{"as_of":"2026-08-19T00:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d049dce255f5f26ef661eedd4e8ba1b353cd424a881b6f41ae2dc46d06552a12","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:53:26.038689Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.11825/citation-record","integrity":"/paper/2505.11825/integrity","json":"/paper/2505.11825/citation-record.json","paper":"/paper/2505.11825"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/0304-4149(82)90058-0","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:26.072476Z","title":null,"venue":null,"work_id":"d16af350-e90e-4749-99a2-6e8807e32094","year":1982},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:24.951388Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:6dafdc0477d0291a88af27d218273d2b891adcdd5dd8219725a1d5959ae98e8a","observation_id":"da5ba79a-33d3-4522-9f3b-04bf68c8b79b","resolution":{"observed_at":"2026-08-15T20:53:26.076663Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:25.038646Z","title":"Weighted sums of certain dependent random variables","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.038646Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:aa7bd34e18edaca9ad26f8fac805b9ce7f2a65a94dfdb8408c2996e586df9d5a","observation_id":"40b9c7d0-8e4c-4670-a522-a238c3707d15","resolution":{"observed_at":"2026-08-15T20:53:25.038646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01014","last_updated":"2026-06-26T09:13:36Z","snapshot_observed_at":"2026-08-16T13:38:15.144902Z","submitted_at":"2024-07-01T07:00:17Z","title":"An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01014","snapshot_observed_at":"2026-08-15T20:53:25.071410Z","title":"An expectation-maximization algorithm for training clean diffusion models from corrupted observations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.071410Z"},"links":{"cited_paper":"/paper/2407.01014","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:013ec84354a9b9cc4f5f77dc2bee045f390d69a4fc52d76d3e29f8a17b86cbda","observation_id":"d10701eb-5310-4cd8-b890-6011e655ca50","resolution":{"observed_at":"2026-08-15T20:53:25.071410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:27.627666Z","title":"Webvid-10m: A large-scale video-text dataset","venue":null,"work_id":"ce626d38-683c-4f41-90da-d35a49f9e730","year":2021},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.080677Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:dcd17b685e4ef9679985b43c0dc6a11709b968525e7cdb3bc767f077e4ee6198","observation_id":"f59b8538-6568-480a-889a-4722421c4f7e","resolution":{"observed_at":"2026-08-15T20:53:27.631973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:27.496371Z","title":null,"venue":null,"work_id":"241699ac-0fc5-4a61-a207-6830ccd6ba48","year":2002},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.085690Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:089f71b1dd7f1193b31fc01e36893792d1eb5291ae7010c18838c20f4bdb84b0","observation_id":"b93c2408-3cb1-49a2-a2ba-7f88f212cb79","resolution":{"observed_at":"2026-08-15T20:53:27.553062Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:27.485304Z","title":"Probability and Measure","venue":null,"work_id":"14e3e65d-1416-40e8-86aa-51909d481f2a","year":1995},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.121512Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:f63ddd67c9778e2feac32188b05e5bc4e34eed154bb2724a499d387269789983","observation_id":"86f2090f-64ed-4ba1-a1a7-527c9d921a4f","resolution":{"observed_at":"2026-08-15T20:53:27.489127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:27.425656Z","title":"Coyo-700m: Image-text dataset for better text-to-image generation","venue":null,"work_id":"afbe5cbe-26e5-4d61-9422-e3449bfda848","year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.197128Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:e85b60cd2e171ca6301fef7d344b4b883d6ce6a70365d5102d41940318a42556","observation_id":"3e599c75-d1bc-4aba-8bca-f3e30e7f26b9","resolution":{"observed_at":"2026-08-15T20:53:27.478075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.13873","last_updated":"2023-09-27T10:35:49Z","snapshot_observed_at":"2026-08-18T12:03:25.183598Z","submitted_at":"2023-03-24T09:30:09Z","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.13873","snapshot_observed_at":"2026-08-15T20:53:25.275853Z","title":"C., Yu, J., et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.275853Z"},"links":{"cited_paper":"/paper/2303.13873","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:40d2ed44ce85f3a23fd3b6b55625597ade027ae2fe1c4fc1bb0a25f65c8be318","observation_id":"4d63c34b-8ad3-4f41-bc18-3f4bee18c48a","resolution":{"observed_at":"2026-08-15T20:53:25.275853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04493","last_updated":"2023-03-22T00:30:56Z","snapshot_observed_at":"2026-08-16T16:09:58.209267Z","submitted_at":"2022-12-08T18:59:05Z","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04493","snapshot_observed_at":"2026-08-15T20:53:25.280630Z","title":"G., and Gui, L.-Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.280630Z"},"links":{"cited_paper":"/paper/2212.04493","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:5af829eb96d675359f70796b34937e8910f67ecf74c2d42ee670b4a3dba2a643","observation_id":"54d275b4-18d0-4e89-8b4f-f6e14c097d5a","resolution":{"observed_at":"2026-08-15T20:53:25.280630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:27.080449Z","title":"Stargan v2: Diverse image synthesis for multiple domains","venue":null,"work_id":"dc340c7a-f1ed-44da-8ab7-89e0f9000e09","year":2020},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.284576Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:6ca927c4d25f1b970f8bf61427b2df1c8b5787dbdda87b4dc7ef73ee31246f1f","observation_id":"ddc90e95-a73d-4635-9114-008490d6325a","resolution":{"observed_at":"2026-08-15T20:53:27.224758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:26.848577Z","title":"Modelscope text-to-video synthesis","venue":null,"work_id":"baf3f1bf-bf8b-4373-96ce-953e56ecf1af","year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.289062Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:f4dbc5c4c7bbf7226a5ad0114fbfeb5cd0b2db68df0b4dadb7a3153d3f41417d","observation_id":"95f3b144-0ed2-41fb-b4a8-fb0ca2def920","resolution":{"observed_at":"2026-08-15T20:53:26.929654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19256","last_updated":"2023-05-30T17:43:33Z","snapshot_observed_at":"2026-08-17T04:23:45.253909Z","submitted_at":"2023-05-30T17:43:33Z","title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19256","snapshot_observed_at":"2026-08-15T20:53:25.293080Z","title":"G., and Klivans, A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.293080Z"},"links":{"cited_paper":"/paper/2305.19256","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:a5aad4ba9b18216fce3557b993654c2b6d15d3b9f24d1553fb2ba28efad9ee87","observation_id":"1f7cfcd1-1389-4fd7-a548-6ebc72732232","resolution":{"observed_at":"2026-08-15T20:53:25.293080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.10177","last_updated":"2024-07-22T11:31:08Z","snapshot_observed_at":"2026-08-16T16:15:19.805243Z","submitted_at":"2024-03-20T14:22:12Z","title":"Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.10177","snapshot_observed_at":"2026-08-15T20:53:25.296937Z","title":"G., and Daskalakis, C","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.296937Z"},"links":{"cited_paper":"/paper/2404.10177","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:3a118fa6b3d98f095ae8f5198d1ab270e74d68f26bf5d59e3593482e9c6537d0","observation_id":"8f1d16d9-e406-4d29-a4c2-c82ceadfcdf6","resolution":{"observed_at":"2026-08-15T20:53:25.296937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.05233","snapshot_observed_at":"2026-08-15T20:53:25.300694Z","title":"and Nichol, A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.300694Z"},"links":{"cited_paper":"/paper/2105.05233","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:74e963371ffdd2cb14cfae0bd90c795ebcaf4e2071c1523df8b157dcee52abef","observation_id":"48d494ec-9729-4bb1-b819-294fab354f1f","resolution":{"observed_at":"2026-08-15T20:53:25.300694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:26.838235Z","title":null,"venue":null,"work_id":"f1af77ea-12f4-4f3a-8fb7-8bc329321219","year":1953},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.304587Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:bf56dd907dd14b5b16f475701fbe07074a55446161758340c63d53e204eef634","observation_id":"24393ec5-e334-490b-b9cd-49e1e92a2578","resolution":{"observed_at":"2026-08-15T20:53:26.842191Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:25.385937Z","title":"Tweedie’s formula and selection bias","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.385937Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:8c5b4673a96cab16815ac7e77839e7aa58958c7448e375d8979a19b6c86f7baa","observation_id":"ce29af08-04f9-4534-86eb-9ee2d792fc26","resolution":{"observed_at":"2026-08-15T20:53:25.385937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:26.827074Z","title":"MINDE : Mutual information neural diffusion estimation","venue":null,"work_id":"c5735260-a41f-4f72-9ebf-91e9d8718509","year":2024},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.475656Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:039c371d17137e4fc35b76bdfca5ac329af3819cbd1a3dae5049250c09fa95c1","observation_id":"939156fd-c0e8-4514-a3c8-17599695d680","resolution":{"observed_at":"2026-08-15T20:53:26.831426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:26.671254Z","title":"On measuring excess capacity in neural networks","venue":null,"work_id":"9788e6ac-65d0-4392-be51-efb8b5bfea50","year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.575940Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:8f9db824ac09a68b031ff8c03a5cd8e439617db3df042794c3209c6fd34e7ebb","observation_id":"16036120-f588-4f58-9fb3-aa6d0ebc1863","resolution":{"observed_at":"2026-08-15T20:53:26.764051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04725","last_updated":"2024-02-08T18:08:57Z","snapshot_observed_at":"2026-08-17T14:04:31.230742Z","submitted_at":"2023-07-10T17:34:16Z","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04725","snapshot_observed_at":"2026-08-15T20:53:25.580284Z","title":"Animatediff: Animate your personalized text-to-image diffusion model without tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.580284Z"},"links":{"cited_paper":"/paper/2307.04725","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:f8faed772942973ac8868506f5318ffbdae7b093beea57042804269ebf018c89","observation_id":"083688d1-2334-4745-9720-600ea37f3d00","resolution":{"observed_at":"2026-08-15T20:53:25.580284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00426","last_updated":"2023-12-29T16:42:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-30T16:18:00Z","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00426","snapshot_observed_at":"2026-08-15T20:53:25.585516Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.585516Z"},"links":{"cited_paper":"/paper/2310.00426","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:c82e5b7543217202950485876227acda5efe5a08a99b21b74d9b1d1d0403c2a4","observation_id":"6887812c-f1f3-4745-8422-c1a750d2b983","resolution":{"observed_at":"2026-08-15T20:53:25.585516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11239","last_updated":"2020-12-16T21:15:05Z","snapshot_observed_at":"2026-08-10T05:21:27.485481Z","submitted_at":"2020-06-19T17:24:44Z","title":"Denoising Diffusion Probabilistic Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11239","snapshot_observed_at":"2026-08-15T20:53:25.589583Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.589583Z"},"links":{"cited_paper":"/paper/2006.11239","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:3c9f9735eda5da50c77bb8e023bfdae562255f9d0d804be1ed42b8979aca26a5","observation_id":"4afd0db3-4986-4fda-b39e-5888d10b9f6c","resolution":{"observed_at":"2026-08-15T20:53:25.589583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03458","last_updated":"2022-06-22T20:22:29Z","snapshot_observed_at":"2026-08-17T13:08:14.312126Z","submitted_at":"2022-04-07T14:08:02Z","title":"Video Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03458","snapshot_observed_at":"2026-08-15T20:53:25.594159Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.594159Z"},"links":{"cited_paper":"/paper/2204.03458","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:49953788ef1596b20936b27262510e305aebf273a1779a496fc78af471dc3436","observation_id":"6a697472-ad21-4206-9fb9-e30dee7f3ad0","resolution":{"observed_at":"2026-08-15T20:53:25.594159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00364","snapshot_observed_at":"2026-08-15T20:53:25.643212Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.643212Z"},"links":{"cited_paper":"/paper/2206.00364","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:037b2a61dd40b4c5862555878ac20b18a249af976e86861b7c5203135b8850bb","observation_id":"11fb1fb5-0810-47bd-9769-d871a9906147","resolution":{"observed_at":"2026-08-15T20:53:25.643212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13128","last_updated":"2024-06-13T18:11:45Z","snapshot_observed_at":"2026-08-16T15:31:03.097816Z","submitted_at":"2023-05-22T15:27:20Z","title":"GSURE-Based Diffusion Model Training with Corrupted Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13128","snapshot_observed_at":"2026-08-15T20:53:25.693113Z","title":"Gsure-based diffusion model training with corrupted data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.693113Z"},"links":{"cited_paper":"/paper/2305.13128","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:9509703e6c9d8f92a2e13f87c2e63b07198a88fb018389b220860de8d6e99352","observation_id":"628aa308-6636-47e7-bb95-22fa44fb1796","resolution":{"observed_at":"2026-08-15T20:53:25.693113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:25.762636Z","title":"Scaling laws for diffusion transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.762636Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:5cade70f37fe3b58ea6440e5356b68071477a77cfc984f49c751ed4ccaec381b","observation_id":"5b0297ca-1966-416f-ba15-fb13af3a232e","resolution":{"observed_at":"2026-08-15T20:53:25.762636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10440","last_updated":"2023-03-25T17:32:25Z","snapshot_observed_at":"2026-08-16T16:15:01.108853Z","submitted_at":"2022-11-18T18:59:59Z","title":"Magic3D: High-Resolution Text-to-3D Content Creation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.10440","snapshot_observed_at":"2026-08-15T20:53:25.766168Z","title":"Magic3d: High-resolution text-to-3d content creation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.766168Z"},"links":{"cited_paper":"/paper/2211.10440","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:99059557512294c2f4104a634fbacec5fad3d82bc4608eb259711c30b5d3ae98","observation_id":"20ea443d-1e22-4cb3-9987-9ee314f1181b","resolution":{"observed_at":"2026-08-15T20:53:25.766168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:26.659903Z","title":"and Upfal, E","venue":null,"work_id":"d1d94946-dbfe-4f72-99b0-51f56ae7ea23","year":2017},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.770527Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:32ef6d6f126cb40f02349e9f697d5e758c7d3558902f2c6b9db92890862d5dca","observation_id":"5c7281cc-8caa-45cb-a0fd-f5303a7e3b71","resolution":{"observed_at":"2026-08-15T20:53:26.664230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:26.542039Z","title":"Sora: World-modeling text-to-video generation","venue":null,"work_id":"350380ce-f6e2-409b-a7d9-75cb21351142","year":2025},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.775924Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:0c65ace51fe351f60294271c16e59926c958f92e05143bc63620763a90a79cc0","observation_id":"e21e93f4-51bf-4439-a6b6-1e8bc01da845","resolution":{"observed_at":"2026-08-15T20:53:26.623951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14988","last_updated":"2022-09-29T17:50:40Z","snapshot_observed_at":"2026-07-06T13:57:54.539656Z","submitted_at":"2022-09-29T17:50:40Z","title":"DreamFusion: Text-to-3D using 2D Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14988","snapshot_observed_at":"2026-08-15T20:53:25.779137Z","title":"T., Mildenhall, B., Duan, Y., Nichol, A., Dhariwal, P., Abbeel, P., Dinh, L., and Chan, E","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.779137Z"},"links":{"cited_paper":"/paper/2209.14988","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:e8f47653324dd18d767aa54a4e2fdc4f9d1d59818b2f7c6b13c6b572f8a567d1","observation_id":"f50f1379-84ab-4471-8f1b-737723a55af5","resolution":{"observed_at":"2026-08-15T20:53:25.779137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10752","snapshot_observed_at":"2026-08-15T20:53:25.783352Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.783352Z"},"links":{"cited_paper":"/paper/2112.10752","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:45b31a5bbcac1b0497a612d867d70e3e7706a13c5dd2d860ee9deac3dfcd54eb","observation_id":"a921e936-d0ae-45d0-a308-0bfbbf4bb2fb","resolution":{"observed_at":"2026-08-15T20:53:25.783352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.08402","last_updated":"2022-10-16T00:08:18Z","snapshot_observed_at":"2026-08-13T17:36:16.794649Z","submitted_at":"2022-10-16T00:08:18Z","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.08402","snapshot_observed_at":"2026-08-15T20:53:25.787543Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.787543Z"},"links":{"cited_paper":"/paper/2210.08402","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:d3dbf00900636ac1d47132cf746e51a320238ec1be179b5ec6eb4d6b56f3fff2","observation_id":"dec37ba6-9df4-4411-ac63-d584064c7762","resolution":{"observed_at":"2026-08-15T20:53:25.787543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.03585","last_updated":"2015-11-18T21:50:51Z","snapshot_observed_at":"2026-07-06T04:11:47.439779Z","submitted_at":"2015-03-12T04:51:37Z","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.03585","snapshot_observed_at":"2026-08-15T20:53:25.791322Z","title":"A., Maheswaranathan, N., and Ganguli, S","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.791322Z"},"links":{"cited_paper":"/paper/1503.03585","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:696b91459127987a8b85a4620c03abd8004e729c60edd604ece2b1fc04bc463d","observation_id":"391ba653-15fc-43bf-ae42-358db6bb8901","resolution":{"observed_at":"2026-08-15T20:53:25.791322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-15T20:53:25.795728Z","title":"P., Kumar, A., Ermon, S., and Poole, B","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.795728Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:a33a31c6cb96779a42e01a202825f868c75e5c4a1f872da415e747cea4820d2e","observation_id":"55d11964-8109-45e5-9332-ddc616ce2800","resolution":{"observed_at":"2026-08-15T20:53:25.795728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.08332","last_updated":"2024-01-11T18:20:29Z","snapshot_observed_at":"2026-08-16T16:15:57.340987Z","submitted_at":"2022-11-15T17:44:05Z","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.08332","snapshot_observed_at":"2026-08-15T20:53:25.846415Z","title":"Versatile diffusion: Text, images, and variations all in one diffusion model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.846415Z"},"links":{"cited_paper":"/paper/2211.08332","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:e07027da11242d877263a63592c5e8b447f9768e8dbe4621bc0c3a24c248ec60","observation_id":"33100fc6-3ddb-449e-94f2-18c6b8e398fd","resolution":{"observed_at":"2026-08-15T20:53:25.846415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:26.529312Z","title":"A Little Book of Martingales, volume 78 of Texts and Readings in Mathematics","venue":null,"work_id":"ac8900b6-a0aa-4d00-8711-5ec34bed6bf8","year":2023},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:25.903187Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:bb29e51f1eb2f2d8e61ee6ea65157b59976aa2980f78b4f71e9c1de9221ea31f","observation_id":"53fbe5a7-6fdc-4041-8173-c97178aaab83","resolution":{"observed_at":"2026-08-15T20:53:26.534028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T20:53:26.399933Z","title":null,"venue":null,"work_id":"ce107768-82ea-4985-b9ff-dd37eb88f535","year":2022},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:26.014749Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:cbbf0402be4e3b57d04a83e10bfa89b0045975da7f111fb2386a163c54124b84","observation_id":"d20c9373-b9ba-40fe-b174-675a4a0438f3","resolution":{"observed_at":"2026-08-15T20:53:26.471991Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.03670","last_updated":"2021-08-29T23:03:30Z","snapshot_observed_at":"2026-08-16T18:33:03.363582Z","submitted_at":"2021-04-08T10:38:03Z","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","version":3},"cited_work":{"arxiv_id":"2104.03670","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.03670","snapshot_observed_at":"2026-08-15T20:53:26.086515Z","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","venue":"cs.CV","work_id":"a0fbe502-613d-4581-870a-575bd503503a","year":2021},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:26.035023Z"},"links":{"cited_paper":"/paper/2104.03670","citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:31cc31a0c178f4980a9418a092021cad914259af5881d7607898442956066a80","observation_id":"abfda3bf-a30b-42f7-b7b2-c64180a59dde","resolution":{"observed_at":"2026-08-15T20:53:26.090568Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:26.038689Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T20:53:26.038689Z"},"links":{"citing_paper":"/paper/2505.11825"},"observation_digest":"sha256:0ca70b553a9ca0803ac5547ed5841114166a17888d4dc491ad3770347ca18a99","observation_id":"fb529d8f-dfdd-4089-bb74-1a7c8a5598eb","resolution":{"observed_at":"2026-08-15T20:53:26.038689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.11825","last_updated":"2025-05-17T04:17:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T01:00:42.002252Z","submitted_at":"2025-05-17T04:17:48Z","title":"Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":2,"verified_fuzzy":10},"total_outbound_references":38},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2505.11825."}