{"as_of":"2026-08-10T17:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ac7ea64c836c7776a0c5137e5a6f203e71631f0d9d41e450b0cdb8ff3437189d","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T05:55:58.399181Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2603.06741/citation-record","integrity":"/paper/2603.06741/integrity","json":"/paper/2603.06741/citation-record.json","paper":"/paper/2603.06741"},"outbound":[{"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":"2026-08-04T05:55:55.238174Z","title":"Pixart-𝛼: Fast training of diffusion transformer for photorealistic text-to-image synthesis.arXiv preprint arXiv:2310.00426, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.238174Z"},"links":{"cited_paper":"/paper/2310.00426","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:68443230a2c14ddf755a6cd15f5f8d76ab4c7bc06b8e6fc8244913e22baa9762","observation_id":"ba39eafe-3e9d-446c-b312-b9b8e6e7c6c0","resolution":{"observed_at":"2026-08-04T05:55:55.238174Z","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":"2026-08-04T05:55:55.271847Z","title":"Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.271847Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:0f5a0f49a8fa8404a5439f750fe941750837641d37239ed7f22c3a08bcd0dcf4","observation_id":"9d5e46b2-cd9a-4997-acb3-bec0f45d7b8c","resolution":{"observed_at":"2026-08-04T05:55:55.271847Z","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":"2026-08-04T05:55:55.328842Z","title":"Decentralized learning made easy with decentralizepy","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.328842Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:e24b96ff1c405573f8c5c159a92e733e0dd9d7f9389348b9c4d03943d04a63ea","observation_id":"c7ed50ab-bacf-49a6-88cc-efccdfdc6a98","resolution":{"observed_at":"2026-08-04T05:55:55.328842Z","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":"2026-08-04T05:55:55.371032Z","title":"Efficient diffusion training via min-snr weighting strategy","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.371032Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:727d602a7f6f5d84e4482f28602dfb3749539626544840193bf29a94aa432fe8","observation_id":"16ad01ed-49a5-4acf-94a8-94c3d7d7e46a","resolution":{"observed_at":"2026-08-04T05:55:55.371032Z","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":"2026-08-04T05:55:55.418774Z","title":"Improved noise schedule for diffusion training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.418774Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:fbbae215eaaf2677593dcebefa034a3929bdfdbaf79c7c27f39846f688da6466","observation_id":"93bbd1ed-c888-4a42-a435-96fcde7c6773","resolution":{"observed_at":"2026-08-04T05:55:55.418774Z","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":"2026-08-04T05:55:55.460305Z","title":"Faster training of diffusion models and improved density estimation via parallel score matching","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.460305Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:46ea6422762334701c690b51a93685a5b6add1f654e33795e539da2e346b0c92","observation_id":"0c2151bc-cc49-4fd8-adcb-a69a23d48c5b","resolution":{"observed_at":"2026-08-04T05:55:55.460305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.06807","last_updated":"2024-11-19T14:31:02Z","snapshot_observed_at":"2026-08-03T11:30:00.885783Z","submitted_at":"2024-03-11T15:26:34Z","title":"Multistep Consistency Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.06807","snapshot_observed_at":"2026-08-04T05:55:55.537035Z","title":"Multistep consistency models.arXiv preprint arXiv:2403.06807, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.537035Z"},"links":{"cited_paper":"/paper/2403.06807","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:7742173df0e4a63afba9d9b9c2696ed9bfe5fb3a6207f93f78422a15698b6276","observation_id":"fb47b92f-8ec9-44ec-bc58-dd877e736f30","resolution":{"observed_at":"2026-08-04T05:55:55.537035Z","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":"2026-08-04T05:55:55.597729Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.597729Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:1657d0ec424b637ea9ce7f1282a563cf4b97a8e289a3a4e73d858fa29ef299eb","observation_id":"accdb808-bf00-43fc-a6f9-1e67a6926419","resolution":{"observed_at":"2026-08-04T05:55:55.597729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-04T05:55:55.773277Z","title":"Classifier-free diffusion guidance.arXiv preprint arXiv:2207.12598, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.773277Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:9c0b4fb571a3987d97eecb3740494f6d9b216d747268e9085bfc9c6022a1f69c","observation_id":"298d8214-8e7d-4564-928c-524991f605b1","resolution":{"observed_at":"2026-08-04T05:55:55.773277Z","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":"2026-08-04T05:55:55.972071Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:55.972071Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:e91302fa0647db8d5c2f537b53ba5be930f4040f9c9a2999a4f23e7379b41b4e","observation_id":"9882bec7-bd49-4f94-b855-5f7080149050","resolution":{"observed_at":"2026-08-04T05:55:55.972071Z","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":"2026-08-04T05:55:56.003152Z","title":"Fast-ddpm: Fast denoising diffusion probabilistic models for medical image-to-image generation.IEEE Journal of Biomedical and Health Informatics, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.003152Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:442b7b1826ce2175aca12d3aa7161d1540ef85130548636894f67b7a0d95e3e4","observation_id":"6735913c-f67f-49ac-a68e-f05452dce7ea","resolution":{"observed_at":"2026-08-04T05:55:56.003152Z","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":"2026-08-04T05:55:56.064629Z","title":"Kingma and Ruiqi Gao","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.064629Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:95debcc1f307f64886d4051a8c319f13417e16f380a553668feb08fd03e570db","observation_id":"f7f02390-be27-49b5-a873-6254e2191db1","resolution":{"observed_at":"2026-08-04T05:55:56.064629Z","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":"2026-08-04T05:55:56.110309Z","title":"Kingma, Tim Salimans, Ben Poole, and Jonathan Ho","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.110309Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:0dc495453a4378acb1a50b7890a9e8af0b8065d23999f2b2f77563e75c134442","observation_id":"15da1229-b5b9-4a1d-a457-1836b5bcd5ee","resolution":{"observed_at":"2026-08-04T05:55:56.110309Z","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":"2026-08-04T05:55:56.163728Z","title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.163728Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:fd19d69b616d85103e8e34da7c720da2570fc6aab8695dd62bc6b615fa6f4e6d","observation_id":"bede5c56-a8d5-40a5-b178-cad06d9885b3","resolution":{"observed_at":"2026-08-04T05:55:56.163728Z","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":"2026-08-04T05:55:56.255942Z","title":"Laion-aesthetics v2: Aesthetic-filtered subset of laion-5b","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.255942Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:196b008b651406d5f56f0f021ab87ce5909e018947ccf7034380fa2cff891abe","observation_id":"f5859bb6-4467-4705-8c6d-e4fbebdb0585","resolution":{"observed_at":"2026-08-04T05:55:56.255942Z","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":"2026-08-04T05:55:56.306198Z","title":"Improving the training of rectified flows.Advances in neural information processing systems, 37:63082–63109, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.306198Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:53b09eca9f433f9992572437a1ff089c9ea34bfad1d0e6eb5697aa39b9c4d34e","observation_id":"cc664b8c-6e6f-4390-b205-a6c3ce823d93","resolution":{"observed_at":"2026-08-04T05:55:56.306198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.16668","last_updated":"2020-06-30T10:42:02Z","snapshot_observed_at":"2026-08-07T09:27:36.420559Z","submitted_at":"2020-06-30T10:42:02Z","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16668","snapshot_observed_at":"2026-08-04T05:55:56.337455Z","title":"Gshard: Scaling giant models with conditional computation and automatic sharding.arXiv preprint arXiv:2006.16668, 2021","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.337455Z"},"links":{"cited_paper":"/paper/2006.16668","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:e925719a6a24136c765e5d0feb75d80d10a3391209cbeab9fa03fbc7f2b40a42","observation_id":"40b05386-bab1-4d67-9a40-44dd2d944862","resolution":{"observed_at":"2026-08-04T05:55:56.337455Z","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":"2026-08-04T05:55:56.376797Z","title":"Distrifusion: Distributed parallel inference for high-resolution diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.376797Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:a431340b025b7e2c84e36574f6e538de2c892660474d35f95e4a94f8b6f12753","observation_id":"a1641c5d-3d86-4bbf-9dc1-8cceff5ea97a","resolution":{"observed_at":"2026-08-04T05:55:56.376797Z","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":"2026-08-04T05:55:56.410296Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.410296Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:1b03c05075ae8c2f6791d1ac9b366e70f2d466cde9657a8a3f1303609d576863","observation_id":"6d18e90e-ca61-4126-8ca9-1a8d101608b5","resolution":{"observed_at":"2026-08-04T05:55:56.410296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-04T05:55:56.443341Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.443341Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:e9babeb8050e3c5b6aea14ea8d50e1e905b73969d9a3923b3ebe9ab101728f48","observation_id":"a2aeacd1-94cf-4427-93ff-74668e80f6e7","resolution":{"observed_at":"2026-08-04T05:55:56.443341Z","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":"2026-08-04T05:55:56.477935Z","title":"Optimal complexity in decentralized training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.477935Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:ec2fbdaf5de266bb5ead801bb180b253c49cee266571d18ede1561ede4e84ea4","observation_id":"38e93e07-da27-4989-a47d-dc439fe5d404","resolution":{"observed_at":"2026-08-04T05:55:56.477935Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.05450","last_updated":"2025-01-10T18:58:11Z","snapshot_observed_at":"2026-08-08T05:31:26.044307Z","submitted_at":"2025-01-09T18:59:56Z","title":"Decentralized Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.05450","snapshot_observed_at":"2026-08-04T05:55:56.526484Z","title":"Decentralized diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.526484Z"},"links":{"cited_paper":"/paper/2501.05450","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:f4f5e80dbe1bfd4223f10f62ffc2b63e5186f6e09fecdfd07c98c8a55a3b6a1e","observation_id":"b12cf6d0-8f54-42d4-b224-4776f85be58f","resolution":{"observed_at":"2026-08-04T05:55:56.526484Z","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":"2026-08-04T05:55:56.599263Z","title":"On distillation of guided diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.599263Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:74ba7832f02f617d46f7f88c27f487ea7a69bdcda955433cb6765ab89dcfffc1","observation_id":"253dbb3f-066a-46d7-a818-98bacbfe9cb9","resolution":{"observed_at":"2026-08-04T05:55:56.599263Z","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":"2026-08-04T05:55:56.654105Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.654105Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:c28e93b5f66839fb324082f90438d6c95fc3350bccfede48c81468cc350d7db9","observation_id":"ed601d30-fbfe-448e-9e16-051369b04823","resolution":{"observed_at":"2026-08-04T05:55:56.654105Z","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":"2026-08-04T05:55:56.719856Z","title":"Dinov2: Learning robust visual features without supervision.Transactions on Machine Learning Research, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.719856Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:c516da4f3d3547172eb0c44b086fb9c811157d847748abf55a70eb0b8ed89cf4","observation_id":"c3eacff0-115c-4f2a-a133-59df2e5684f7","resolution":{"observed_at":"2026-08-04T05:55:56.719856Z","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":"2026-08-04T05:55:56.788293Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.788293Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:aa8bfd70c854ab1df814b0eb281f6a53639f66d1c542bfb2aff3d184b5f67080","observation_id":"8cc2072c-d9eb-43de-9973-95b7044eeb1c","resolution":{"observed_at":"2026-08-04T05:55:56.788293Z","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":"2026-08-04T05:55:56.918972Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.918972Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:51c17c9377a78a6cd010f90b0d94a6b9ab9dd2018c4d4ffbf46506a476770e4a","observation_id":"0f785a7d-7e1c-4287-b6d8-4b6338aac32e","resolution":{"observed_at":"2026-08-04T05:55:56.918972Z","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":"2026-08-04T05:55:56.955548Z","title":"High-resolution image synthesis with latent diffusion models.Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:56.955548Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:ceba08ce794d9fd7f1ab34e9edaba17dc0b5f4e1ba6fbababa7061fea6a83a93","observation_id":"2248a9dd-50ff-4964-9911-0185d4fbfb95","resolution":{"observed_at":"2026-08-04T05:55:56.955548Z","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":"2026-08-04T05:55:57.053872Z","title":"Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.053872Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:33cd8098e7b14ba8f1eb4eb4590557a9176b418dfcfebb432bb1bd8a6d53a43a","observation_id":"8c42a69a-299e-47e0-a746-f8d30e1718f6","resolution":{"observed_at":"2026-08-04T05:55:57.053872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.00512","last_updated":"2022-06-07T09:17:35Z","snapshot_observed_at":"2026-08-09T18:51:51.917654Z","submitted_at":"2022-02-01T16:07:25Z","title":"Progressive Distillation for Fast Sampling of Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.00512","snapshot_observed_at":"2026-08-04T05:55:57.134894Z","title":"Progressive distillation for fast sampling of diffusion models.arXiv preprint arXiv:2202.00512, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.134894Z"},"links":{"cited_paper":"/paper/2202.00512","citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:a6a9b113348c02eb53fd4b9cb61e0712132f3eb5f41e4ff55976b1a71a743fb5","observation_id":"e725642f-ac70-4b9b-8869-bd4a949da5b0","resolution":{"observed_at":"2026-08-04T05:55:57.134894Z","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":"2026-08-04T05:55:57.366817Z","title":"LAION-5b: An open large-scale dataset for training next generation image-text models.Advances in Neural Information Processing Systems, 35:25278–25294, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.366817Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:e39536120821fc744fd352a8ea6a3b1fd98bb56c5aa5957ff70738f85b9b4a45","observation_id":"c8937ae0-691f-40f3-bb07-5f7e3436bf93","resolution":{"observed_at":"2026-08-04T05:55:57.366817Z","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":"2026-08-04T05:55:57.442332Z","title":"Diff2flow: Training flow matching models via diffusion model alignment","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.442332Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:2eb41e55e5d4533b7b48062f40fedae96f0a465844234864a1de53b1c764ac93","observation_id":"2f8fd87e-7887-433c-9ea4-6ccbca062f2b","resolution":{"observed_at":"2026-08-04T05:55:57.442332Z","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":"2026-08-04T05:55:57.494931Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.494931Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:ee21f4053489214ebc26b2aaf04f759a9254cf3f3dacb3bd07d1e8ce429f9f3d","observation_id":"56151e92-cfbb-4fb2-8320-bb095fd42782","resolution":{"observed_at":"2026-08-04T05:55:57.494931Z","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":"2026-08-04T05:55:57.586098Z","title":"Consistency models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.586098Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:be411e45d0554bf5a5915bcf759ea4bc02f13f008c860bb73e648445c9ec7e16","observation_id":"ebe3158f-b34a-401c-ba36-2be217eefcef","resolution":{"observed_at":"2026-08-04T05:55:57.586098Z","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":"2026-08-04T05:55:57.689546Z","title":"Swarm learning for decentralized and confidential clinical machine learning.Nature, 594(7862):265–270, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.689546Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:f1468eafc4055c7ce6e324f80d1d2a576d650235f2211d6ee64edf0b24c5dcb9","observation_id":"44254f48-8193-442e-9ae4-90d5cd47cb02","resolution":{"observed_at":"2026-08-04T05:55:57.689546Z","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":"2026-08-04T05:55:57.743925Z","title":"Communication-efficient federated learning via knowledge distillation.Nature communications, 13(1):2032, 2022","venue":null,"work_id":null,"year":2032},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.743925Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:ebbed898c904708b901d2d6179d3ee6b15ebf1dae5cbe04bbd3fee048bec1c87","observation_id":"bb593b8d-e00e-431b-bcdd-dc1f6541cfbd","resolution":{"observed_at":"2026-08-04T05:55:57.743925Z","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":"2026-08-04T05:55:57.791754Z","title":"Decentralized federated learning towards communication efficiency, robustness, and personalization.ACM Transactions on Sensor Networks, 21(3): 1–20, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.791754Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:93ba640c8eba24d617b94a557371526a2508addd952e1db4d6694214a9bf5b3a","observation_id":"c70b7d9a-a6dc-4d3d-9af6-9911726c8b3b","resolution":{"observed_at":"2026-08-04T05:55:57.791754Z","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":"2026-08-04T05:55:57.822976Z","title":"Redi: efficient learning-free diffusion inference via trajectory retrieval","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.822976Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:e5bdce53da0b3b74c39e71b0aaa2460969ca34deddd30c6834f00e56ea20c45c","observation_id":"974bbe21-8035-4918-a857-8a829129704e","resolution":{"observed_at":"2026-08-04T05:55:57.822976Z","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":"2026-08-04T05:55:57.892082Z","title":"Efros, Eli Shechtman, and Oliver Wang","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.892082Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:076e886a70eedb45a5270736ded3f798e54571c06c15fa97e8820030d4123ef6","observation_id":"5faf377c-3968-4706-8bd5-e4390ccacffe","resolution":{"observed_at":"2026-08-04T05:55:57.892082Z","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":"2026-08-04T05:55:57.949519Z","title":"Communication-efficient decentralized federated learning via one-bit compressive sensing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:57.949519Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:9b79a02fd713b264b3e1468ddc644601f15c14232a3939e39a86acb381acb73f","observation_id":"2942e059-8e26-4a77-b2fb-b93dfac6c43d","resolution":{"observed_at":"2026-08-04T05:55:57.949519Z","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":"2026-08-04T05:55:58.007283Z","title":"Data Preprocessing and Clustering Dataset.We train on the LAION-Aesthetics subset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:58.007283Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:22657a16b7c729be98a544857713cf59b8a9f3f592f53c2fb98ed736c219e743","observation_id":"063e0405-dd5f-4dbb-a8da-2800675995a9","resolution":{"observed_at":"2026-08-04T05:55:58.007283Z","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":"2026-08-04T05:55:58.087358Z","title":"baked into","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:58.087358Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:ed9357089620d67fc9263db468117f3d5b4814c390a69a9db97ee7f918d17c77","observation_id":"ddbaa07b-7d16-4b00-98a3-56bc18ea6658","resolution":{"observed_at":"2026-08-04T05:55:58.087358Z","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":"2026-08-04T05:55:58.276786Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:58.276786Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:1f4f2429499f1f0dac6d0315c6083a22d811bd1cb94a7fd995f33ff3c495b56a","observation_id":"81b0e828-653c-4063-81cd-ddbc68236bf5","resolution":{"observed_at":"2026-08-04T05:55:58.276786Z","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":"2026-08-04T05:55:58.399181Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T05:55:58.399181Z"},"links":{"citing_paper":"/paper/2603.06741"},"observation_digest":"sha256:daed975cee82ecad4fad0fd7faa70ea4989a7f3f62b09afe97d23e996cfbdb28","observation_id":"18b644e6-8b5e-41c5-9e5f-15e8c4903c82","resolution":{"observed_at":"2026-08-04T05:55:58.399181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.06741","last_updated":"2026-07-31T17:10:16Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T23:10:59.912213Z","submitted_at":"2026-03-06T08:43:43Z","title":"Heterogeneous Decentralized Diffusion Models"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":44,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":44},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2603.06741."}