{"as_of":"2026-08-10T06:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4c8e5c229c5d911937eca696209960b7c8ce025f2554d627d4d21c26d77dcbe6","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T13:44:11.471857Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T01:04:35.510933Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-14T19:39:23.872435Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"cited_work":{"arxiv_id":"2509.25682","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.25682","snapshot_observed_at":"2026-07-01T02:17:17.017569Z","title":"Omnidfa: A unified framework for open set synthesis image detection and few-shot attribution","venue":null,"work_id":"b14a4c48-3690-470b-b355-3acd3e8cdca0","year":2025},"citing_paper":{"arxiv_id":"2605.12967","last_updated":"2026-05-13T04:01:10Z","snapshot_observed_at":"2026-08-02T17:48:26.431725Z","submitted_at":"2026-05-13T04:01:10Z","title":"ImageAttributionBench: How Far Are We from Generalizable Attribution?","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-14T19:38:41.659261Z"},"links":{"cited_paper":"/paper/2509.25682","citing_paper":"/paper/2605.12967"},"observation_digest":"sha256:90d70cf511bf003eb1764d72ecfc40af898c54b9fca1a4d10419333cfaacb214","observation_id":"7db0886d-ed1d-48c7-9ab6-d1135ec15d00","resolution":{"observed_at":"2026-07-01T02:17:17.017569Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.25682","snapshot_observed_at":"2026-08-01T01:04:35.510933Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25962","last_updated":"2026-07-28T16:45:52Z","snapshot_observed_at":"2026-08-06T09:14:07.805736Z","submitted_at":"2026-07-28T16:45:52Z","title":"LaP-Forensics: Latent-Pixel Consistency Guided Multimodal Reasoning for Deepfake Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T01:04:35.510933Z"},"links":{"cited_paper":"/paper/2509.25682","citing_paper":"/paper/2607.25962"},"observation_digest":"sha256:ca40f3688e45e8a3b6bf9e09e50a7ea3e88f25a64c88b3560a46e215ffd8528b","observation_id":"39832900-f1e8-4127-8989-d0a65bd415c4","resolution":{"observed_at":"2026-08-01T01:04:35.510933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.25682/citation-record","integrity":"/paper/2509.25682/integrity","json":"/paper/2509.25682/citation-record.json","paper":"/paper/2509.25682"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:07.613800Z","title":"Con- trasting deepfakes diffusion via contrastive learning and global-local similarities","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.613800Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:933355d5c78a3cc0b63f23168e66b4bb23b58673625612a1d77d35644309b921","observation_id":"7061cd69-7bbc-4ba7-aff1-af85139020bd","resolution":{"observed_at":"2026-08-04T13:44:07.613800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:07.718108Z","title":"Raising the bar of ai-generated image detection with CLIP","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.718108Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:96cb6a86371b016d936258c2c9ed3f9345859afc994a196a9970bf5ba93b8ba4","observation_id":"b008a3b2-2d86-4719-bcda-f951c4215679","resolution":{"observed_at":"2026-08-04T13:44:07.718108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.14683","last_updated":"2025-07-27T11:45:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T17:59:30Z","title":"Emerging Properties in Unified Multimodal Pretraining","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.14683","snapshot_observed_at":"2026-08-04T13:44:07.836898Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.836898Z"},"links":{"cited_paper":"/paper/2505.14683","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:56a3231912fffc92f35eb142ebc360de65e7205fa5d11c5f8ff324035f6694b3","observation_id":"29be766b-de08-4b29-89f1-28adc3fe4783","resolution":{"observed_at":"2026-08-04T13:44:07.836898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03206","last_updated":"2024-03-05T18:45:39Z","snapshot_observed_at":"2026-07-06T17:40:01.975792Z","submitted_at":"2024-03-05T18:45:39Z","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03206","snapshot_observed_at":"2026-08-04T13:44:07.934725Z","title":"Shengbang Fang, Tai D","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.934725Z"},"links":{"cited_paper":"/paper/2403.03206","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:07a513543cd2f9290cea88895c660617d4bf8d90f2fb8b8a5190644a481f77db","observation_id":"4ba9eb43-61fe-496f-9ac7-8e328c530e52","resolution":{"observed_at":"2026-08-04T13:44:07.934725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.21210","last_updated":"2026-04-07T08:34:05Z","snapshot_observed_at":"2026-07-06T20:59:27.162712Z","submitted_at":"2025-03-27T06:54:06Z","title":"Toward Generalizable Forgery Detection and Reasoning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.21210","snapshot_observed_at":"2026-08-04T13:44:08.050865Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.050865Z"},"links":{"cited_paper":"/paper/2503.21210","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:c6914c472de0e99adcef0f176d90c0f57614587dc026f8afda53ecd124d76f66","observation_id":"e3f05b50-55fd-4fb4-8d43-fd7f80b6b020","resolution":{"observed_at":"2026-08-04T13:44:08.050865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.181108Z","title":"Wukong: A 100 million large- scale chinese cross-modal pre-training benchmark","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.181108Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:0fda122e41b4a094df3fe7774858644479e57d6937ee335a33891fc3d4bd3342","observation_id":"10366f7e-3515-4185-b764-926262851966","resolution":{"observed_at":"2026-08-04T13:44:08.181108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.271257Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.271257Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:e407e3f49ee4c81c96b13d1736b24316b448c8bddf09eb44a50b1c570d060241","observation_id":"fc28b73c-c9e3-4409-bb99-b472223c86c7","resolution":{"observed_at":"2026-08-04T13:44:08.271257Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.365878Z","title":"Progressive growing of gans for im- proved quality, stability, and variation","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.365878Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:50d11e5548b2c2322521a4c78274541094ef1341184d79a28cf052eb3ef42e7d","observation_id":"9309ac86-1935-425b-97a2-f5caaa5c451a","resolution":{"observed_at":"2026-08-04T13:44:08.365878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08748","last_updated":"2024-05-14T16:33:25Z","snapshot_observed_at":"2026-07-06T18:14:16.386835Z","submitted_at":"2024-05-14T16:33:25Z","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08748","snapshot_observed_at":"2026-08-04T13:44:08.667828Z","title":"Ziqiang Li, Jiazhen Yan, Ziwen He, Kai Zeng, Weiwei Jiang, Lizhi Xiong, and Zhangjie Fu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.667828Z"},"links":{"cited_paper":"/paper/2405.08748","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:0f510b62babe443df48ec022978623f69b0b16308616b4f0a04bae6340e648ab","observation_id":"37ccd311-6343-46c1-921a-b5e96caee0ab","resolution":{"observed_at":"2026-08-04T13:44:08.667828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.03147","last_updated":"2025-06-18T18:00:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-03T17:59:33Z","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.03147","snapshot_observed_at":"2026-08-04T13:44:08.762641Z","title":"Tsung-Yi Lin, Michael Maire, Serge J","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.762641Z"},"links":{"cited_paper":"/paper/2506.03147","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:cccdf8682df17c7902bb1af9b9f71b291f1ed9c5db1f032c861a55936cc8f548","observation_id":"aca39f43-31b8-4937-8d56-ccf68ee59dcf","resolution":{"observed_at":"2026-08-04T13:44:08.762641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.870574Z","title":"Which model generated this image? A model-agnostic approach for origin attribution","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.870574Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:43d9275c097b1fa93b1190aceef98c1f7bb9344de0ca2b42bc462bea259cc405","observation_id":"c0b2244c-92e8-4036-8fc5-55c34812964f","resolution":{"observed_at":"2026-08-04T13:44:08.870574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.922275Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.922275Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:042a18038a3b874c122a433f81f4bed617ca936e990716a32ea94226448a631f","observation_id":"42dd3655-a5d4-41f8-9f6a-9028ac00b685","resolution":{"observed_at":"2026-08-04T13:44:08.922275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.13023","last_updated":"2023-09-22T18:16:28Z","snapshot_observed_at":"2026-07-06T15:19:57.802336Z","submitted_at":"2023-04-25T17:51:59Z","title":"Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.13023","snapshot_observed_at":"2026-08-04T13:44:09.002350Z","title":"Yunpeng Luo, Junlong Du, Ke Yan, and Shouhong Ding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.002350Z"},"links":{"cited_paper":"/paper/2304.13023","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:f552705da71c7bd790a3fbb8bb1f216c6c54b96cd00afd32c3c65c9e0cb4f89d","observation_id":"4da0a3bc-24af-4c74-996b-9f837da9af5b","resolution":{"observed_at":"2026-08-04T13:44:09.002350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.179502Z","title":"Community forensics: Using thousands of generators to train fake image detectors","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.179502Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:93e465242112db9b8c3262c0ecd5a0a2ce324ca46f1b70198d96d8e820792472","observation_id":"f7b316a2-429e-4470-a980-852654ff2ec6","resolution":{"observed_at":"2026-08-04T13:44:09.179502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11970","last_updated":"2023-02-24T13:41:35Z","snapshot_observed_at":"2026-07-06T14:55:00.475642Z","submitted_at":"2023-02-23T12:40:36Z","title":"ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11970","snapshot_observed_at":"2026-08-04T13:44:09.246335Z","title":"Anirudh Sundara Rajan and Yong Jae Lee","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.246335Z"},"links":{"cited_paper":"/paper/2302.11970","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:4b0d3325321bff6095b21ce76d14b74d04e7d5d0c2cee8a4c87bfe74f716c8ea","observation_id":"b79cefbc-b258-428f-941c-f32ec2bb6804","resolution":{"observed_at":"2026-08-04T13:44:09.246335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07778","last_updated":"2025-05-26T03:33:23Z","snapshot_observed_at":"2026-08-09T21:14:14.474992Z","submitted_at":"2025-02-11T18:59:10Z","title":"Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.07778","snapshot_observed_at":"2026-08-04T13:44:09.310059Z","title":"Jonas Ricker, Denis Lukovnikov, and Asja Fischer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.310059Z"},"links":{"cited_paper":"/paper/2502.07778","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:622d0057c7c43790b25b2fde7ca6521fa5f41f1732b7d03df6b775487a56bbd4","observation_id":"e02ce1d1-0bb2-41eb-825b-fdca1eb14996","resolution":{"observed_at":"2026-08-04T13:44:09.310059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.407620Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.407620Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:398c99245401e3ca0bfa787e88d637ce451ce8aaa2619bbab64e2a2ce7252719","observation_id":"2ab14176-4aef-4db6-afbd-e9c03295de24","resolution":{"observed_at":"2026-08-04T13:44:09.407620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.515079Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.515079Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:e8d2b87718bc5b4dd26cba71744d2e074e1b9be79dec42ea930761ba8cd840d0","observation_id":"858c023c-ef21-4e52-ad21-eacbf87b3dc5","resolution":{"observed_at":"2026-08-04T13:44:09.515079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.561620Z","title":"Contrastive pseudo learning for open-world deepfake attribution","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.561620Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:faae5e4fbf0b6c0605b700a09e145619875cb7c820fead840efa3f5492a76dd6","observation_id":"9aa8fcaa-e8e8-4d97-a113-20ce07c51405","resolution":{"observed_at":"2026-08-04T13:44:09.561620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.607613Z","title":"Rethinking the up-sampling operations in cnn-based generative network for generalizable deep- fake detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.607613Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:87ee70a9a804a63eea824551d9f9c638387b79da5f46e96b16115e02c7c3d9dd","observation_id":"0d5c70af-e906-49f6-8155-5736dd3b0706","resolution":{"observed_at":"2026-08-04T13:44:09.607613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.23044","last_updated":"2025-07-01T09:33:23Z","snapshot_observed_at":"2026-08-06T21:49:22.757971Z","submitted_at":"2025-06-29T00:40:17Z","title":"Ovis-U1 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.23044","snapshot_observed_at":"2026-08-04T13:44:09.708983Z","title":"Ovis-u1 technical report, 2025a","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.708983Z"},"links":{"cited_paper":"/paper/2506.23044","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:cf3bd4b95b0936cf121705c348d90eefd283bcf2984ff07fa3218fd7bbc1baa2","observation_id":"e4e1981a-d8f5-4e2e-a892-9b6253aac7b7","resolution":{"observed_at":"2026-08-04T13:44:09.708983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.795263Z","title":"DIRE for diffusion-generated image detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.795263Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:278cdb32fd793d282fcd11ddd7d9856d9d83eff9246e61110aa01e60873095ca","observation_id":"e36c8167-3170-4c70-8b55-5b65796c36c4","resolution":{"observed_at":"2026-08-04T13:44:09.795263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.911330Z","title":"Detecting origin attribution for text-to-image diffu- sion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.911330Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:564414b7f56b170c63d64d22296a4b585cb20b76222eed2a2bb433eb6d579689","observation_id":"b34ddd3d-5041-497f-8380-2176dd180b3f","resolution":{"observed_at":"2026-08-04T13:44:09.911330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.952147Z","title":"Deepfake network architecture attribution","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.952147Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:3c56184c11cf7d2779badec19638f27324477123d45ec39d546d6b9e6a98e746","observation_id":"55ecb388-7072-46ca-886a-9cf0706d036f","resolution":{"observed_at":"2026-08-04T13:44:09.952147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.03365","last_updated":"2016-06-04T09:51:30Z","snapshot_observed_at":"2026-08-08T13:26:17.517503Z","submitted_at":"2015-06-10T15:38:47Z","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.03365","snapshot_observed_at":"2026-08-04T13:44:10.018872Z","title":"Nan Zhong, Yiran Xu, Sheng Li, Zhenxing Qian, and Xinpeng Zhang","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.018872Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:91c324bca0e80efc235d28df4649b5a5566981690e32cfe749b46c993d61fc0a","observation_id":"38b730a6-3a2d-4262-bcbd-b2346e28a5a3","resolution":{"observed_at":"2026-08-04T13:44:10.018872Z","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":"2026-08-07T07:10:19.526284Z","submitted_at":"2023-11-21T07:12:40Z","title":"PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12397","snapshot_observed_at":"2026-08-04T13:44:10.069836Z","title":"Mingjian Zhu, Hanting Chen, Qiangyu Yan, Xudong Huang, Guanyu Lin, Wei Li, Zhijun Tu, Hailin Hu, Jie Hu, and Yunhe Wang","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.069836Z"},"links":{"cited_paper":"/paper/2311.12397","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:1bf8e83b23db17dfb0896ca1600e0a8dec697e5a7051fc29a5e8588bb3c1a690","observation_id":"3ead3ad5-d6bb-458b-88c5-e19e3dfb82e9","resolution":{"observed_at":"2026-08-04T13:44:10.069836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.136240Z","title":"For instance, the widely-used GenImage dataset (Zhu et al.,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.136240Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:d231f856fc1848bd96a8d9a093efa780410a46e0eb37f3a1e7f4fea3c6cbe761","observation_id":"5b36a919-15d9-4440-8f65-f21816a17f50","resolution":{"observed_at":"2026-08-04T13:44:10.136240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.186527Z","title":"This structural homogeneity results in remarkably similar feature distributions among their gener- ated images","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.186527Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:397194276424db2ad1331248d862a4ba6d3337d5570fa9f3ab507f98654972e2","observation_id":"32f76acb-d5dd-494d-a9aa-461807862318","resolution":{"observed_at":"2026-08-04T13:44:10.186527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.251864Z","title":"Therefore, merely making minor modifications to the weights or model architecture is insufficient to enable the model to express fundamentally different representations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.251864Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:1292fd4f34c9143dad4c2ebe19c486ad37748cb9276f8572a8a37f40a7537460","observation_id":"45603e14-ae4d-4c58-9401-9451bd2a372c","resolution":{"observed_at":"2026-08-04T13:44:10.251864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.324749Z","title":"As diffusion mod- els (Ho et al.,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.324749Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:136c8e270ce3597fbb8ad40444944703e0114cb7b2e518ded4f34c9da562c7c0","observation_id":"578002dc-cf05-4244-95c5-2f74cd3b3e9f","resolution":{"observed_at":"2026-08-04T13:44:10.324749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.368616Z","title":"However, these datasets only cover a limited number of generators, restricting the generalization capability of detectors","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.368616Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:484973fd6569c692f33ae184bb431c79b0fda9d95ea2aee6f2a0837fa33d081f","observation_id":"0718a799-d1c4-4f7d-aceb-f4a5df84f0d7","resolution":{"observed_at":"2026-08-04T13:44:10.368616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.439932Z","title":"Community Forensics (Park & Owens,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.439932Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:2e42e551f8b1f8d2816d53570c70228dbc73c54cdee3f495f64d471773412e50","observation_id":"dff1aadc-11f8-4d65-9ad8-7c9b6d6140a8","resolution":{"observed_at":"2026-08-04T13:44:10.439932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.510650Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.510650Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:73e4f52c279ff04a8b52b99d97102307a46ce40dbfd3113a5bc1706ec4bbdfc7","observation_id":"542cc213-d40c-45cd-a15f-66ef14ff8383","resolution":{"observed_at":"2026-08-04T13:44:10.510650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.585465Z","title":"Recent studies (Cocchi et al.,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.585465Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:764067c5ad5325c8a17faceaa41161ea66d83089eda57a8b9f82c0d7bfc50459","observation_id":"03fea5f2-a5b1-4e18-9ecf-05fdadad9e49","resolution":{"observed_at":"2026-08-04T13:44:10.585465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.680962Z","title":"Bi et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.680962Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:f435fdfbc6a8579d406496a2375871c7be3e1d9b4376ea37de34cbe09bdc1650","observation_id":"cfdefbf2-95c6-4112-ae4e-2d98fed123a8","resolution":{"observed_at":"2026-08-04T13:44:10.680962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.752326Z","title":"Inspired by these advances, we aim to fully explore the potential of metric learning for out-of-distribution deepfake detection","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.752326Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:5abf6cfd3052c900f071b5a41ec5b0529af270da85a020569a2957cf52bcbe07","observation_id":"ac72578b-8998-4727-8ac0-a63a10049ef6","resolution":{"observed_at":"2026-08-04T13:44:10.752326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.827129Z","title":"Their motivations are based on the observation that models with different architectures exhibit distinct fingerprints","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.827129Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:6b0cc02a96839ef3e9114d80a3695a672da1043a6c3743393a3c7ad702b3b31a","observation_id":"21dfc92e-d853-4379-b930-ca26483273bc","resolution":{"observed_at":"2026-08-04T13:44:10.827129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.886386Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.886386Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:db74c13c42711666edf2da6ef8df1c4df85199eea4bdca4173464d36a4208a39","observation_id":"d7fc451d-de96-49a9-9c72-a093b33f205f","resolution":{"observed_at":"2026-08-04T13:44:10.886386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:10.961919Z","title":"Our synthetic categories include models from the same family, but we rigorously ensure that they are not derived from the same backbone","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:10.961919Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:7cb53d39bc38e4e5fa9a4347596e5705f4730629900250359248fb513ac57c52","observation_id":"875dba32-d32e-4d8d-96e5-9d73e649130b","resolution":{"observed_at":"2026-08-04T13:44:10.961919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:11.031293Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:11.031293Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:2061ddf1574687236755728e44d2db9d8d9cdcac916e56afa3e3f116d43b7f55","observation_id":"ef7f6dd4-2fac-44d2-a451-6197b1561e9c","resolution":{"observed_at":"2026-08-04T13:44:11.031293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:11.091897Z","title":"However, this practice can introduce significant real biases by limiting the diversity and representativeness of the authentic class","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:11.091897Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:a4f57aedd811c047b2d2ac0a2511350772fb2fd180e75a5eabac1fc4c7fe885c","observation_id":"8e7f93fd-b5f6-4fd8-b532-3141a96bbb21","resolution":{"observed_at":"2026-08-04T13:44:11.091897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:11.172981Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:11.172981Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:d367c6ca0bdc080be029fe4e177ddc1bd8fee95806602b68d1812938bc96450a","observation_id":"e2c10e0b-0072-4117-81f2-fa9a6f46e280","resolution":{"observed_at":"2026-08-04T13:44:11.172981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:11.262624Z","title":"These are balanced with carefully constructed datasets including Ima- geNet (Russakovsky et al., 2015), MSCOCO (Lin et al.,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:11.262624Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:ba9a06ab6443250392843b2a05d96ba08e570448aa7f6d851f29e52db3210e97","observation_id":"90bd0981-85a5-48b9-bf7e-92187c876d18","resolution":{"observed_at":"2026-08-04T13:44:11.262624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:11.367384Z","title":"This approach not only maximizes the utilization of limited data but also guarantees that model performance is evaluated across diverse and representative subsets","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:11.367384Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:62d69d5475df931cb3ee26cdfd779adc37b85f24e0db6959351ffe6ab11e7b1e","observation_id":"6f218674-cc4b-416f-bbc9-78324eb5a536","resolution":{"observed_at":"2026-08-04T13:44:11.367384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:11.471857Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:11.471857Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:7c6ef847fbff974e9707fa06aa3cd69827c6f91e2c536af45c9e50c7fe827295","observation_id":"307eb9ea-36f2-4850-960c-0897cf6f352f","resolution":{"observed_at":"2026-08-04T13:44:11.471857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.100970Z","title":"Fake or jpeg? revealing common biases in generated image detection datasets","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.100970Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:61b3b5532eb5a69fd35b0e1a0ea86cd562fb3b6c846c6602be623f46b9d05cad","observation_id":"80b97ac5-a694-4d47-ade6-7f72b0434c52","resolution":{"observed_at":"2026-08-04T13:44:08.100970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18871","last_updated":"2026-04-21T17:32:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-23T17:38:54Z","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.18871","snapshot_observed_at":"2026-08-04T13:44:09.835527Z","title":"Omnigen2: Exploration to advanced multimodal generation, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.835527Z"},"links":{"cited_paper":"/paper/2506.18871","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:53653c18796c40b9aa9ee0de73a9aad0949e04c11e88b1fe6d8804d75c20d8f7","observation_id":"68362cee-3233-4960-8091-bf7eb83ddc59","resolution":{"observed_at":"2026-08-04T13:44:09.835527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.469364Z","title":"Supervised contrastive learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.469364Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:38b7665a2df040fc63cb39e10f2f00c8ad4bf5e0d92bc107699d01ba4ce9a0f7","observation_id":"51f8b733-bac3-45f2-8443-6635ceb165ed","resolution":{"observed_at":"2026-08-04T13:44:08.469364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:08.581609Z","title":"Improving synthetic image detection towards generalization: An image transformation perspective","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:08.581609Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:1e8f2b58717be831b3d4b17cc53dce8d404f9c8e2bef4274c5cc686a9ad61e23","observation_id":"dbdf9714-2a06-41db-ac4e-0af2de516571","resolution":{"observed_at":"2026-08-04T13:44:08.581609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:09.105814Z","title":"Towards universal fake image detectors that generalize across generative models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:09.105814Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:f67a91a72ccf62eb1177de0a6667d8d2e5b71c390238a8a80aa67c53866be564","observation_id":"24fa729f-3cde-4ae0-ba95-f9a401ba6529","resolution":{"observed_at":"2026-08-04T13:44:09.105814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:07.407516Z","title":"Conceptual 12m: Pushing web- scale image-text pre-training to recognize long-tail visual concepts","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.407516Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:5414f2e08a8492458e577dfbe7808ee961be8849ecdadd1f3e375a422c6f67a2","observation_id":"e75af16b-d184-42d3-95b8-3d71b2e4e2bd","resolution":{"observed_at":"2026-08-04T13:44:07.407516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:44:07.994808Z","title":"Leveraging frequency analysis for deep fake image recognition","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.994808Z"},"links":{"citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:126a51dac071a003ba06ab6baabd72570426a501bf12094ae0213a4b5409eedd","observation_id":"ae1c6fe3-abc8-4005-b763-d6882c6bd95a","resolution":{"observed_at":"2026-08-04T13:44:07.994808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09568","last_updated":"2025-05-14T17:11:07Z","snapshot_observed_at":"2026-07-06T21:23:57.084147Z","submitted_at":"2025-05-14T17:11:07Z","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09568","snapshot_observed_at":"2026-08-04T13:44:07.523527Z","title":"Blip3-o: A family of fully open unified multimodal models-architecture, training and dataset, 2025a","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.523527Z"},"links":{"cited_paper":"/paper/2505.09568","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:6e24194c606acd17f89ee16ef1bb16a75f50a5552e66783ab98873fd4d7c6da4","observation_id":"2cf751ab-92c1-4daf-ae65-c32eff28d8e0","resolution":{"observed_at":"2026-08-04T13:44:07.523527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20020","last_updated":"2025-01-14T12:31:48Z","snapshot_observed_at":"2026-08-04T12:48:59.386559Z","submitted_at":"2024-07-29T13:57:24Z","title":"ImagiNet: A Multi-Content Benchmark for Synthetic Image Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.20020","snapshot_observed_at":"2026-08-04T13:44:07.282736Z","title":"Tu Bui, Ning Yu, and John P","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-04T13:44:07.282736Z"},"links":{"cited_paper":"/paper/2407.20020","citing_paper":"/paper/2509.25682"},"observation_digest":"sha256:e01a87a9bf2ff471c7c98642ac925371579f3f9e3df01d98ae2d2ffef2da146d","observation_id":"7a20384a-724e-45f8-9152-b44a46db50e4","resolution":{"observed_at":"2026-08-04T13:44:07.282736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.25682","last_updated":"2026-06-30T07:06:33Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T12:23:04.844284Z","submitted_at":"2025-09-30T02:36:40Z","title":"Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samples"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":54,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":54},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 2 inbound Pith citation observations for arXiv:2509.25682."}