{"as_of":"2026-08-09T10:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7ef7fd1e19d7301799fbab8e3476e5c4eb3815be53fb3d67815af79778ccdb5f","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T07:41:41.612242Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.16283/citation-record","integrity":"/paper/2607.16283/integrity","json":"/paper/2607.16283/citation-record.json","paper":"/paper/2607.16283"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T07:41:35.146410Z","title":"Improving image generation with better captions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.146410Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:df776f0300baff1d69494cee335b47d51ea573bbe0d107e0ce82b95b9bfc4591","observation_id":"c87bfb71-9fcb-4b3f-97ff-76f1aa3c93b5","resolution":{"observed_at":"2026-08-02T07:41:35.146410Z","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":"2026-08-02T07:41:35.287489Z","title":"CIFAKE: Image classification and explainable identification of AI-generated synthetic images.IEEE Access, 12:15642–15650, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.287489Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:f527306b2e23187e96aa87a8356e7a4e6e7b926c0b864f41cb212f3a99dbebbb","observation_id":"680d233d-424c-4daf-b1f6-feef0635d7ba","resolution":{"observed_at":"2026-08-02T07:41:35.287489Z","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":"2026-08-02T07:41:35.404105Z","title":"FLUX.1.https://github.com/black-forest-labs/flux, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.404105Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:4b57a9fadceb74b11af5b74f6d53a2351cdf9cbe7eeee71fbe34335f22676484","observation_id":"7e518f3b-263e-4016-b802-323609168867","resolution":{"observed_at":"2026-08-02T07:41:35.404105Z","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":"2026-08-02T07:41:35.511892Z","title":"FLUX.2: Frontier Visual Intelligence","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.511892Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:a273c10fbb5fa3b1346920aa940ca5a1d54f7fe58dab3a934dc265e38705b6b5","observation_id":"73319207-c68f-42ef-880e-9729bebee3fc","resolution":{"observed_at":"2026-08-02T07:41:35.511892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.23951","last_updated":"2026-06-26T07:53:46Z","snapshot_observed_at":"2026-08-04T14:42:12.962842Z","submitted_at":"2025-09-28T16:14:10Z","title":"HunyuanImage 3.0 Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.23951","snapshot_observed_at":"2026-08-02T07:41:35.626705Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.626705Z"},"links":{"cited_paper":"/paper/2509.23951","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:03347ed9ed5e108f37c13cb66b09e15328a24bd5ae3b5356cd8d41d9d69b919f","observation_id":"e6287d60-fefa-473e-9dc6-5b815f578d89","resolution":{"observed_at":"2026-08-02T07:41:35.626705Z","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":"2026-08-02T07:41:35.713321Z","title":"CO-SPY: Com- bining semantic and pixel features to detect synthetic images by AI","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.713321Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:c05e39c00f2c5f24161d6c241542b40256f42f718c4229046b68e6bceb93b3ed","observation_id":"f839f8b5-ab71-4f9d-8c5e-1e42eb5c077b","resolution":{"observed_at":"2026-08-02T07:41:35.713321Z","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":"2026-08-02T07:41:35.833154Z","title":"Pytorch cifar models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.833154Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:39824f95e68f18d012f5b3e74820635f3248de36d3c826c3abd10613b90d3ca0","observation_id":"af704daa-17d4-4fd4-ad29-de57afe753e2","resolution":{"observed_at":"2026-08-02T07:41:35.833154Z","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":"2026-08-02T07:41:35.992420Z","title":"Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael I","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:35.992420Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:a5258cac1db6848ba1d3ba3e251f85d6637f4b942559e0aafbd7b73a02af0c29","observation_id":"44cc714a-bfdf-42b7-b223-c4229b079bb3","resolution":{"observed_at":"2026-08-02T07:41:35.992420Z","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":"2026-08-02T07:41:36.138401Z","title":"On the detection of synthetic images generated by diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.138401Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:a1a7e46d374c514b6f9b716b6a7343f73b15df05b3ad29c9ce76dae359e492f3","observation_id":"f701f020-4d75-4a2d-9274-fed25814535c","resolution":{"observed_at":"2026-08-02T07:41:36.138401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00195","last_updated":"2024-04-29T14:25:42Z","snapshot_observed_at":"2026-08-07T11:24:38.731489Z","submitted_at":"2023-11-30T21:11:20Z","title":"Raising the Bar of AI-generated Image Detection with CLIP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00195","snapshot_observed_at":"2026-08-02T07:41:36.298139Z","title":"Raising the bar of AI-generated image detection with CLIP.arXiv preprint arXiv:2312.00195, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.298139Z"},"links":{"cited_paper":"/paper/2312.00195","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:9ec048b9433581ddafc51ece52a70b07830aa224ce47d71a3eeb59d35a614d63","observation_id":"c07bf614-89f5-4c7c-b0d8-68981ba22da7","resolution":{"observed_at":"2026-08-02T07:41:36.298139Z","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":"2026-08-02T07:41:36.436492Z","title":"ImageNet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.436492Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:0d6e4b60f6f19a8a2c62e93db4873430f7c6cf2d66ec6bfa1ebbd2e3df876cd4","observation_id":"4faa78be-eb4d-465a-b8b4-3ec7458151ff","resolution":{"observed_at":"2026-08-02T07:41:36.436492Z","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":"2026-08-02T07:41:36.589289Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.589289Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:66fe2cb6c0c3c81146c941568459d620aca76320bef532bc3308b8920fd755a2","observation_id":"b896057b-ea9a-466d-b7f7-05a1932e7dc9","resolution":{"observed_at":"2026-08-02T07:41:36.589289Z","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":"2026-08-02T07:41:36.664480Z","title":"Scaling rectified flow transformers for high-resolution image synthesis.arXiv preprint arXiv:2403.03206, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.664480Z"},"links":{"cited_paper":"/paper/2403.03206","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:dc1c35bbd6b177e2a7d4ef573251275c60b1a36a9f14098654638881894606ed","observation_id":"558031bb-29c4-4474-8e9c-a5827b4f7eb1","resolution":{"observed_at":"2026-08-02T07:41:36.664480Z","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":"2026-08-02T07:41:36.807489Z","title":"Leveraging frequency analysis for deep fake image recognition","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.807489Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:d1e90822978c184029f96cc886e5c6cac636d115023766eaaebbb7f5e1747371","observation_id":"0e951a22-466e-436a-82b0-8af2dbd1ad2b","resolution":{"observed_at":"2026-08-02T07:41:36.807489Z","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":"2026-08-02T07:41:36.978081Z","title":"Generative adversarial nets.Advances in Neural Information Processing Systems (NeurIPS), 27, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:36.978081Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:bed4c57ca674882b379262272340fcdf13f45d5e7d5acddabbbb5eed3a7ebb20","observation_id":"a76fbe61-3622-44ae-bcbe-871dd9f441f6","resolution":{"observed_at":"2026-08-02T07:41:36.978081Z","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":"2026-08-02T07:41:37.083719Z","title":"Are GAN generated images easy to detect? A critical analysis of the state-of-the-art","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.083719Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:8b389576c3a9af584142214e37eae7bb35d0a4193404e14de1e3dc32adffbbed","observation_id":"aebfa16a-2583-4834-b817-5e847e179e39","resolution":{"observed_at":"2026-08-02T07:41:37.083719Z","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":"2026-08-02T07:41:37.203391Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.203391Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:feb0dfa04f27b85ef1110c3492b35bb15489d6f6705070202c491aaf49727476","observation_id":"ae52179b-22e6-4cd5-9dec-1c0d59e260f4","resolution":{"observed_at":"2026-08-02T07:41:37.203391Z","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":"2026-08-02T07:41:37.311780Z","title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.311780Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:b7362ac0399736286d1b07aa6575da1445abc0f2da7dfc8b98d286117917dff8","observation_id":"ae8f47c5-2c73-408e-9543-ffd5eef01659","resolution":{"observed_at":"2026-08-02T07:41:37.311780Z","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":"2026-07-06T09:30:47.469703Z","submitted_at":"2020-06-19T17:24:44Z","title":"Denoising Diffusion Probabilistic Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11239","snapshot_observed_at":"2026-08-02T07:41:37.398958Z","title":"Denoising diffusion probabilistic models.arXiv preprint arXiv:2006.11239, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.398958Z"},"links":{"cited_paper":"/paper/2006.11239","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:c939b372d8bec9d46bbd69272e7629a4e74292571ce080555696861906215b64","observation_id":"02eb5c21-7229-4a4b-b4a0-b8e8099fffff","resolution":{"observed_at":"2026-08-02T07:41:37.398958Z","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":"2026-08-02T07:41:37.506715Z","title":"Wild- Fake: A large-scale and hierarchical dataset for AI-generated images detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.506715Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:a13e9413d5b62d601ef6d5d6fcf2151790673cec93eda3b8b2f1d541d71d6871","observation_id":"8ee6a28f-4980-4fe8-a8ad-dbd695bd934f","resolution":{"observed_at":"2026-08-02T07:41:37.506715Z","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":"2026-08-02T07:41:37.660460Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.660460Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:7f103df93d14579025c1b055c397082f4ae08fe2718ba3792f9a623d0be9b20e","observation_id":"f1a2ebf3-1ccf-4391-8ed6-23246b0fa909","resolution":{"observed_at":"2026-08-02T07:41:37.660460Z","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":"2026-08-02T07:41:37.768975Z","title":"Progressive growing of GANs for improved quality, stability, and variation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.768975Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:49cd64b1c4ea2c1a949259c9ff66db0311a5030d4c4d964475aab36f0326a899","observation_id":"b956e138-fdd2-47ca-9a58-69a9f95c3b96","resolution":{"observed_at":"2026-08-02T07:41:37.768975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.04948","last_updated":"2019-03-29T11:08:46Z","snapshot_observed_at":"2026-08-07T15:57:18.072541Z","submitted_at":"2018-12-12T13:59:43Z","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.04948","snapshot_observed_at":"2026-08-02T07:41:37.879241Z","title":"A style-based generator architecture for generative adversarial networks.arXiv preprint arXiv:1812.04948, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.879241Z"},"links":{"cited_paper":"/paper/1812.04948","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:aa56dc41b1f1c5a1ef8b723e2b61f5d174ffe9d370b1b74a224148a33167253c","observation_id":"15f387b3-1090-45c9-8c03-49f937df77a7","resolution":{"observed_at":"2026-08-02T07:41:37.879241Z","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":"2026-08-02T07:41:37.950110Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:37.950110Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:fb9dc6b236ffcb74a208cf1db12c99efb79bccdf041a15de0e75df22c0a1084e","observation_id":"0f64426c-83a1-40d2-93fa-786226a212f9","resolution":{"observed_at":"2026-08-02T07:41:37.950110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.06991","last_updated":"2019-10-30T12:33:29Z","snapshot_observed_at":"2026-07-06T07:46:06.039145Z","submitted_at":"2019-04-15T12:20:32Z","title":"Improved Precision and Recall Metric for Assessing Generative Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.06991","snapshot_observed_at":"2026-08-02T07:41:38.164636Z","title":"Improved precision and recall metric for assessing generative models.arXiv preprint arXiv:1904.06991, 2019","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.164636Z"},"links":{"cited_paper":"/paper/1904.06991","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:8863758ffcfdb6d6bd9f0e5114965f3886ddbfd90c94600eacba991fc6bd5c82","observation_id":"3a4cdbeb-7c10-4145-90d2-44df0be602ed","resolution":{"observed_at":"2026-08-02T07:41:38.164636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-02T07:41:38.265434Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.265434Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:037cceef113590e276136bbee68bbfe3316d1ec14ce4ad1921cc278a7ce27c8c","observation_id":"719d2f42-351e-4b3a-b939-f0ba949d7342","resolution":{"observed_at":"2026-08-02T07:41:38.265434Z","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":"2026-08-02T07:41:38.382041Z","title":"Swin-base fine-tuned on cifar-10","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.382041Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:a0308c6d89551bb0137f63b4a2a67ffb4d41745f3ef3f9b8e7d66dc524a5d4e2","observation_id":"4286153f-cdf2-4c22-887a-55ea4907c8f8","resolution":{"observed_at":"2026-08-02T07:41:38.382041Z","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":"2026-08-02T07:41:38.544828Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.544828Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:22ec5cf8367baab4cef865ce0c1eb1845ed41b9dc8d0cec691615c4be88382dd","observation_id":"22e8f943-2d55-4c18-9bc4-c07b145aed75","resolution":{"observed_at":"2026-08-02T07:41:38.544828Z","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":"2026-08-02T07:41:38.641868Z","title":"A ConvNet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.641868Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:7b8c9853b6fa934251bc8a25600688bbdbeb773be9b523507b6056c12a1df3af","observation_id":"cb41b25b-4cb8-4487-97d1-562d7e0c0099","resolution":{"observed_at":"2026-08-02T07:41:38.641868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-02T07:41:38.732051Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.732051Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:5ab7efbaada16ea1e79d38c3f39c2ddf2199b757fb704e3b1ef86f8c0980b4be","observation_id":"48a3d7e8-4f0a-48d8-a42b-dd39cf10dfa1","resolution":{"observed_at":"2026-08-02T07:41:38.732051Z","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":"2026-08-02T07:41:38.860624Z","title":"When does label smoothing help? In Advances in Neural Information Processing Systems (NeurIPS), pages 4694–4703, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:38.860624Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:ec3e171f9fa7bf14f4d04b65f2399b665428bbd257ea34ddd62886b000573a89","observation_id":"60cb137c-8ef2-4baa-a145-da4010519223","resolution":{"observed_at":"2026-08-02T07:41:38.860624Z","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":"2026-08-02T07:41:39.033075Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.033075Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:5cd0589a77595e6d78e02a15d5ea0e8d11cac0f35ae63f5dbea48805a6245140","observation_id":"b18e0ad5-3df5-4382-b379-d927a92f2dfd","resolution":{"observed_at":"2026-08-02T07:41:39.033075Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.10174","last_updated":"2024-04-01T04:00:31Z","snapshot_observed_at":"2026-08-07T09:10:17.410802Z","submitted_at":"2023-02-20T18:59:04Z","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.10174","snapshot_observed_at":"2026-08-02T07:41:39.190072Z","title":"Towards universal fake image detectors that generalize across generative models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.190072Z"},"links":{"cited_paper":"/paper/2302.10174","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:48363bc277de604518d776d057b8816ff471bbea3bca85e924db18dfef0c6819","observation_id":"2c74660a-f68b-4461-8b97-760c89d81e01","resolution":{"observed_at":"2026-08-02T07:41:39.190072Z","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":"2026-08-02T07:41:39.313965Z","title":"Pytorch cifar-10 pre-trained models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.313965Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:e017ddb037f40211c4948b679c973cd99b2ad2d14c0bbc2938c4dab0ef146aed","observation_id":"794c0540-2da1-4a88-b24e-43a330c91d35","resolution":{"observed_at":"2026-08-02T07:41:39.313965Z","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":"2026-08-02T07:41:39.439694Z","title":"Qwen-image: Advancing text-to-image generation via latent diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.439694Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:ab78fff929c571ee967664171239b09043efc28d07df3cf96be08ed6834b3e8b","observation_id":"af6ae506-1b02-4341-8459-dd1a541f862d","resolution":{"observed_at":"2026-08-02T07:41:39.439694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.13678","last_updated":"2020-03-30T17:57:47Z","snapshot_observed_at":"2026-08-07T01:31:50.220041Z","submitted_at":"2020-03-30T17:57:47Z","title":"Designing Network Design Spaces","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.13678","snapshot_observed_at":"2026-08-02T07:41:39.593248Z","title":"Design- ing network design spaces.arXiv preprint arXiv:2003.13678, 2020","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.593248Z"},"links":{"cited_paper":"/paper/2003.13678","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:02c45d8d596179f0c437965683630e79cd7c21532e0548d43b7d6f05b35f0b0d","observation_id":"13537002-8691-47aa-8a13-275a19f2a91f","resolution":{"observed_at":"2026-08-02T07:41:39.593248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-02T07:41:39.722500Z","title":"Hierarchical text-conditional image generation with CLIP latents.arXiv preprint arXiv:2204.06125, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.722500Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:5b0696c1d21c05bf2f1e39b7a03d0bc68172addfb7c392757c4162db98963a7f","observation_id":"8f5599ca-c96a-494e-821b-ded4839d9344","resolution":{"observed_at":"2026-08-02T07:41:39.722500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17879","last_updated":"2024-03-27T09:17:14Z","snapshot_observed_at":"2026-08-06T09:21:30.457153Z","submitted_at":"2024-01-31T14:36:49Z","title":"AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17879","snapshot_observed_at":"2026-08-02T07:41:39.848466Z","title":"AEROBLADE: Training-free detection of latent diffusion images using autoencoder reconstruction error.arXiv preprint arXiv:2401.17879, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.848466Z"},"links":{"cited_paper":"/paper/2401.17879","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:de8b1eeea01f528f6ffc732dee6846a0cacf2d8ac52e7b24e86c105702b796b8","observation_id":"a21db223-f313-4ed6-a77e-192e55434bf4","resolution":{"observed_at":"2026-08-02T07:41:39.848466Z","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":"2026-08-02T07:41:39.927445Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:39.927445Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:f66fb8ad74e3d1a1f2450f7c93c366ffda437bcb441ceda3be613e76b1e8a879","observation_id":"109e006e-7738-47b9-9e66-40946c40878a","resolution":{"observed_at":"2026-08-02T07:41:39.927445Z","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":"2026-08-02T07:41:40.023326Z","title":"Improved techniques for training GANs","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.023326Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:8e63621df3ef85af09bcd94907ed2a65f0ecbbf429a6c4d2606b953b49f5057c","observation_id":"f181e21e-e057-4b45-926f-18d900ef2298","resolution":{"observed_at":"2026-08-02T07:41:40.023326Z","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":"2026-08-02T07:41:40.111399Z","title":"MobileNetV2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.111399Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:89dad79605bbe1864eec8ff1d90840c7c9f2ead8c215229a241e8db7eda53c67","observation_id":"3b747748-911c-4466-8a48-3df0a1e478ed","resolution":{"observed_at":"2026-08-02T07:41:40.111399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.06998","last_updated":"2023-01-09T16:33:43Z","snapshot_observed_at":"2026-07-06T14:04:44.193264Z","submitted_at":"2022-10-13T13:08:54Z","title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.06998","snapshot_observed_at":"2026-08-02T07:41:40.207788Z","title":"DE-FAKE: Detection and attribution of fake images generated by text-to-image generation models.arXiv preprint arXiv:2210.06998, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.207788Z"},"links":{"cited_paper":"/paper/2210.06998","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:eef94ba0a4727e57fbe308bea67aa24ce2f43a4d19fbd2604f58378b78be5d6c","observation_id":"dd492fa7-a9c3-4e84-8455-1ed09e56fe71","resolution":{"observed_at":"2026-08-02T07:41:40.207788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-02T07:41:40.314274Z","title":"Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.314274Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:1f0b200ccbca8d4ed14af34db7661f2fe58be96a24a8983711db59189de2dd14","observation_id":"e7c68d69-ee1b-4adc-8461-40335ab1c753","resolution":{"observed_at":"2026-08-02T07:41:40.314274Z","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":"2026-08-02T07:41:40.503507Z","title":"Stable diffusion 3.5","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.503507Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:7dc5e42ad43476dc5476e40b54ac482328eecbe0a21c7a3fe1286f1400c80e4a","observation_id":"9d69eba7-8a2f-476e-be6e-e04d284f8fff","resolution":{"observed_at":"2026-08-02T07:41:40.503507Z","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":"2026-08-02T07:41:40.615823Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.615823Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:c8c11ce2c723e8a9391ae14b66a6466badf49c2e3525d57bcb6207866ba95f10","observation_id":"f5aae27d-ee53-4ec6-a177-f7b341cf03c8","resolution":{"observed_at":"2026-08-02T07:41:40.615823Z","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":"2026-08-02T07:41:40.734561Z","title":"Re- thinking the inception architecture for computer vision","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.734561Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:481f0aefc90580b3c00c059f003921e06951fb8538e8b23ec3f968bca2550b88","observation_id":"a84d2ef8-4b93-48ab-813e-894ec9aafa9d","resolution":{"observed_at":"2026-08-02T07:41:40.734561Z","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":"2026-08-02T07:41:40.826674Z","title":"MnasNet: Platform-aware neural architecture search for mobile","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.826674Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:b5acea96bda6dec99dc3cee4adaaecd0a586296702f2265caed0859ffa5b92ac","observation_id":"e6c4bf1f-b086-4c19-aa5f-8d2d8fc352ce","resolution":{"observed_at":"2026-08-02T07:41:40.826674Z","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":"2026-08-02T07:41:40.979712Z","title":"EfficientNet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:40.979712Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:fbb5fcd3d5411101193686a6758de509114c3a266cf8391c21e78bcb884546bc","observation_id":"c8ee866a-39c1-4bc9-ba00-4dcbdc767d43","resolution":{"observed_at":"2026-08-02T07:41:40.979712Z","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":"2026-08-02T07:41:41.114953Z","title":"EfficientNetV2: Smaller models and faster training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:41.114953Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:6ef522258d9afa9eb3347bb69db17333e8166662e7f847d61bd6ec9c646ecbd2","observation_id":"b2ac9292-67b9-4a12-96db-9c3f66b94436","resolution":{"observed_at":"2026-08-02T07:41:41.114953Z","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":"2026-08-02T07:41:41.261150Z","title":"CNN- generated images are surprisingly easy to spot","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:41.261150Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:018cf2e9df8d0f6eebd9874378eaf31723e9d52be642f4977d2cf13b3082048b","observation_id":"1829bd81-48f2-4cfc-a514-ca5f8536fdf7","resolution":{"observed_at":"2026-08-02T07:41:41.261150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00808","last_updated":"2023-01-02T18:59:31Z","snapshot_observed_at":"2026-08-08T08:01:57.986531Z","submitted_at":"2023-01-02T18:59:31Z","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00808","snapshot_observed_at":"2026-08-02T07:41:41.358271Z","title":"ConvNeXt V2: Co-designing and scaling ConvNets with masked autoencoders","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:41.358271Z"},"links":{"cited_paper":"/paper/2301.00808","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:8aaaf06d4e7fd7984494c194a63f2c86f23429b703c96c3cb5c22846047aac90","observation_id":"cabea251-e2a0-4456-81cf-d9e469812438","resolution":{"observed_at":"2026-08-02T07:41:41.358271Z","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":"2026-08-02T07:41:41.468315Z","title":"Vit-base-patch16-224 fine-tuned on cifar-10","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:41.468315Z"},"links":{"citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:d800f271538154ad01bb01dac4975a97db8f2c8d0783186b40f62fc25ac6fc7c","observation_id":"54774132-428d-4c76-9050-86f59f320eba","resolution":{"observed_at":"2026-08-02T07:41:41.468315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08571","last_updated":"2023-06-24T08:41:47Z","snapshot_observed_at":"2026-08-07T00:33:05.384898Z","submitted_at":"2023-06-14T15:21:09Z","title":"GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08571","snapshot_observed_at":"2026-08-02T07:41:41.612242Z","title":"GenImage: A million-scale benchmark for detecting AI-generated images.arXiv preprint arXiv:2306.08571, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T07:41:41.612242Z"},"links":{"cited_paper":"/paper/2306.08571","citing_paper":"/paper/2607.16283"},"observation_digest":"sha256:df2f070de992419ae5a27166bb4e59129b27b432a85d99f4ca7962b2a98d4699","observation_id":"59fff57b-444c-4a01-82b1-857730138405","resolution":{"observed_at":"2026-08-02T07:41:41.612242Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.16283","last_updated":"2026-07-10T09:47:16Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T13:41:29.483241Z","submitted_at":"2026-07-10T09:47:16Z","title":"GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":53},"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 9 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2607.16283."}