{"as_of":"2026-08-18T05:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c5d0a980c9e8d728d429e52be4587232db91734560e82042ec317c5efe3249da","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T10:52:31.849094Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2603.13419/citation-record","integrity":"/paper/2603.13419/integrity","json":"/paper/2603.13419/citation-record.json","paper":"/paper/2603.13419"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2410.08727","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T23:57:28.804387Z","title":"arXiv preprint arXiv:2410.08727 , year=","venue":null,"work_id":"e2188b07-358a-43f4-9b30-4a484ed962c0","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:4bdf1af95582a7da8a791378cd0f91d448c25eb927e9eb713a594bb1efd22cde","observation_id":"a052bd72-e123-4618-a507-ef8d9a57f8e3","resolution":{"observed_at":"2026-05-21T10:54:07.959101Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.10257","last_updated":"2025-08-29T13:10:29Z","snapshot_observed_at":"2026-08-15T06:09:40.190346Z","submitted_at":"2024-11-15T15:04:04Z","title":"Guiding a diffusion model using sliding windows","version":3},"cited_work":{"arxiv_id":"2411.10257","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.10257","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"78172a09-266b-461f-b6d9-3ea4ca22a212","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2411.10257","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:9b1640452c9845ade9d0314da028dda0877b5bbe889275f4a05bbf8879abf30b","observation_id":"987932e9-def3-4f96-abbf-620db84533bd","resolution":{"observed_at":"2026-05-21T10:54:07.852990Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00570","last_updated":"2024-11-19T11:00:38Z","snapshot_observed_at":"2026-08-16T14:13:44.653809Z","submitted_at":"2024-03-01T14:47:46Z","title":"Rethinking cluster-conditioned diffusion models for label-free image synthesis","version":2},"cited_work":{"arxiv_id":"2403.00570","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.00570","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"org/abs/2403.00570 Diffusion Models Generalize but Not in the Way You Might Think 13","venue":null,"work_id":"8ac6894f-67d0-46c8-b7e0-d5073002d5b9","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2403.00570","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:c55be718ce482af66ae2daa527867cf3e70160eced69c907b06de97b57db0e1e","observation_id":"eaf6bf94-4d38-4b43-b261-1af2df2bb771","resolution":{"observed_at":"2026-05-21T10:54:07.962345Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17377","last_updated":"2025-07-07T04:05:02Z","snapshot_observed_at":"2026-08-16T14:06:25.396562Z","submitted_at":"2024-03-26T04:49:11Z","title":"Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance","version":2},"cited_work":{"arxiv_id":"2403.17377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.17377","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-rectifying diffusion sampling with perturbed-attention guidance","venue":null,"work_id":"f26f9e78-adfe-40e9-afe0-03faf285e8bc","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2403.17377","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:3541ce4f4fb0db9e1b856866cbf86ffe5d1bfc8900840825f84195bef2f36654","observation_id":"b3c42993-02ec-4f07-935d-58179656a0f6","resolution":{"observed_at":"2026-05-21T10:54:07.843749Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41467-024-54281-3","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Nature Communications15(1) (Nov 2024).https://doi.org/10.1038/ s41467-024-54281-3,http://dx.doi.org/10.1038/s41467-024-54281-3","venue":"Nature Communications","work_id":"4c4bd977-b534-4676-9f0b-55c77d356eef","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:ef13ecc25a027ed2aa9e0a608cbfabde6e55924d7aab55489f3f0d241ed4d2a5","observation_id":"3207ff2e-52f5-419a-801b-b3c2b6a1524e","resolution":{"observed_at":"2026-05-21T10:54:07.764461Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-17T12:45:30.627161Z","submitted_at":"2023-11-25T22:28:38Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","version":1},"cited_work":{"arxiv_id":"2311.15127","doi":"10.48550/arxiv.2311.15127","metadata_source":"pith","pith_arxiv_id":"2311.15127","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","venue":"cs.CV","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:df71ac5cf3687f263a1630e8e599bba8fbc1e38f10c4874f4a4ef174a4ad3c95","observation_id":"3340802a-9236-4664-a6a6-59bf2696661f","resolution":{"observed_at":"2026-05-21T10:54:07.883723Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-07-11T15:53:24.472993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T15:53:24.472993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.17638","doi":"10.48550/arxiv.2505.17638","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"& Mézard, M.Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in TrainingarXiv:2505.17638 [cs]","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","work_id":"8d093768-810c-4001-906b-d7feae97c429","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:139ac9afe10ed8add612291453735e8000442a908ef1b008d651705f8a9b8f4c","observation_id":"592e771a-b7ab-430d-a100-32f5d3ffdfed","resolution":{"observed_at":"2026-05-21T10:54:07.908351Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.17689","last_updated":"2025-08-25T05:56:05Z","snapshot_observed_at":"2026-08-16T23:05:12.293350Z","submitted_at":"2025-08-25T05:56:05Z","title":"On the Edge of Memorization in Diffusion Models","version":1},"cited_work":{"arxiv_id":"2508.17689","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.17689","snapshot_observed_at":"2026-07-02T11:46:55.233145Z","title":"On the edge of memorization in diffusion models","venue":null,"work_id":"4a86cc98-6fd9-466b-adb4-e0c7865db49f","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2508.17689","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:1b0c832a393f79b8f3bf575d543ed06c2a6924baef4122bca9faccfdf1dc2d95","observation_id":"0bf5aa68-eec2-4d8b-9091-80f0e0a521c7","resolution":{"observed_at":"2026-05-21T10:54:07.976965Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03216","last_updated":"2021-12-29T12:35:57Z","snapshot_observed_at":"2026-08-16T18:19:17.290618Z","submitted_at":"2021-06-06T19:33:04Z","title":"On Memorization in Probabilistic Deep Generative Models","version":4},"cited_work":{"arxiv_id":"2106.03216","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.03216","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"33b2e90f-b906-4072-b93e-627c01e0944d","year":2021},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2106.03216","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:b49141b48db3b0bc7545d4d541d9f235f2e8613cb77d842cfdc8a9631406fa71","observation_id":"2263f37d-a183-47af-90db-1190b7f573d2","resolution":{"observed_at":"2026-05-21T10:54:07.950843Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13188","last_updated":"2023-01-30T18:53:09Z","snapshot_observed_at":"2026-08-16T15:59:03.518014Z","submitted_at":"2023-01-30T18:53:09Z","title":"Extracting Training Data from Diffusion Models","version":1},"cited_work":{"arxiv_id":"2301.13188","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.13188","snapshot_observed_at":"2026-06-29T08:53:16.273989Z","title":"Extracting training data from diffusion models","venue":null,"work_id":"46927175-5a5c-4357-a334-b29fcf6f7c8e","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2301.13188","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:d4862e4c8eb08ca6e97f8877f5d4813ba3f9b0659a6f7b7efe5c56e6aa39deb7","observation_id":"cd70add8-0503-4ce2-9bb6-babab1a4db19","resolution":{"observed_at":"2026-05-21T10:54:07.928206Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21665","last_updated":"2025-04-25T03:20:52Z","snapshot_observed_at":"2026-08-16T13:05:08.708696Z","submitted_at":"2024-10-29T02:16:01Z","title":"Exploring Local Memorization in Diffusion Models via Bright Ending Attention","version":2},"cited_work":{"arxiv_id":"2410.21665","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.21665","snapshot_observed_at":"2026-07-01T15:05:48.268574Z","title":"Exploring local memorization in diffusion models via bright ending attention","venue":null,"work_id":"060dc838-2e66-4652-957e-293b35a55157","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2410.21665","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:3370fa15ade37dcdbe585a99987d790059d1c3ea7c8be9e7216bd10f39278167","observation_id":"77e31558-803d-4d2d-972d-eb51b3c2116a","resolution":{"observed_at":"2026-05-21T10:54:07.930849Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07023","last_updated":"2020-06-15T23:01:14Z","snapshot_observed_at":"2026-08-14T14:15:41.462243Z","submitted_at":"2019-11-16T12:54:05Z","title":"Effectively Unbiased FID and Inception Score and where to find them","version":3},"cited_work":{"arxiv_id":"1911.07023","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1911.07023","snapshot_observed_at":"2026-07-01T17:05:51.276966Z","title":null,"venue":null,"work_id":"207926cf-e76b-4ede-8977-30575f483a84","year":2020},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/1911.07023","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:4507b26e7748814a78550adb57b2a1853ed0057620829f41c4a485c3ab09d23f","observation_id":"1abd36ef-fd1c-4a28-b791-7ef2a53bb13b","resolution":{"observed_at":"2026-05-21T10:54:07.970353Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41551-025-01468-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Nature Biomedical Engineering (2025) https://doi.org/ 10.1038/s41551-025-01468-8","venue":"Nature Biomedical Engineering","work_id":"990ceb96-abbc-41c8-bfee-79ec62117708","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:1cac4c80fffd4836239b50b2f4e9ca2af4442109a9952646278e03ba8c6ecfeb","observation_id":"5ef1290b-5a77-4aaa-ac72-bf4de8d8ae39","resolution":{"observed_at":"2026-05-21T10:54:07.760584Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.05233","last_updated":"2021-06-01T17:49:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-05-11T17:50:24Z","title":"Diffusion Models Beat GANs on Image Synthesis","version":4},"cited_work":{"arxiv_id":"2105.05233","doi":"10.48550/arxiv.2105.05233","metadata_source":"pith","pith_arxiv_id":"2105.05233","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Diffusion Models Beat GANs on Image Synthesis","venue":"cs.LG","work_id":"2eb944bb-93ba-462c-8111-4e8c915dd873","year":2021},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2105.05233","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:2dc07b07fdcac022a36381dce486b3f41906f4859f52e1966ff03519a95ae23a","observation_id":"1abe2382-9c44-4f67-89d7-c5479b0498a2","resolution":{"observed_at":"2026-05-21T10:54:07.963991Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-24T01:23:30.424112+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T01:23:30.424112+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.12148","last_updated":"2025-08-16T20:15:16Z","snapshot_observed_at":"2026-08-07T03:43:34.797895Z","submitted_at":"2025-08-16T20:15:16Z","title":"Demystifying Foreground-Background Memorization in Diffusion Models","version":1},"cited_work":{"arxiv_id":"2508.12148","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.12148","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"org/abs/2508.12148","venue":null,"work_id":"0ebef789-5876-4a95-be6d-9c0b4296284d","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2508.12148","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:8032787f01922f2b63876890677a4218dca07b1ffcdca2c19cab6d127cef4bd8","observation_id":"cccd3f03-40e5-481f-9fc6-297fd053dd0b","resolution":{"observed_at":"2026-05-21T10:54:07.918794Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07516","last_updated":"2025-02-14T17:24:56Z","snapshot_observed_at":"2026-08-16T05:59:30.820706Z","submitted_at":"2025-02-11T12:36:00Z","title":"The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation","version":2},"cited_work":{"arxiv_id":"2502.07516","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.07516","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint (2025),https: //arxiv.org/abs/2502.07516","venue":null,"work_id":"fe832163-026c-4a75-808f-31d8aed4c1bd","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2502.07516","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:d69c5dac625ab9ab3410c7ba4faeaedd6442e52e3242141cd8e8f09f5d2c6552","observation_id":"cbe3c3c1-2641-4f16-8f71-9dc2323e3bc6","resolution":{"observed_at":"2026-05-21T10:54:07.941194Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.19458","last_updated":"2025-02-11T12:41:08Z","snapshot_observed_at":"2026-08-16T13:48:04.028702Z","submitted_at":"2024-05-29T19:12:08Z","title":"MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection","version":4},"cited_work":{"arxiv_id":"2405.19458","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.19458","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint (2024),https://arxiv.org/abs/2405.19458","venue":null,"work_id":"74e07562-a363-43d2-9d21-351fb8ba77a4","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2405.19458","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:86fa60f92e56ab8dc860668b43348cb24ab6b71966a9f129a37c363d085058b4","observation_id":"8f89234f-4186-4b39-bb23-9f4c4f7cd1fc","resolution":{"observed_at":"2026-05-21T10:54:07.897661Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.02305","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T14:37:03.126540Z","title":"Diffusion models and the manifold hypothesis: Log-domain smoothing is geometry adaptive","venue":null,"work_id":"ead2f995-7ac1-4634-b15b-70a981385e5d","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:9014548f0380934c549a25dd4b091de6a7081f8cd39da07c9b2441418ba4f9ef","observation_id":"50c7a628-51d4-4794-ad78-664226c8041f","resolution":{"observed_at":"2026-05-21T10:54:07.972921Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.03756","last_updated":"2025-07-04T18:07:06Z","snapshot_observed_at":"2026-08-14T18:34:33.424939Z","submitted_at":"2025-07-04T18:07:06Z","title":"Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis","version":1},"cited_work":{"arxiv_id":"2507.03756","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.03756","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"aaeac76d-2865-4e6b-9b45-bb69d5350c65","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2507.03756","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:f48054f7fa72b1e84e253ea870a55da597b83afbcfd2aefd639625a7d2a6901c","observation_id":"c2fa3806-b403-474f-89d9-cc16a8f99564","resolution":{"observed_at":"2026-05-21T10:54:07.930248Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1310.0425","last_updated":"2013-12-19T22:46:03Z","snapshot_observed_at":"2026-08-15T00:00:45.899266Z","submitted_at":"2013-10-01T18:54:49Z","title":"Testing the Manifold Hypothesis","version":2},"cited_work":{"arxiv_id":"1310.0425","doi":null,"metadata_source":"pith","pith_arxiv_id":"1310.0425","snapshot_observed_at":"2026-07-04T02:59:25.673197Z","title":"Testing the Manifold Hypothesis","venue":"math.ST","work_id":"5553170b-d13e-47bd-9081-230b16bc18c2","year":2013},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/1310.0425","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:85236362304ddadd8f9866f1ce7675080690c3dc76957d22504f4f7fb5ed6a8b","observation_id":"50f6ee56-c480-420a-a4ea-75226d8872f3","resolution":{"observed_at":"2026-05-21T10:54:07.954542Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.23594","last_updated":"2024-10-31T03:08:07Z","snapshot_observed_at":"2026-08-16T14:59:33.399636Z","submitted_at":"2024-10-31T03:08:07Z","title":"How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?","version":1},"cited_work":{"arxiv_id":"2410.23594","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.23594","snapshot_observed_at":"2026-07-02T22:57:26.202515Z","title":"Kaiser et al","venue":null,"work_id":"401bcef7-868c-4d76-918a-d27a71c00240","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2410.23594","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:a07124142ba8b84d494a8d02caf88d7f291566a7e3fbaaa20b4c7e72c2dfc8fb","observation_id":"a1830376-886b-4c27-b137-3f7a53b8347e","resolution":{"observed_at":"2026-05-21T10:54:07.980923Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.00336","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves","venue":null,"work_id":"e2ece9e2-a959-48f9-8f71-a3c63ee8a4d2","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:97ab683e08ad5d93a1e3f4bbad68b47466dcefa67ce190f6e54e4fff80c0a3c3","observation_id":"34d0ced3-21a1-4312-8062-703ea274b56f","resolution":{"observed_at":"2026-05-21T10:54:07.953625Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02664","last_updated":"2025-02-20T06:17:25Z","snapshot_observed_at":"2026-08-16T14:55:12.639975Z","submitted_at":"2023-10-04T09:04:20Z","title":"On Memorization in Diffusion Models","version":2},"cited_work":{"arxiv_id":"2310.02664","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.02664","snapshot_observed_at":"2026-07-10T01:26:43.231633Z","title":"On memorization in diffusion models","venue":"cs.LG","work_id":"b0f9f823-4f4d-4603-8a86-8a24cd20f548","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2310.02664","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:ca937abc0464ad8213e53e442557321ca3a3e79a03eea91b6844686738d199ae","observation_id":"64e2570c-aefd-4c6f-8147-f3b06ad7009b","resolution":{"observed_at":"2026-05-21T10:54:07.948183Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G","venue":null,"work_id":"0fb32965-0a6a-4ad7-9316-0d7184599f5c","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:2cf8062a614d8222d97c991fce43c9adaebbc91a5608d8493f4f792308aa55d0","observation_id":"eeaf3ab5-9c31-4501-a83f-8b6e79cdc05a","resolution":{"observed_at":"2026-05-21T10:54:08.275582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17807","last_updated":"2025-08-06T18:39:59Z","snapshot_observed_at":"2026-08-18T02:09:43.484498Z","submitted_at":"2024-11-26T19:00:01Z","title":"A solvable generative model with a linear, one-step denoiser","version":3},"cited_work":{"arxiv_id":"2411.17807","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17807","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9f4da320-6e10-43b4-a0d0-dc27875fcd85","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2411.17807","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:85596f7f661b20ce98ec5e7f6ae73167f36c676c65d8c8b34c2341baabc226dd","observation_id":"5529318b-ff46-4fc0-8118-4bab545363d5","resolution":{"observed_at":"2026-05-21T10:54:07.984585Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.08500","last_updated":"2018-01-12T14:05:44Z","snapshot_observed_at":"2026-08-14T20:51:33.836666Z","submitted_at":"2017-06-26T17:45:23Z","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","version":6},"cited_work":{"arxiv_id":"1706.08500","doi":"10.48550/arxiv.1706.08500","metadata_source":"pith","pith_arxiv_id":"1706.08500","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","venue":"cs.LG","work_id":"fe24e68f-7467-4ea6-a130-10e1464b876e","year":2017},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/1706.08500","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:faaff07caba8ae9642423b426454caf221714b90c2088195a94acb51a3c1be18","observation_id":"6be701fe-a305-4294-9d7e-8178e6aecc93","resolution":{"observed_at":"2026-05-21T10:54:07.973518Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2cd45356-043c-4ad2-855d-65cf9e030a7a","year":2020},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:1c2e944d2df81742a339d6cde10e84c7c6898cca1f734e8c79f02b0d4f259f1d","observation_id":"b0dfaffb-eb34-41cb-8cf2-2acee4bd10e5","resolution":{"observed_at":"2026-05-21T10:54:08.272925Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-14T06:37:15.299690Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":"2207.12598","doi":"10.1109/cvpr52733.2024.02494","metadata_source":"pith","pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Classifier-Free Diffusion Guidance","venue":"cs.LG","work_id":"acf2c588-c088-4a6c-938e-150ad7c666d7","year":2022},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:94fce4a0953152daa1ca4b5fda1f05ec8581cec1c066de788796d2001117e3c6","observation_id":"f161b3a3-b5dc-4455-aa22-66a2a45c5109","resolution":{"observed_at":"2026-05-21T10:54:07.977375Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9d29f28e-5048-43cd-ac08-d71debb964d5","year":2022},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:c3d7e4ba8533053548f9d8006028dad25efb5bf243b7ba759424cf31e373140c","observation_id":"6b5e94af-972b-4dda-8417-bbdba96f3147","resolution":{"observed_at":"2026-05-21T10:54:08.280672Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00760","last_updated":"2024-10-01T01:04:58Z","snapshot_observed_at":"2026-08-16T13:29:08.820288Z","submitted_at":"2024-08-01T17:59:09Z","title":"Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention","version":2},"cited_work":{"arxiv_id":"2408.00760","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2408.00760","snapshot_observed_at":"2026-06-28T22:42:46.332620Z","title":"Smoothed energy guidance: Guiding diffusion models with reduced energy curvature of attention","venue":null,"work_id":"02ecce87-68f5-4f70-876f-0fb933b1e292","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2408.00760","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:ff25353c13595b2d4da4ae68600315b2070d49ed6de99f54c629c54ee308768f","observation_id":"264ceeb4-074f-464a-b91b-ca25a7abc228","resolution":{"observed_at":"2026-05-21T10:54:07.936322Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00736","last_updated":"2025-05-31T22:51:36Z","snapshot_observed_at":"2026-08-09T04:35:50.309243Z","submitted_at":"2025-05-31T22:51:36Z","title":"IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling","version":1},"cited_work":{"arxiv_id":"2506.00736","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.00736","snapshot_observed_at":"2026-07-01T20:16:12.335677Z","title":"Impact: Iterative mask-based parallel decoding for text-to-audio generation with diffusion modeling","venue":null,"work_id":"5e4f86e3-9d80-44e7-a30f-26e697966e75","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2506.00736","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:0adc3c30808a791b3c9fbb1937b2dfeb7aaf093828a7904911daf512dc304445","observation_id":"5d485529-abfb-4c0c-8453-f9fd9b9aa3a0","resolution":{"observed_at":"2026-05-21T10:54:07.944534Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12661","last_updated":"2023-01-30T04:44:34Z","snapshot_observed_at":"2026-08-17T08:10:22.173010Z","submitted_at":"2023-01-30T04:44:34Z","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","version":1},"cited_work":{"arxiv_id":"2301.12661","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.12661","snapshot_observed_at":"2026-06-28T20:42:37.763677Z","title":"Make-An-Audio: Text-to-audio generation with prompt-enhanced diffusion models","venue":null,"work_id":"a9bc5106-f11c-415f-9d34-fb7a465c5185","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2301.12661","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:08d14cb7cb03cd48a5db208373196646704fadb1406e0c620642e60b189a99d9","observation_id":"57bc67d6-2b79-47a4-8100-e00e957d52b9","resolution":{"observed_at":"2026-05-21T10:54:07.939129Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.04440","last_updated":"2024-03-13T00:48:30Z","snapshot_observed_at":"2026-08-16T15:56:38.547570Z","submitted_at":"2023-02-09T04:57:27Z","title":"Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples","version":4},"cited_work":{"arxiv_id":"2302.04440","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.04440","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"f206491c-c42b-4ae1-b06d-0269c229c12a","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2302.04440","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:0cf1fbf5aa846536bc1b0c14f80ffbbca5b26cd1f3813a453ec275a0103063cc","observation_id":"d4bdb464-573e-489d-b734-4a83c49c31cb","resolution":{"observed_at":"2026-05-21T10:54:07.922078Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02557","last_updated":"2024-04-12T15:48:47Z","snapshot_observed_at":"2026-08-16T14:55:16.039455Z","submitted_at":"2023-10-04T03:30:32Z","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representations","version":3},"cited_work":{"arxiv_id":"2310.02557","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.02557","snapshot_observed_at":"2026-07-10T01:26:43.160993Z","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representations","venue":"cs.CV","work_id":"51bc152c-8aa3-423a-be7f-416a1a429774","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2310.02557","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:c949e4b0cd9e0a3d4115ac2093481ea005575d31a2ec05faa0ff2dafec84f37a","observation_id":"3f530f76-887c-407b-8581-b0320044dc68","resolution":{"observed_at":"2026-05-21T10:54:07.933541Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20292","last_updated":"2025-06-05T05:09:27Z","snapshot_observed_at":"2026-08-16T08:43:12.375693Z","submitted_at":"2024-12-28T22:33:29Z","title":"An analytic theory of creativity in convolutional diffusion models","version":2},"cited_work":{"arxiv_id":"2412.20292","doi":"10.48550/arxiv.2412.20292","metadata_source":"arxiv_reference","pith_arxiv_id":"2412.20292","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An analytic theory of creativity in convolutional diffusion models","venue":"arXiv (Cornell University)","work_id":"f18f1029-2aef-47f7-89fb-2b09fdf163d7","year":1960},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2412.20292","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:26cc8d25257a92272d0fd20e821eb8adbc45ca7c8aed9a0b2d9e429c549dac14","observation_id":"e968bcad-87f7-4717-80fe-e2f2124da6c6","resolution":{"observed_at":"2026-05-21T10:54:07.850284Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00364","last_updated":"2022-10-11T13:20:30Z","snapshot_observed_at":"2026-07-06T13:16:16.926712Z","submitted_at":"2022-06-01T10:03:24Z","title":"Elucidating the Design Space of Diffusion-Based Generative Models","version":2},"cited_work":{"arxiv_id":"2206.00364","doi":"10.48550/arxiv.2206.00364","metadata_source":"pith","pith_arxiv_id":"2206.00364","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Elucidating the Design Space of Diffusion-Based Generative Models","venue":"cs.CV","work_id":"a80a774d-caed-4e4c-9b69-471be05076e6","year":2022},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2206.00364","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:82213600a69f4de1ed713abb13e1e84f6c429bc91507a3654edb4c5568aa0f21","observation_id":"5d91950b-db25-44c8-8d0e-96892e460cbc","resolution":{"observed_at":"2026-05-21T10:54:07.885945Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-07-12T13:49:30.261846+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T13:49:30.261846+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02507","last_updated":"2024-12-19T10:43:11Z","snapshot_observed_at":"2026-08-16T13:46:11.340525Z","submitted_at":"2024-06-04T17:25:59Z","title":"Guiding a Diffusion Model with a Bad Version of Itself","version":3},"cited_work":{"arxiv_id":"2406.02507","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.02507","snapshot_observed_at":"2026-07-08T00:04:22.640093Z","title":"Guiding a diffusion model with a bad version of itself","venue":"cs.CV","work_id":"2f4dfaa0-8682-49ca-975c-b50a6c0b64ec","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2406.02507","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:0393606ec1abb511159da60c2b85d27a546b13d9872b4e3784aab1128a61b9a4","observation_id":"182228c6-3316-4a01-bbfe-ecf641832710","resolution":{"observed_at":"2026-05-21T10:54:07.888714Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.02696","last_updated":"2024-03-20T12:58:14Z","snapshot_observed_at":"2026-08-17T05:24:26.663546Z","submitted_at":"2023-12-05T11:55:47Z","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","version":2},"cited_work":{"arxiv_id":"2312.02696","doi":"10.48550/arxiv.2312.02696","metadata_source":"pith","pith_arxiv_id":"2312.02696","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Analyzing and improving the training dynamics of diffusion models","venue":"cs.CV","work_id":"b4377a41-80c7-4851-9dc6-d16c87170097","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2312.02696","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:953e0081f0081de60767e8a0263870173abb147a0703bc50c4d203bac740276c","observation_id":"892d8635-5ab3-4537-bf89-42fda1773b8f","resolution":{"observed_at":"2026-05-21T10:54:07.938477Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-24T01:23:45.246764+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T01:23:45.246764+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"48010f16-48a6-44a7-aef1-4b5b0f7231d5","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:990cede19004e8433eb64cef99def62472a957b45b23bc4183d3158a4e601c01","observation_id":"0eb3613c-a22d-425f-8f19-cb516787f463","resolution":{"observed_at":"2026-05-21T10:54:08.266654Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6cfe385c-5bf5-4639-8fe1-4f2d87daa878","year":2021},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:f4e64e6888b560a53cb64b675aeeb6067d56d873778a0f11b168956160895663","observation_id":"10b02caa-5bd7-419d-80fd-92d3a4be4dc6","resolution":{"observed_at":"2026-05-21T10:54:08.286411Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.16880","last_updated":"2026-05-28T09:55:39Z","snapshot_observed_at":"2026-08-18T01:23:56.594065Z","submitted_at":"2025-07-22T15:02:38Z","title":"Finding DoRI: Discovery of Retained Images in Diffusion Models","version":3},"cited_work":{"arxiv_id":"2507.16880","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.16880","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Finding dori: Memorization in text-to-image diffusion mod- els is not local","venue":null,"work_id":"84f82599-2d68-4296-b72f-7fbc780f2248","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2507.16880","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:2fb280683e2ddb9eddd7280aa62ae1ffe7bbfa3eaa7091f22920d1b55585f482","observation_id":"bef02f8a-d550-4c20-ae24-4d3917963834","resolution":{"observed_at":"2026-05-29T02:04:54.769376Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12503","last_updated":"2023-09-09T15:27:58Z","snapshot_observed_at":"2026-08-16T15:59:22.404915Z","submitted_at":"2023-01-29T17:48:17Z","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","version":3},"cited_work":{"arxiv_id":"2301.12503","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.12503","snapshot_observed_at":"2026-07-04T11:59:50.469153Z","title":"Audioldm: Text-to-audio generation with latent diffusion models","venue":null,"work_id":"b44ebce5-47f1-4f14-b13b-b5b4eb072d2c","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2301.12503","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:b6a20ade58abb9d749c136cf64dcf28586bec5160de04b584875ee56d59cff51","observation_id":"d8e4dd18-5751-40fe-bcf0-56855f426025","resolution":{"observed_at":"2026-05-21T10:54:07.907159Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2509.09672","doi":"10.48550/arxiv.2509.09672","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Locality in image diffusion models emerges from data statistics","venue":"arXiv (Cornell University)","work_id":"0bcc0d66-767e-428e-b049-710f00fafb47","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:93a75e10c6d780abf1425b8c9794a3002c81cf6d4999f25dcba3d4cd49f8bee8","observation_id":"e4d929fa-93df-439c-9a13-0b1757c0de0e","resolution":{"observed_at":"2026-05-21T10:54:07.927715Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.03150","last_updated":"2024-11-17T00:40:09Z","snapshot_observed_at":"2026-08-17T03:30:36.137886Z","submitted_at":"2024-05-06T04:01:42Z","title":"Video Diffusion Models: A Survey","version":2},"cited_work":{"arxiv_id":"2405.03150","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.03150","snapshot_observed_at":"2026-07-04T02:39:25.583762Z","title":"arXiv preprint arXiv:2405.03150 (2024)","venue":null,"work_id":"7667d445-6839-49aa-9d9a-15034291f7f0","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2405.03150","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:754f219bd1884f33b6ff0b687ea5c4b1c2e53e9f3687b40a5dc6ed3ddc3e0790","observation_id":"6134f40c-ed22-4750-b063-0da622dd201a","resolution":{"observed_at":"2026-05-21T10:54:07.916538Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22971","last_updated":"2024-10-30T12:38:49Z","snapshot_observed_at":"2026-08-16T13:04:33.924831Z","submitted_at":"2024-10-30T12:38:49Z","title":"Private Synthetic Text Generation with Diffusion Models","version":1},"cited_work":{"arxiv_id":"2410.22971","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.22971","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ed1604cc-29eb-40eb-812f-af0ebaeec3a8","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2410.22971","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:8e258e65626d0ba0b9dfbdb06e2fb004f5cf21d17d60f377332f681eaf6cb166","observation_id":"9f6d3412-8ad2-4ed0-bb20-516067431f0c","resolution":{"observed_at":"2026-05-21T10:54:07.892093Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-17T13:03:40.359628Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":"2304.07193","doi":"10.48550/arxiv.2304.07193","metadata_source":"pith","pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DINOv2: Learning Robust Visual Features without Supervision","venue":"cs.CV","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:e32f61a810cfa893a92ccff86fa0f22dc9f1cbafd050f5bc68d5d2e18d0352f3","observation_id":"a67bc087-c267-46a6-aa33-830ab19f6f8b","resolution":{"observed_at":"2026-05-21T10:54:07.903814Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d02a6707-dd1c-482e-8fd9-1a0ac812bab7","year":2021},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:a1e6693619b834a92de3ff5ec4985060d373e0adb8c4ea75d2fcab849e3187a1","observation_id":"0e2250ce-9caf-4fd1-a1a0-d2bf9d2dbaa7","resolution":{"observed_at":"2026-05-21T10:54:08.278778Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.11052","last_updated":"2025-06-29T22:08:04Z","snapshot_observed_at":"2026-08-16T14:09:09.103201Z","submitted_at":"2024-03-17T01:27:00Z","title":"Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention","version":2},"cited_work":{"arxiv_id":"2403.11052","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.11052","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b3938dac-5000-418f-bdd7-b3f0dff1711b","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2403.11052","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:5fc553f67690c58510e66fcab2c9e9d6a2800ab11949c5c9eea4402e3505a635","observation_id":"4b89b864-a8d3-4af4-b98e-ca5d083ed309","resolution":{"observed_at":"2026-05-21T10:54:07.925088Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10752","last_updated":"2022-04-13T11:38:44Z","snapshot_observed_at":"2026-07-06T12:20:47.369918Z","submitted_at":"2021-12-20T18:55:25Z","title":"High-Resolution Image Synthesis with Latent Diffusion Models","version":2},"cited_work":{"arxiv_id":"2112.10752","doi":"10.48550/arxiv.2112.10752","metadata_source":"pith","pith_arxiv_id":"2112.10752","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"High-Resolution Image Synthesis with Latent Diffusion Models","venue":"cs.CV","work_id":"f0270d36-2952-47fb-84c1-95e3ec341126","year":2021},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2112.10752","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:62b3599aa1c0197e531497533f3e437ea2ff0230573033b680f0aaa0b1e7eea4","observation_id":"4f3d3257-5429-4c19-aa5d-eb998df40cb3","resolution":{"observed_at":"2026-05-21T10:54:07.956262Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-24T01:24:00.877132+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T01:24:00.877132+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12395","last_updated":"2025-05-05T19:12:30Z","snapshot_observed_at":"2026-08-16T14:50:53.511704Z","submitted_at":"2023-10-19T00:45:05Z","title":"Closed-Form Diffusion Models","version":3},"cited_work":{"arxiv_id":"2310.12395","doi":"10.48550/arxiv.2310.12395","metadata_source":"pith","pith_arxiv_id":"2310.12395","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Closed-form diffusion models.arXiv preprint arXiv:2310.12395","venue":"cs.LG","work_id":"23f8506c-50c6-48e9-976b-6c3255384ce1","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2310.12395","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:065fc1bf7d2765dca215711f9de88b9bbd36cdbd36f32e0bef1b2ef2b94f859d","observation_id":"c305036c-fd18-4a7f-8fc6-e6ca6078789b","resolution":{"observed_at":"2026-05-21T10:54:07.949189Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-07-18T14:51:21.587659+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T14:51:21.587659+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.21278","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"org/abs/2502.21278","venue":null,"work_id":"670650b4-f43b-433e-a012-a9b01d940986","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:0563838f1ad18f0099269257e7d83e29cbbcd1e806b198ee15f69e1f52eef405","observation_id":"9711308c-6c24-45c8-9787-d78d74ea6792","resolution":{"observed_at":"2026-05-21T10:54:07.935654Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"599f3ae2-a731-47ac-a98b-61c74e179bf2","year":2015},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:ff0c1bb3ad38ea80f3739f7fd181d78b4b4ef6a562eb0ac19cd76ecbacb4579d","observation_id":"f57b6681-0419-4fda-acea-4b81060db278","resolution":{"observed_at":"2026-05-21T10:54:08.261177Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03860","last_updated":"2022-12-12T18:52:13Z","snapshot_observed_at":"2026-08-17T14:09:41.133913Z","submitted_at":"2022-12-07T18:58:02Z","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","version":3},"cited_work":{"arxiv_id":"2212.03860","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2212.03860","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ae9c7ca1-3676-42d3-ada2-2300b7d3e64d","year":2022},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2212.03860","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:906a098f9eb87a8b393cb1f8613a94a02ccd91101b73a89f2c74d39663ed29ea","observation_id":"d79dda92-dc0a-48dd-8369-fef1aa326e5a","resolution":{"observed_at":"2026-05-21T10:54:07.932720Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"f1fe0b1c-95d1-4a5b-89fe-58572f3c5bd9","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:e74755f0948f3ce214a4609349a5e4395c49ffa323833380adecc24045bf082c","observation_id":"fd3d35d2-92ad-45b4-aa68-533a5ffbcf7a","resolution":{"observed_at":"2026-05-21T10:54:08.293982Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.05600","last_updated":"2020-10-10T07:46:19Z","snapshot_observed_at":"2026-08-01T16:44:46.833530Z","submitted_at":"2019-07-12T07:37:26Z","title":"Generative Modeling by Estimating Gradients of the Data Distribution","version":3},"cited_work":{"arxiv_id":"1907.05600","doi":"10.48550/arxiv.1907.05600","metadata_source":"pith","pith_arxiv_id":"1907.05600","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Generative Modeling by Estimating Gradients of the Data Distribution","venue":"cs.LG","work_id":"8ad170e5-27c5-474b-aae5-bbbdcf73b90a","year":2019},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/1907.05600","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:29bb9bd0b212df79938ec5288fb68eb8493e4136b7a5067d295f5cfc794bf493","observation_id":"edb9e23d-9f0d-4da9-856b-4a25c4418e41","resolution":{"observed_at":"2026-05-21T10:54:07.951967Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-05-19T16:23:26.520269+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-19T16:23:26.520269+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"cc404818-ba22-4d15-bd67-304c983b5985","year":2021},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:3abe759f17600a640cad4f16aa706e8b951a650e2a2e936eec6ff7d2b3328c0c","observation_id":"29ef331a-208d-4de0-b8d7-e2f5ff58a40a","resolution":{"observed_at":"2026-05-21T10:54:08.291567Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04675","last_updated":"2023-10-30T18:00:00Z","snapshot_observed_at":"2026-08-16T15:25:44.417482Z","submitted_at":"2023-06-07T18:00:00Z","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","version":2},"cited_work":{"arxiv_id":"2306.04675","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.04675","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2306.04675 [cs.LG]https://arxiv.org/abs/2306.04675 Jente Vandersanden, Sascha Holl, Xingchang Huang, and Gurprit Singh","venue":null,"work_id":"6f7453d8-dd67-4fa5-a028-fb1b44792195","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2306.04675","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:b8b8809a9ca1cb2720976f7d17e1270caeeebd7d00d290d8b4d4ec70d8dae218","observation_id":"692d4561-a985-4f72-9d21-3160f45641eb","resolution":{"observed_at":"2026-05-21T10:54:07.870843Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.01844","last_updated":"2016-04-24T20:03:35Z","snapshot_observed_at":"2026-08-14T22:24:38.656852Z","submitted_at":"2015-11-05T18:22:44Z","title":"A note on the evaluation of generative models","version":3},"cited_work":{"arxiv_id":"1511.01844","doi":null,"metadata_source":"pith","pith_arxiv_id":"1511.01844","snapshot_observed_at":"2026-07-10T23:47:46.754736Z","title":"A note on the evaluation of generative models","venue":"stat.ML","work_id":"ba3b1e19-120f-452f-8ab9-b7cdb959c36a","year":2015},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/1511.01844","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:357c0770036113d2f28805f2fc2ae813162995429427b34b8a848f5a790cbacd","observation_id":"ce75045c-b4ce-4203-8b54-4c5cdb563c34","resolution":{"observed_at":"2026-05-21T10:54:07.960941Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05898","last_updated":"2025-04-11T16:19:15Z","snapshot_observed_at":"2026-08-16T13:11:34.060251Z","submitted_at":"2024-10-08T10:55:40Z","title":"Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion","version":7},"cited_work":{"arxiv_id":"2410.05898","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.05898","snapshot_observed_at":"2026-07-10T01:26:43.237278Z","title":"Kaiser et al","venue":"stat.ML","work_id":"49136ee9-39fd-485b-8ef2-ac9740c354b8","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2410.05898","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:de6226cd32a4dfb01ff0498058b733d4493de678f2e2b9f62bd46f4d6981a951","observation_id":"b55b5e8c-517a-4227-9394-5c2caf09ea36","resolution":{"observed_at":"2026-05-21T10:54:07.910932Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15103","last_updated":"2023-09-27T03:51:52Z","snapshot_observed_at":"2026-08-17T12:21:00.357059Z","submitted_at":"2023-09-26T17:52:03Z","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","version":2},"cited_work":{"arxiv_id":"2309.15103","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.15103","snapshot_observed_at":"2026-06-29T18:43:51.114876Z","title":"Lavie: High-quality video gener- ation with cascaded latent diffusion models","venue":null,"work_id":"e26464f0-6aed-49c2-b00f-e3639b1da5b1","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2309.15103","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:bb75ffa3bafaf4bb1a5311fa3efa2e46e85dbc663efd8396b1b1f28c364f1005","observation_id":"aed1d325-c14b-40f6-ac9a-77c1fa19ec6f","resolution":{"observed_at":"2026-05-21T10:54:07.916209Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21357","last_updated":"2025-03-07T04:28:45Z","snapshot_observed_at":"2026-08-16T13:05:17.774393Z","submitted_at":"2024-10-28T17:25:56Z","title":"Energy-Based Diffusion Language Models for Text Generation","version":4},"cited_work":{"arxiv_id":"2410.21357","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.21357","snapshot_observed_at":"2026-07-03T17:38:43.641550Z","title":"Energy-based diffusion language models for text generation.arXiv preprint arXiv:2410.21357","venue":null,"work_id":"754d42d5-957c-400b-b214-b37945f90fe6","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"cited_paper":"/paper/2410.21357","citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:620eb15a2dfcae6617d351f12d5fd7d7ec7f19ddc9a047add6cf7d19b7738e73","observation_id":"b3e48828-8c16-49c9-b6c6-70b1bdb618d6","resolution":{"observed_at":"2026-05-21T10:54:07.924812Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b71c9b19-c43e-46c9-a96f-a9c372ade9a9","year":2025},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:b4fca186bbc30c386b4274002d09365cd2e9780692be7fe1a4cb1949b8308531","observation_id":"1850232d-3c9b-430e-9ad2-d78bfd24506d","resolution":{"observed_at":"2026-05-21T10:54:08.288758Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.7717/peerj-cs.1905","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"PeerJ Computer Science10, e1905 (2024).https://doi.org/ 10.7717/peerj-cs.1905,https://doi.org/10.7717/peerj-cs.1905","venue":"PeerJ Computer Science","work_id":"0500f485-b5c8-4740-9619-2665be1a9631","year":2024},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:0853945909f02cede3e64f93d810a73c63e92f7045451382bf530424915f813f","observation_id":"77e9f3f5-0644-48ef-9c3e-fb5d22623345","resolution":{"observed_at":"2026-05-21T10:54:07.762369Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6b55071e-cb7e-4551-ad83-fe9b2eb0eaca","year":2023},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:84dfebec7004f40c035732fb4f467d927bc72e26e89475d9543f8bd34394b376","observation_id":"e6198d68-04d1-4be1-b5ef-25f680ad98ae","resolution":{"observed_at":"2026-05-21T10:54:08.269498Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"646eca17-70ed-480b-9d5d-e3b2929a2384","year":null},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:923985de891172d078a7588a28d668c7f90e6c584a64333ffc86a6edcfcfde9c","observation_id":"e1144afe-6e69-4b66-b356-e702b0c111a3","resolution":{"observed_at":"2026-05-21T10:54:08.283655Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6db4f4b0-1be1-4c0f-9889-c05da3b9f43d","year":null},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:ed43cc3eee67f147530bea7a983faaaedcc5986aa232f8355d8a246996085e8b","observation_id":"88433fe5-d954-4e40-8aa7-81c55265ead3","resolution":{"observed_at":"2026-05-21T10:54:08.278304Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Train\" shows the average results between 20 different subsets of the training data","venue":null,"work_id":"ce6061a1-5872-4e16-a908-48e97bebe5d5","year":null},"citing_paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-21T10:52:31.849094Z"},"links":{"citing_paper":"/paper/2603.13419"},"observation_digest":"sha256:31224d0531796062d0a89184dd208cc3244383cfb661746c8583d796f53eef52","observation_id":"4189ac88-2aee-4699-ba8f-1ee17f67aac3","resolution":{"observed_at":"2026-05-21T10:54:08.286727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2603.13419","last_updated":"2026-05-20T10:08:19Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T16:47:23.439569Z","submitted_at":"2026-03-12T21:02:17Z","title":"Diffusion Models Memorize in Training -- and Generalize in Inference"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":53,"verified_fuzzy":2},"total_outbound_references":67},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:2603.13419."}