19:54.150959+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T23:19:54.150959+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Efficient memory management for large language model serving with pagedattention,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:42c7111f6b34350f9b862122bc2f93ac0f245c3ece764a01f2af6a323cc86b34","observation_id":"07e80e04-3bf5-4520-8956-af2b39382d46","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Sglang: Efficient execution of structured language model programs,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:f0e4d8ef6189ecaa5d14275da52277a7f6627de7e141805b2882d3830dd21d0a","observation_id":"09f13c35-e48f-46a0-8d69-c4ad3a33d1ea","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2501.12948","doi":"10.1016/j.artmed.2024.103001","metadata_source":"pith","pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","venue":"cs.CL","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:e18644de4ce12f208cb4515da77931ab8acb6dacc6de1d947d4d376d20c52da1","observation_id":"b2f514ee-081e-4b02-9e7b-cc5ce9af4656","resolution":{"observed_at":"2026-06-29T08:03:14.106857Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.17018","doi":"10.48550/arxiv.2505.17018","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Sophiavl-r1: Reinforcing mllms reasoning with thinking reward","venue":"ArXiv.org","work_id":"de003be6-a854-4f8d-84ec-4a852d8422c6","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:8c6522cacfceab7c293d30a23938594b1b0136f66f1d6fa2b404349ac319ddf2","observation_id":"3e59ff88-379e-45cd-afe2-0fa3ba4a3964","resolution":{"observed_at":"2026-06-29T08:03:14.126779Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"On the detection of synthetic images generated by diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:836f4b970a7ac9f67d3952f84f2203e1a6d78e5b3c21ac721af3d8448536e60f","observation_id":"147e8b69-828f-45fc-a50e-a244baabc5c1","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15633","last_updated":"2025-05-20T12:06:56Z","snapshot_observed_at":"2026-08-06T14:53:33.853203Z","submitted_at":"2024-11-23T19:10:32Z","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","version":4},"cited_work":{"arxiv_id":"2411.15633","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.15633","snapshot_observed_at":"2026-07-09T17:16:23.136828Z","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","venue":"cs.CV","work_id":"3ee10805-5d15-48ba-955d-528468dc1f6f","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2411.15633","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:267de894c7b9a252640ed60c69bb3ffcbab4cc152d367ced9cf7ca933cfeb641","observation_id":"24ebeb57-0bfd-4b92-9836-1ad66bc60da4","resolution":{"observed_at":"2026-06-29T08:03:14.109387Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19435","last_updated":"2025-02-15T16:01:36Z","snapshot_observed_at":"2026-08-18T14:59:59.053013Z","submitted_at":"2024-06-27T17:59:49Z","title":"A Sanity Check for AI-generated Image Detection","version":3},"cited_work":{"arxiv_id":"2406.19435","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.19435","snapshot_observed_at":"2026-07-08T12:04:50.442080Z","title":"A sanity check for ai-generated image detection","venue":"cs.CV","work_id":"8b1627f4-5434-49ca-9cf6-3496ae1c191d","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2406.19435","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:24113fa6bfbcfa1e11648f4c60d37efcc05c25770d8ce7e8708ac15ce8ff1a3f","observation_id":"a6c3b986-30a3-4631-be24-78698bdff06b","resolution":{"observed_at":"2026-06-29T08:03:14.145411Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Gpt-5 system card,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:f9d5e30b8ea24a2a5141e37037c62539ec4f99cc49469aa6c56a4435b454cc94","observation_id":"2ddfe369-9bf4-4fcb-9034-aa1cc11ed27c","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.10302","last_updated":"2024-12-13T17:37:48Z","snapshot_observed_at":"2026-08-07T03:01:29.031129Z","submitted_at":"2024-12-13T17:37:48Z","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","version":1},"cited_work":{"arxiv_id":"2412.10302","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.10302","snapshot_observed_at":"2026-07-10T13:27:05.559849Z","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","venue":"cs.CV","work_id":"0fa0432e-2510-462b-954d-436d3b669375","year":2024},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2412.10302","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:8d5bf5daa841202881b7ef3dd77e0edeca8ceb3fe2b446dd9e313650bc99dd8a","observation_id":"fc97621d-93ec-4a11-94fe-3e4627891ec3","resolution":{"observed_at":"2026-06-29T08:03:14.158918Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:bdd87dbf9b2ff8687723191a933b09e9446d732229718353e0baac2ae1020591","observation_id":"b2a2c78f-72ef-4087-8190-204561be5383","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10479","last_updated":"2025-04-19T03:47:21Z","snapshot_observed_at":"2026-08-17T09:56:52.502317Z","submitted_at":"2025-04-14T17:59:25Z","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","version":3},"cited_work":{"arxiv_id":"2504.10479","doi":"10.48550/arxiv.2504.10479","metadata_source":"pith","pith_arxiv_id":"2504.10479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","venue":"cs.CV","work_id":"fe8637aa-12bc-4434-8d36-9f57b5eebcbe","year":2025},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"cited_paper":"/paper/2504.10479","citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:912ac2adb4df4e98f8db5583aeffda7b942705928a9098cdf48983fd88c89ffb","observation_id":"1f6d22a9-6731-46d4-83b0-05335c15ee82","resolution":{"observed_at":"2026-06-29T08:03:14.117991Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-05-20T07:54:09.017512+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-20T07:54:09.017512+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T07:59:44.436264Z","title":"Global texture enhancement for fake face detection in the wild,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:3b7eb1048d4217db8db720cf65735bb01341bdfcff14f0eaa482d03430dae63d","observation_id":"c52195c7-0daf-41db-9893-90d9ade1d42f","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","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":"2026-06-29T07:59:44.436264Z","title":"Fusing global and local features for generalized ai-synthesized image detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-06-29T07:59:44.436264Z"},"links":{"citing_paper":"/paper/2605.30062"},"observation_digest":"sha256:d959022a2a629afd37dd88276640a7642f0c74d8d093c3ff0c0af364f299da4e","observation_id":"180f86e5-724b-4f31-a6b6-cdb1ecc1dbec","resolution":{"observed_at":"2026-06-29T07:59:44.436264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.30062","last_updated":"2026-05-28T15:13:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T09:23:03.040130Z","submitted_at":"2026-05-28T15:13:31Z","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection"},"reference_resolution":{"displayed":78,"state_counts":{"malformed_identifier":0,"metadata_mismatch":3,"parse_uncertain":0,"unresolved":44,"verified_exact":31,"verified_fuzzy":0},"total_outbound_references":78},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 1 inbound Pith citation observation for arXiv:2605.30062."}