{"as_of":"2026-08-10T07:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b9c7bab736d151003be50059e2809632c3f85c421551008f6961e5e0553dd22c","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:35:19.869576Z","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":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T01:44:04.922621Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T01:46:13.859391Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"cited_work":{"arxiv_id":"2505.18521","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18521","snapshot_observed_at":"2026-07-01T02:16:54.609590Z","title":null,"venue":null,"work_id":"90fc1ccf-29b0-407b-ad14-7424bd921c7e","year":2025},"citing_paper":{"arxiv_id":"2605.08144","last_updated":"2026-05-02T19:43:16Z","snapshot_observed_at":"2026-08-02T07:31:09.899562Z","submitted_at":"2026-05-02T19:43:16Z","title":"NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-12T01:44:04.922621Z"},"links":{"cited_paper":"/paper/2505.18521","citing_paper":"/paper/2605.08144"},"observation_digest":"sha256:a36189bd5064d13b2085b416833a6c8e5cf53961ba78405792fb9a8cd790a018","observation_id":"8a3fb5c1-c619-419d-af16-4c674058c9cf","resolution":{"observed_at":"2026-07-01T02:16:54.609590Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.18521/citation-record","integrity":"/paper/2505.18521/integrity","json":"/paper/2505.18521/citation-record.json","paper":"/paper/2505.18521"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:20.237557Z","title":"Image embedding for denoising generative models.Artificial Intelligence Review, 56(12):14511–14533, 2023","venue":null,"work_id":"4780b8fa-de1a-4a0a-aa35-372747272792","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.106327Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:d2525e7aaff92c88a81e87a795ecaad0a64748fae157b1f6cdc90d3668db4fee","observation_id":"2081ea35-4c2b-43ca-ba8c-506ad70b7b5f","resolution":{"observed_at":"2026-08-07T14:35:20.241994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:20.227358Z","title":"Conditional wasser- stein distances with applications in bayesian ot flow matching, 2024","venue":null,"work_id":"645f2e4f-69d6-46d7-b280-7db47cd60dbd","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.148357Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:7f5322c04e62e59746b2e655f49ec1cfa24c10b5717253185c88cc6dfeb5a750","observation_id":"a1d02260-1225-4088-8ea0-c10ae71449dc","resolution":{"observed_at":"2026-08-07T14:35:20.230470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:17.220792Z","title":"Diffusion policy: Visuomotor policy learning via action diffusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.220792Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:ddf54bc13b2e82089b950b3b62c18a9cb7e529ab18acbe0fcd85eb63eb22b9f7","observation_id":"8d9b636b-0d7a-4fcc-8f9f-d33f7a172b11","resolution":{"observed_at":"2026-08-07T14:35:17.220792Z","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":"2026-08-07T14:35:20.210764Z","title":"On implementing 2d rectangular assignment algorithms.IEEE Transactions on Aerospace and Electronic Systems, 52(4):1679–1696, 2016","venue":null,"work_id":"3c39ccfc-0dc2-4628-86ad-5fd25732e8f5","year":2016},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.298177Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:2c81b666cd5220df0574f3271af13bb921e63dd8b54cae1647ef2c4ae22f83e3","observation_id":"3f94372f-110b-4363-92d3-f5b696fdc807","resolution":{"observed_at":"2026-08-07T14:35:20.214636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:17.379383Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.379383Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:83a15caf0f1007f9f56691b7a89467ed6ec220df1259d9aa55ec754d5b391eb8","observation_id":"9cb9382d-9267-4cdf-88ce-26cd74960fe1","resolution":{"observed_at":"2026-08-07T14:35:17.379383Z","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":"2026-08-07T14:35:20.194079Z","title":null,"venue":null,"work_id":"3d8641af-46b9-424b-a312-2d12f8620a39","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.470670Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:0c8cf3be557be5934f692680ef450be1ce1eed02bf6838e8e0d143a0e27ce750","observation_id":"40681f8a-2c22-4b11-9098-94634103d02f","resolution":{"observed_at":"2026-08-07T14:35:20.197744Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:17.562302Z","title":"Clipscore: A reference-free evaluation metric for image captioning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.562302Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:d5997448a59dd18a4944dc79eb3e094d2a9fb72cea87a953bedf098a2fdb7289","observation_id":"d72e5ca0-bdfc-4d5a-9367-2566c6c16c93","resolution":{"observed_at":"2026-08-07T14:35:17.562302Z","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":"2026-08-07T14:35:17.676073Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.676073Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:bbf884c575d160e09719346361b6490120763db2102e6184fae1354b78bd08a6","observation_id":"15c79646-a3bb-45c3-b5ef-32be32018838","resolution":{"observed_at":"2026-08-07T14:35:17.676073Z","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":"2026-08-07T14:35:20.170067Z","title":"Blue noise for diffusion models","venue":null,"work_id":"a00c3c2c-191b-4c22-8eb8-04f7483c2636","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.773335Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:4027669987cd36fa6d84b1b812bca4f7f769afc0c6b79b1dc95fbb65cb92cd33","observation_id":"e7cd5209-851a-4280-9f00-d9582a38d152","resolution":{"observed_at":"2026-08-07T14:35:20.173207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:20.159192Z","title":"Improving consistency models with generator-induced coupling, 2024","venue":null,"work_id":"2b2d7c36-7d10-48a8-ba6e-83d9d6e31a17","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.874942Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:766a3c88783815d44238ea8984a9129cab67598cfda37837b228c309aa2ad385","observation_id":"c59fac77-0b87-4966-83d9-77a5430ed32c","resolution":{"observed_at":"2026-08-07T14:35:20.162573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:17.954290Z","title":"Analyzing and improving the training dynamics of diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:17.954290Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:828f432d0eebbb27f0170eb428f4d701831547edbd9822984f815298dc7d04d3","observation_id":"c0ea3938-f79e-410d-9b86-af0d1fcaa813","resolution":{"observed_at":"2026-08-07T14:35:17.954290Z","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":"2026-08-07T14:35:20.142255Z","title":"Understanding DDPM latent codes through optimal transport","venue":null,"work_id":"84b71919-62c8-49bc-8488-75166a810b6a","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.046099Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:c6473e1c8fca847dc2a6d9429d659b0ace2f61164b864ba429eb14b7232e13b0","observation_id":"07d425d7-a9f6-4ce4-9a67-8fb6ef5d0b7e","resolution":{"observed_at":"2026-08-07T14:35:20.145645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:18.109936Z","title":"Auto-encoding variational bayes, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.109936Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:0a214263f8b81b434ff8c082b66a8f90cff48d07dd30aa2ff6de54c1053cefa5","observation_id":"60c7b2c3-075b-4cfc-9ccd-339d49d2af78","resolution":{"observed_at":"2026-08-07T14:35:18.109936Z","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":"2026-08-07T14:35:18.202676Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.202676Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:b7da025207726fb2a3fd618387e7f76ad6cf46aa03c2bab5644a13e1daefdd63","observation_id":"f2ce1ac9-c097-48a2-a17b-6db7232e57f4","resolution":{"observed_at":"2026-08-07T14:35:18.202676Z","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":"2026-08-07T14:35:20.116148Z","title":"Score-based generative modeling secretly minimizes the wasserstein distance","venue":null,"work_id":"6ab25460-104e-4c26-b027-6bb0581d7a44","year":2022},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.294473Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:8673be52e893885e399aa8f84325bd338dad95aac74b5fb819373f1b3ea76a13","observation_id":"ef78fb8c-ac58-4336-9637-40a58e17f8b0","resolution":{"observed_at":"2026-08-07T14:35:20.119476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:20.105831Z","title":"Minimizing trajectory curvature of ODE-based generative models","venue":null,"work_id":"c986d4bf-e188-47c9-8660-26dc6cb03dc8","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.397598Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:8c5b66ab1c056c866512e251e975e1e8db7f0044a37210e8ae3eae1c6baabe44","observation_id":"47205a05-ff3d-4bf6-bfe2-e87ecd5607d2","resolution":{"observed_at":"2026-08-07T14:35:20.108993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:20.095315Z","title":"Immiscible diffusion: Accelerating diffusion training with noise assignment","venue":null,"work_id":"3bbe902d-f8ba-4876-a45c-1e6581aafaec","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.490815Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:97b73ef41483ffa7d271f61726dae09606eb3a78ffb89f6d5121aaaa5ec30ad0","observation_id":"cc7556ae-1cd6-4aed-a6b3-0f940cf00207","resolution":{"observed_at":"2026-08-07T14:35:20.099138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:18.602691Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.602691Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:21178768d37351d236a9ee09e9a663ced7bc03cdbbab892620c175c9e45117cc","observation_id":"c1884b41-0dd4-4e6c-bf97-4ca61a4135a5","resolution":{"observed_at":"2026-08-07T14:35:18.602691Z","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":"2026-08-07T14:35:18.685011Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.685011Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:423215302893454b887352e0370cc87a2f79b290014c858d2d2a93f994a21755","observation_id":"638ebe06-f26a-4f8b-b716-837f3d1d414f","resolution":{"observed_at":"2026-08-07T14:35:18.685011Z","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":"2026-08-07T14:35:18.772393Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.772393Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:55e087a2f043ff1bcd41f6d32418d51ce90e3f0064ff85decb5da25f3b4b823a","observation_id":"ca4e24d5-33d3-458d-9d69-94161beccc1a","resolution":{"observed_at":"2026-08-07T14:35:18.772393Z","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":"2026-08-07T14:35:20.062132Z","title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","venue":null,"work_id":"404e3dcb-a9ab-4a5d-84dd-57401a38336b","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.838734Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:52cec76cebb6a11fc47f7582194198b96b4588d37550f9b60a651528bee3cd5b","observation_id":"0d497223-ba09-48b4-afc6-92d706c9e172","resolution":{"observed_at":"2026-08-07T14:35:20.066308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19339","last_updated":"2025-06-09T18:57:55Z","snapshot_observed_at":"2026-08-04T22:17:26.539831Z","submitted_at":"2024-11-28T19:22:17Z","title":"Towards a Mechanistic Explanation of Diffusion Model Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19339","snapshot_observed_at":"2026-08-07T14:35:18.955715Z","title":"Towards a mecha- nistic explanation of diffusion model generalization.arXiv preprint arXiv:2411.19339, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:18.955715Z"},"links":{"cited_paper":"/paper/2411.19339","citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:a116ad945fad5fbe4fa72e172219be1c3ad01f2a8842c32da82b6b9ab17b1706","observation_id":"8b858cfe-f4f5-4df4-8b8a-68b702c4c593","resolution":{"observed_at":"2026-08-07T14:35:18.955715Z","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":"2026-08-07T14:35:20.050048Z","title":null,"venue":null,"work_id":"3387f01c-9046-45cd-a064-17de91bc1b14","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.044031Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:ca8c79b26a67e1773723fa4fe26df17f2a0f2cb9f07ec046085af5e171482fe8","observation_id":"3720c17c-f1a0-4e6d-a847-bb33ed038ad9","resolution":{"observed_at":"2026-08-07T14:35:20.054675Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:19.120209Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.120209Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:92db4d80f6b8cc75a1247ee2e5f2b55b89c88dcea7378d05dc06791465994a4e","observation_id":"61868b2e-7fee-4f3b-90c0-f0525a9dce44","resolution":{"observed_at":"2026-08-07T14:35:19.120209Z","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":"2026-08-07T14:35:19.223012Z","title":"High-resolution image synthesis with latent diffusion models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.223012Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:0066704680f30caad4f8675a10104047d2a20f726fcb6712a0b2bad316637ec9","observation_id":"dab53375-1911-4703-9159-9d5abe30c129","resolution":{"observed_at":"2026-08-07T14:35:19.223012Z","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":"2026-08-07T14:35:19.332166Z","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":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.332166Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:efbe21415559f5089c7ee7f88ce9cd03edc0c1149fa0f48cf0e3f0ac02fbe8e1","observation_id":"a161498d-171c-4549-8904-872c1950effc","resolution":{"observed_at":"2026-08-07T14:35:19.332166Z","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":"2026-08-07T14:35:19.499586Z","title":"Denoising diffusion implicit models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.499586Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:fd5b8a3fdaf6aadf95719622da609b00c3a6c4e0e303f1232158f9f8fc18e444","observation_id":"ca60182a-7a93-4297-b148-dfe4b5016d02","resolution":{"observed_at":"2026-08-07T14:35:19.499586Z","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":"2026-08-07T14:35:19.674543Z","title":"Improved techniques for training consistency models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.674543Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:9a29e9b42e30f1badf3f98d4c410cb59482ea05435414ffa32dd88f944d87027","observation_id":"8c98eb2b-7eb2-41b9-ac42-5d1ec8fa8a54","resolution":{"observed_at":"2026-08-07T14:35:19.674543Z","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":"2026-08-07T14:35:19.995602Z","title":"Consistency models","venue":null,"work_id":"3cda8961-20be-4e15-aa3a-191fb5896e81","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.838986Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:3070d27b30fdd0959f0a7b1cbaeacb605983a5e0d0c98b78251a0c8844ca3b6e","observation_id":"d072f5f7-4aee-4dfc-9bbb-0b7fbf3f1cd3","resolution":{"observed_at":"2026-08-07T14:35:19.998759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:19.843038Z","title":"Improving and generalizing flow-based generative models with minibatch optimal transport, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.843038Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:cb57d05352123972ad5a3db38e135057e784879604417099572979a9e62dc758","observation_id":"23028d1c-7a39-438b-b701-309a8876cec7","resolution":{"observed_at":"2026-08-07T14:35:19.843038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17403","last_updated":"2025-03-25T08:38:28Z","snapshot_observed_at":"2026-07-06T18:20:44.070255Z","submitted_at":"2024-05-27T17:51:36Z","title":"A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17403","snapshot_observed_at":"2026-08-07T14:35:19.847310Z","title":"A closer look at time steps is worthy of triple speed-up for diffusion model training.arXiv preprint arXiv:2405.17403, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.847310Z"},"links":{"cited_paper":"/paper/2405.17403","citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:74b13fa304fa5bd2e33f6d2e1a0c8daa8d9569fd5c47316e9ffe4358cf354bcc","observation_id":"e35654e6-a92c-4dfe-9315-07892d907c1c","resolution":{"observed_at":"2026-08-07T14:35:19.847310Z","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":"2026-08-07T14:35:19.851419Z","title":"Patch diffusion: Faster and more data-efficient training of diffusion models.Advances in neural information processing systems, 36:72137–72154, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.851419Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:6e7fab6549c3197ddd393de1390ea4da1c454dd7f2f82e5f87a3740c2e501478","observation_id":"ab259c75-54dd-412b-ac58-0d3f3f70ff10","resolution":{"observed_at":"2026-08-07T14:35:19.851419Z","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":"2026-08-07T14:35:19.968099Z","title":"Exploring straighter trajecto- ries of flow matching with diffusion guidance, 2023","venue":null,"work_id":"25428da9-41c6-4787-aefb-d89e9de1fec2","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.855066Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:c0044e43130a1d1bdbb45be82e6d69e1a5762bb6446696228e876e4e3e653c58","observation_id":"1a6042b6-47a2-4a4f-97cf-6e001d2e3d37","resolution":{"observed_at":"2026-08-07T14:35:19.972272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:19.956721Z","title":"The emergence of reproducibility and consistency in diffusion models","venue":null,"work_id":"2162c8b3-af94-48c5-9868-148817924fff","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.858858Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:c484c9e643a62f4373055423172662ffb0e7c32d58ee168d52556cad37f3a36e","observation_id":"59e52e97-bf65-4538-aced-7e8c6bad0865","resolution":{"observed_at":"2026-08-07T14:35:19.960448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:19.944963Z","title":"Formulating discrete probability flow through optimal transport","venue":null,"work_id":"b890f168-3ddb-43dc-b17e-fe3ad83593ec","year":2023},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.862268Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:8b7e2fdc4cd7bb62e138389a167d5992a56f00710f6f3659793d13af298dc625","observation_id":"cefc30d6-c037-49be-9727-06ba8aa01081","resolution":{"observed_at":"2026-08-07T14:35:19.948412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:19.934253Z","title":"Non-uniform timestep sampling: Towards faster diffusion model training","venue":null,"work_id":"4c4e4c0d-0d8c-42bf-9faa-85b8e0ef0cd8","year":2024},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.865899Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:c6af0a353335f685b3a8ced9691a42b9639b7c42a58408bdd5cbdfdf0313d60d","observation_id":"54765b26-637a-449b-bb84-69ebe1e5f7c7","resolution":{"observed_at":"2026-08-07T14:35:19.937767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:35:19.920998Z","title":"There and back again: On the relation between noise and image inversions in diffusion models, 2025","venue":null,"work_id":"bf1f97bb-4d3e-461a-90d1-a723415f794d","year":2025},"citing_paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:35:19.869576Z"},"links":{"citing_paper":"/paper/2505.18521"},"observation_digest":"sha256:1f3853b18c21506481dcc5584021dc497929586d2e9065fdd03579acc243db84","observation_id":"01b0a997-93ba-423b-aa81-af97d991b776","resolution":{"observed_at":"2026-08-07T14:35:19.926782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.18521","last_updated":"2026-06-30T02:59:08Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T06:17:30.952975Z","submitted_at":"2025-05-24T05:38:35Z","title":"Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":16},"total_outbound_references":37},"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 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2505.18521."}