{"as_of":"2026-08-15T14:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ffd4a396bb4765b5beb5a1925837e2c1d1807ae51047f682de56d64e1eae2459","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T04:39:22.194541Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-05-20T11:55:36.275835Z","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":"2026-05-20T11:58:15.115532Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"cited_work":{"arxiv_id":"2502.08598","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.08598","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unke, Klaus-Robert M¨ uller, and Shinichi Nakajima","venue":null,"work_id":"6c27f5c0-a1f4-44bb-a8fb-6789fe06fa90","year":2025},"citing_paper":{"arxiv_id":"2605.19050","last_updated":"2026-05-18T19:14:53Z","snapshot_observed_at":"2026-08-15T02:10:29.403415Z","submitted_at":"2026-05-18T19:14:53Z","title":"Generative Pseudo-Force Fields for Molecular Generation","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-20T11:55:36.275835Z"},"links":{"cited_paper":"/paper/2502.08598","citing_paper":"/paper/2605.19050"},"observation_digest":"sha256:e6d8c46dca66b071e1d04913e234e42eb4cf8d7764b5d095c1afb8b2c9298e76","observation_id":"bdebff92-878d-4b79-b1e4-83ca0f8d23c7","resolution":{"observed_at":"2026-05-20T11:58:15.117009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.08598/citation-record","integrity":"/paper/2502.08598/integrity","json":"/paper/2502.08598/citation-record.json","paper":"/paper/2502.08598"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:39:21.947027Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.947027Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:ee2f079f5763369aac584bc598a03cb104397006b29ecf00bc71b170c77333dc","observation_id":"e87b5f9a-543d-404a-b068-35f0375f8310","resolution":{"observed_at":"2026-08-08T04:39:21.947027Z","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":"2026-08-08T04:39:21.951367Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.951367Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:de40e681f7cad4ff03084c685452ba4d4956c5a4d893b79a5b144e948a932d2f","observation_id":"d518ae45-2214-4f2e-a9f2-a6b9fa918c70","resolution":{"observed_at":"2026-08-08T04:39:21.951367Z","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":"2026-08-08T04:39:22.936451Z","title":"Improved techniques for training score-based generative models","venue":null,"work_id":"39c2a556-bc82-4b7c-9f71-a9ba8bf2fef5","year":2020},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.955803Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:4d58ffa2f4cd92793d31666fef6b3c494784b30464e31f5adc13a211d4a98b4a","observation_id":"4d673fe3-672b-4f44-88ff-4377ecfab11f","resolution":{"observed_at":"2026-08-08T04:39:22.940232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:21.960411Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.960411Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:99b634095364c76e130e5c062283875eca6ff3f357dbd1c08b66b7d5c2eb8a50","observation_id":"a2053eb3-d263-4782-a5b1-c80458e4e9c9","resolution":{"observed_at":"2026-08-08T04:39:21.960411Z","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":"2026-08-08T04:39:21.964878Z","title":"Diffusion models beat GAN s on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.964878Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:63535c1c72732267c080fc3603e910033d96d02394f7a5370a78f7035fe5054e","observation_id":"5b39819b-5fb1-44f0-beca-ec6e6fac93b3","resolution":{"observed_at":"2026-08-08T04:39:21.964878Z","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":"2026-08-08T04:39:22.913466Z","title":"GLIDE : Towards photorealistic image generation and editing with text-guided diffusion models","venue":null,"work_id":"32779bf9-af87-41a8-8887-79ca8d382125","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.969276Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:bd654232fbec684bb4c9bccfa2bc5d42665fac450204b66fc271745b674b4565","observation_id":"15627399-056d-45f4-994f-8a27f2dc3527","resolution":{"observed_at":"2026-08-08T04:39:22.917215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.902820Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"2ce180fc-8db8-4f0a-afce-576a2dbab642","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.973905Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:dbc8558e263a25c2911a6a8518ce307fbe4774bcceb1e7ef7b33f0f8018ff561","observation_id":"c366bdda-13be-402e-8038-f29fcd7b4668","resolution":{"observed_at":"2026-08-08T04:39:22.906785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.892764Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"3030818b-3bbc-4e09-aa58-65d9a61ab116","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.977939Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:699905798acc6e9f4fefaa78430ddf196c34ca6f34975cf5d99d9668c912e63c","observation_id":"4cc806a3-4be0-4ec6-b024-ee53fded9bbc","resolution":{"observed_at":"2026-08-08T04:39:22.896387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.882781Z","title":"Albergo, Nicholas M","venue":null,"work_id":"e683e232-585a-477b-8f2e-423990db5ee6","year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.982122Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:4ed9aa64045fd5a25e8f7ae535806ae41a6002d428135b4944f7f28d4121563a","observation_id":"f198e124-5348-4e04-867c-24851bccaa11","resolution":{"observed_at":"2026-08-08T04:39:22.886159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.872178Z","title":"Diffwave: A versatile diffusion model for audio synthesis","venue":null,"work_id":"21ab0c97-d803-4975-bf67-f4fde159f3dd","year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.986243Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:a7ea3bd8d84202b31e10f0a5bd4e84c8de93aacdffeaf4af2df2f1cd684db03f","observation_id":"9cda7531-9b70-4f5d-af82-063537ce75a5","resolution":{"observed_at":"2026-08-08T04:39:22.875857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.861749Z","title":"Wavegrad: Estimating gradients for waveform generation","venue":null,"work_id":"752de042-d4e7-4719-b8f2-24dc51333531","year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.990117Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:8fe08ed596d96aff421ac543efefaaf4f8f2454429ab5976d97e3ca93fd9677d","observation_id":"98b7779d-be49-444e-a995-05e8e6a28be1","resolution":{"observed_at":"2026-08-08T04:39:22.865487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.850711Z","title":"A udio LDM : Text-to-audio generation with latent diffusion models","venue":null,"work_id":"c983d53a-f896-4e92-ba57-2d17e10e4cfb","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.994463Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:00b44810598981fb005f35f6b37828349598269529c47a02e3203a061c54b4c2","observation_id":"3fe738a7-e0a4-4b0d-8fc3-ca80fd6002cd","resolution":{"observed_at":"2026-08-08T04:39:22.854876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.839000Z","title":"u ller, and Kristof T Sch \\","venue":null,"work_id":"bc118a07-a4bc-4492-be3c-8df4fbcf64b0","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:21.999261Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:0cfe0d2246fe10f3738a63ac939184fa616ca2fe402b59f756b540053149c9ad","observation_id":"4d820db2-38f2-4554-8f2f-4104eb6125a4","resolution":{"observed_at":"2026-08-08T04:39:22.842943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.826160Z","title":"Equivariant diffusion for molecule generation in 3 D","venue":null,"work_id":"6315fc4a-f27f-488f-a66e-96f10d4a59bc","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.003309Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:4b88fcbc90f447d2b413c934271600d71bb66124891c10d61c3e39df5f2bba41","observation_id":"d44f444b-1ec7-484c-804d-b895488128b1","resolution":{"observed_at":"2026-08-08T04:39:22.831128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.813235Z","title":"Diffusion-based molecule generation with informative prior bridges","venue":null,"work_id":"0d8abce6-206d-46cb-a5d8-ea0169986756","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.007436Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:e88e369f61781866d4ae52529b7d09e0cddecc9c5fadffe95b0d171037dda289","observation_id":"5c12d65b-67da-4504-a144-9898ea7833dc","resolution":{"observed_at":"2026-08-08T04:39:22.818446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.011416Z","title":"Mdm: Molecular diffusion model for 3d molecule generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.011416Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:4a8ba49544b5a6c95e20b1d23e1902b386a7982d6ff21ba7a6bf688edeb9501c","observation_id":"418e51ff-75a3-4b69-b2c8-aed0947b2e53","resolution":{"observed_at":"2026-08-08T04:39:22.011416Z","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":"2026-08-08T04:39:22.802368Z","title":"Dror, Stefano Ermon, and Jure Leskovec","venue":null,"work_id":"5adf9f57-cf13-41b6-96c3-eb97ce42341f","year":null},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.015453Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:2fa25a5d22965c2cdcb243e94995f1b8b6ae8d397013b5076347c2ba45cebc33","observation_id":"aca8c776-c927-4f3c-9e16-dcc806191308","resolution":{"observed_at":"2026-08-08T04:39:22.806081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.790139Z","title":"M ol D iff: Addressing the atom-bond inconsistency problem in 3 D molecule diffusion generation","venue":null,"work_id":"cee4bcd0-0d0c-4c21-8b6c-018ae8814b51","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.019633Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:b66372b8b9e1e82604c62a529920b6767ca1fe1bf0ad4df1e81fb1cbcf97a729","observation_id":"9e5d99e7-9d15-4294-b9eb-a67620cff046","resolution":{"observed_at":"2026-08-08T04:39:22.795062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.779042Z","title":"Midi: Mixed graph and 3d denoising diffusion for molecule generation","venue":null,"work_id":"bb069b39-2590-415f-b66d-6f1b63810e8e","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.023917Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:de5f0e7866e371df2bab89e182e39f77a59deb325fd70e5243d08e0b9cebaf24","observation_id":"a57af8aa-a521-4aa0-b750-0360b3628f0d","resolution":{"observed_at":"2026-08-08T04:39:22.782816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.027940Z","title":"Navigating the design space of equivariant diffusion-based generative models for de novo 3d molecule generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.027940Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:9328efe408291a532711d2f8470e7a7f95bdff3340f7d385001cb4e554314f11","observation_id":"4b7e6963-4cc6-4487-b7e6-68a7f2de5cd1","resolution":{"observed_at":"2026-08-08T04:39:22.027940Z","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":"10.1088/2632-2153/ad652c","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Molecular relaxation by reverse diffusion with time step prediction","venue":"Machine Learning Science and Technology","work_id":"72e8cc10-e3c1-4540-add6-2a03f328b3bd","year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.032229Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:d3a5dfee1ce3cdf9007ec4c46372c2efd5f2c4c0e83dd5858db17827115a68b6","observation_id":"6278024c-955f-4394-a388-9bd9d38bb859","resolution":{"observed_at":"2026-08-08T04:39:22.249712Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.761352Z","title":"GeoDiff : A geometric diffusion model for molecular conformation generation","venue":null,"work_id":"0d603584-1a9e-440f-a847-3d193b6f9583","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.036425Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:1b1942278b2836801cbee3f84a782890d38745f5487bbd461b51896eda285562","observation_id":"b5e1af51-5a2f-4468-a353-ecd0157b6481","resolution":{"observed_at":"2026-08-08T04:39:22.765361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.040391Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.040391Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:141ec4f9d8ec28915bef211b8984f5d57b0e073b9ee281e0f1377a8af4a9e5c0","observation_id":"c9554421-d697-4fcf-b6b5-f246bc896c7d","resolution":{"observed_at":"2026-08-08T04:39:22.040391Z","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":"2026-08-08T04:39:22.742844Z","title":"Learning fast samplers for diffusion models by differentiating through sample quality","venue":null,"work_id":"08811245-694f-4cbd-91b6-e91d9b979641","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.044221Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:b107ca88a04fd16a4ea7a237bd84c04e1a360c5484343884efe6b1ef1fc508a5","observation_id":"0ce2caf5-4f44-4254-a920-e5d884b7f6aa","resolution":{"observed_at":"2026-08-08T04:39:22.747324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.048149Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.048149Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:880de27c20d0476cfea401584b0d912c80dd9fa5e1ed1661c9ad1dee32b8e501","observation_id":"46d0c2ed-fc1d-4662-949d-ecae3c9327ea","resolution":{"observed_at":"2026-08-08T04:39:22.048149Z","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":"2026-08-08T04:39:22.724768Z","title":"Consistency models","venue":null,"work_id":"83547253-d82f-4504-848d-5c6967eda418","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.052174Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:a6f2588b085c984af25a61dbddd462d04dbcde2e0ba3d5ffa6a4daedc1fbcc16","observation_id":"6aa470cc-ede2-4229-8958-3283ffc827a0","resolution":{"observed_at":"2026-08-08T04:39:22.728407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.056133Z","title":"Simplifying, stabilizing and scaling continuous-time consistency models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.056133Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:8a4443bf0969029a5017c7c87c7f79b08fb4b17635393060c4d4deb850e75353","observation_id":"1f29ec94-59a2-419d-94f2-4686a99b42e2","resolution":{"observed_at":"2026-08-08T04:39:22.056133Z","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":"2026-08-08T04:39:22.060160Z","title":"Simple reflow: Improved techniques for fast flow models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.060160Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:deadc04b16e16e0865739afac8169b81a0e1c4568d753f85e5d43a5693866a8b","observation_id":"5e385240-20d3-4092-b25a-d682ff5949c7","resolution":{"observed_at":"2026-08-08T04:39:22.060160Z","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":"2026-08-08T04:39:22.700308Z","title":"DPM -solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","venue":null,"work_id":"4dbdabec-c4f4-4ee0-95e0-a28dedb6bd2f","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.064117Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:eed6d5f58605b0659810ba8328aee4354dfacaadbd22598c3574852e34cf51af","observation_id":"a3f0cafa-8b93-4e9c-9f9c-d79f430d8f85","resolution":{"observed_at":"2026-08-08T04:39:22.704868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.068106Z","title":"Pseudo numerical methods for diffusion models on manifolds","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.068106Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:ca705c227454f19ca7a3f5b5d2581141751a2d8fcbbd0d5604bb88a2d5a5ede8","observation_id":"f55b95fa-0a91-4e96-88bb-befbd63550f4","resolution":{"observed_at":"2026-08-08T04:39:22.068106Z","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":"2026-08-08T04:39:22.682434Z","title":"GENIE : Higher-order denoising diffusion solvers","venue":null,"work_id":"68e38248-f0f9-4823-8f00-3f890ec8d161","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.071772Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:90c96289abf43f91709f5ed6dada59a4738de8a095eb127bda8a29c804c77426","observation_id":"75887482-076c-4db3-b4ff-78407de8ac99","resolution":{"observed_at":"2026-08-08T04:39:22.686338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.670364Z","title":"Gotta go fast when generating data with score-based models, 2022","venue":null,"work_id":"88d946dd-2680-4e27-af0e-8dde5cc57c5b","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.075895Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:2096ec063dac70aa8505f9df6157b358dbb94a52d42bc8782a5221451892b384","observation_id":"4e1e4316-584e-4704-b78a-5e2b6bef31b5","resolution":{"observed_at":"2026-08-08T04:39:22.674852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.658043Z","title":"DPM -solver-v3: Improved diffusion ODE solver with empirical model statistics","venue":null,"work_id":"4d923922-3cd0-43ba-a80c-99a227a7ffaa","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.080054Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:16242bc75abc704ef16093e76711cf603682b05e9c425c290fd301377cef076b","observation_id":"9cc0698b-ba8b-4d35-a0ce-89e8b41a4b32","resolution":{"observed_at":"2026-08-08T04:39:22.662524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.645028Z","title":"Fast sampling of diffusion models with exponential integrator","venue":null,"work_id":"5b88c72e-c293-40ab-a32f-2eb2b0fc9171","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.084210Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:9f486229c2e5b5f46622e411b187dacfa3af4526d9dfd745a6aba9e7b7fad698","observation_id":"71192092-5485-4659-9dff-2b2a1f92da5d","resolution":{"observed_at":"2026-08-08T04:39:22.649271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.631951Z","title":"Uni PC : A unified predictor-corrector framework for fast sampling of diffusion models","venue":null,"work_id":"4712d336-f4df-46ad-914f-d9b0d0c24795","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.088469Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:41d0687bbe317548112ea6166650d265426bf496678bf1ae0d86ee67851794bb","observation_id":"ad3a8ca2-d703-4a08-8f5a-374025e3bea0","resolution":{"observed_at":"2026-08-08T04:39:22.636965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.10972","last_updated":"2023-05-21T07:07:55Z","snapshot_observed_at":"2026-08-14T17:24:49.885507Z","submitted_at":"2023-01-26T07:37:22Z","title":"On the Importance of Noise Scheduling for Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.10972","snapshot_observed_at":"2026-08-08T04:39:22.092846Z","title":"On the importance of noise scheduling for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.092846Z"},"links":{"cited_paper":"/paper/2301.10972","citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:b354925270fbe524efc62df1c7fae42c92fe8dc668fff8f6c92af60470723226","observation_id":"ac36a447-91c1-4df3-94c7-b3435017f1ed","resolution":{"observed_at":"2026-08-08T04:39:22.092846Z","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":"2026-08-08T04:39:22.620495Z","title":"Common diffusion noise schedules and sample steps are flawed","venue":null,"work_id":"f289b762-6aee-4719-a843-b0121fd63c73","year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.097339Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:2e90a31490534d1dd5a4fa8ac27e4987b82b9ea0d48c9199225959872accfebc","observation_id":"5aa731df-33ec-4979-9cfc-c1632533fd97","resolution":{"observed_at":"2026-08-08T04:39:22.624622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.609380Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":"c5a74180-2c91-4923-8765-aa326adbce70","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.101347Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:99fe1ab08781bdee41b873dd272c63821596ae91f435b086e21a34dc9d50a3a4","observation_id":"f4ae7517-fbd4-4726-93c8-3935b5df6f32","resolution":{"observed_at":"2026-08-08T04:39:22.613349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.598267Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":"ae06aaae-92ed-4a5f-a71e-b7cd2234ada7","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.105280Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:ac1a45a13d7f674ffa932acc1b4cf626ccd413faef34655ee59a7c0074ae3501","observation_id":"03b7a33f-d3c1-4d61-b7b2-3a685bd956f9","resolution":{"observed_at":"2026-08-08T04:39:22.602235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.109201Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.109201Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:71c0b0e3238cc59189418c73049ae9a455585676bbc92f921487c6d3580f7e3f","observation_id":"187a948f-25f8-481d-a1cb-a90a6f70e91a","resolution":{"observed_at":"2026-08-08T04:39:22.109201Z","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":"2026-08-08T04:39:22.578554Z","title":"Building normalizing flows with stochastic interpolants","venue":null,"work_id":"bc752e1b-b930-46fb-a3ab-d384f7bfa49b","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.112848Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:70a31bebddd49824c38696bf5abc50b1b4d4b2539dc240a9e29a9d3e70aa2098","observation_id":"271d2fc8-a9cc-4b83-a5fe-0d8841c5a75c","resolution":{"observed_at":"2026-08-08T04:39:22.582673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.566512Z","title":null,"venue":null,"work_id":"a6aacb95-5a4c-4fcf-9ab0-a73537c5b76a","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.116475Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:1f520363dbc1655e37ee7f89718e43aaa7aab6aba32d4082b4c74f9086b42a96","observation_id":"a54c97ea-93c5-49ef-b5fe-50d8c9fa2d50","resolution":{"observed_at":"2026-08-08T04:39:22.570470Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.120219Z","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.120219Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:872bb24792aa310cde347f1e30f376481e60061236346e789c4d2c16102122ce","observation_id":"b7dc9d92-fee0-47c3-9485-fb7030acb199","resolution":{"observed_at":"2026-08-08T04:39:22.120219Z","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":"2026-08-08T04:39:22.124231Z","title":"Equivariant flow matching","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.124231Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:284e888849475ab95dc50dfdb25f5db1ec7e5f656accebccf170278b1757df16","observation_id":"13d147d9-60c0-47f1-b168-d1242c1442de","resolution":{"observed_at":"2026-08-08T04:39:22.124231Z","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":"2026-08-08T04:39:22.543513Z","title":"Equivariant flow matching with hybrid probability transport for 3d molecule generation","venue":null,"work_id":"32c9839e-07c2-4ca3-8fa2-1fa164f93bf6","year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.127875Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:47a95a0231fd6091cb63677b928cc7986b28501c6a829b402b131388875bebac","observation_id":"7bcdefab-d8bf-4dfd-8dea-184f84fb67b8","resolution":{"observed_at":"2026-08-08T04:39:22.547395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.131523Z","title":"Efficient 3d molecular generation with flow matching and scale optimal transport","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.131523Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:aed9cc7ccf340006687146840db49d7888731473ad124ffbc3e3ec9b8b12c04f","observation_id":"abc390bf-6f31-45b1-b295-1b37a7dc3016","resolution":{"observed_at":"2026-08-08T04:39:22.131523Z","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":"2026-08-08T04:39:22.135226Z","title":"Generative modeling by estimating gradients of the data distribution","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.135226Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:105b4bd0f454954e836583ed137d1289d57e2d4b7d9015aa1ba87571aacf1f77","observation_id":"1abd5488-b1e9-4c9d-91a9-76e748c3a2a8","resolution":{"observed_at":"2026-08-08T04:39:22.135226Z","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":"2026-08-08T04:39:22.519899Z","title":"Variational diffusion models","venue":null,"work_id":"a5c44f2a-8ee3-4709-8e93-5cdd1238f3dc","year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.138973Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:5f4fccf60b463c1bbf707869fd9bd2e664c58f8761744e026efe6342e4085da9","observation_id":"63217234-7037-46ba-863b-1a73c0552a4a","resolution":{"observed_at":"2026-08-08T04:39:22.523865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.509253Z","title":"Diffusion normalizing flow","venue":null,"work_id":"59ee7bec-c7b9-477e-841b-1232b3fcf770","year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.142592Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:4cca77268f8cc85387eec65e478cb57e7a0786be6a5e5276ff3445bcbcd4e2f9","observation_id":"1eec2fd8-4286-4393-b6db-650378da1e1a","resolution":{"observed_at":"2026-08-08T04:39:22.512869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.146089Z","title":"A connection between score matching and denoising autoencoders","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.146089Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:feff25868f01c91fb0e4c1d2e2280ad5fe8e31262c72b098686fdae6a8f29de4","observation_id":"af970004-1f20-48d2-8865-334f2b65273a","resolution":{"observed_at":"2026-08-08T04:39:22.146089Z","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":"2026-08-08T04:39:22.149719Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.149719Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:3d9c4987e174cd30429e07deb25117f817c952ea04ba1f341d308806230f85fe","observation_id":"ef54207c-b793-44af-9191-b7d5110bbcb7","resolution":{"observed_at":"2026-08-08T04:39:22.149719Z","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":"2026-08-08T04:39:22.490376Z","title":"DPM -solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","venue":null,"work_id":"9c8df920-7165-4da9-a944-4cdf6946c4ad","year":2022},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.153748Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:89782c1502622136e0e36ff53514268bfe18136c7d44fbf6306aa76b24d6bbf2","observation_id":"9260bfb4-4a68-4b1e-83c8-7f84c4f43eb3","resolution":{"observed_at":"2026-08-08T04:39:22.494580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.478283Z","title":"Equivariant flow matching for molecular conformer generation","venue":null,"work_id":"e1b00dc3-13f3-4c9e-a586-f7c6e874ad92","year":2024},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.157495Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:dc8b310833dd831ac28a157f310d9ed90dc16f4c5c626c318aa64ebb5aeec59f","observation_id":"24761a9e-8649-410b-a59a-9a2df17c9878","resolution":{"observed_at":"2026-08-08T04:39:22.482590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.161149Z","title":"Ramakrishnan, P","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.161149Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:7a28d1ce30aa1d896e9ad54bd320cc3f34277a98570fc74ef4992ab3d1f15cc6","observation_id":"0996fb05-8753-4d5d-bc81-7e490d82bc30","resolution":{"observed_at":"2026-08-08T04:39:22.161149Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01095","last_updated":"2025-05-19T07:56:56Z","snapshot_observed_at":"2026-08-15T03:10:54.042099Z","submitted_at":"2022-11-02T13:14:30Z","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01095","snapshot_observed_at":"2026-08-08T04:39:22.164949Z","title":"DPM - Solver ++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models , May 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.164949Z"},"links":{"cited_paper":"/paper/2211.01095","citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:2e279d2cfa9b611f5e3745bf6df90ada2d8e8b32b8dd18dbf2a7be7d4af56129","observation_id":"58130f4c-ff2a-42ef-9acb-fbd909f8b8b0","resolution":{"observed_at":"2026-08-08T04:39:22.164949Z","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":"2026-08-08T04:39:22.466849Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":"62acca9b-b93c-4af9-95b3-3ffb98f88bea","year":2017},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.168911Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:102001f00013b25f9db8d28455f9bf4a9a2f7571e032e461ffca18d71d226509","observation_id":"b313e372-a20e-423f-b2bb-13a38858d934","resolution":{"observed_at":"2026-08-08T04:39:22.470968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.455079Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"0af39ec2-c421-4d5e-80b1-9080a333c185","year":2009},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.172884Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:042b19eab35767829b371d57d27c3b4e45ece5352e1a45d67201aa7b3072d77b","observation_id":"e25b07f8-e9ad-4d32-b327-5d543f0463d6","resolution":{"observed_at":"2026-08-08T04:39:22.459117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.443285Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":"4bc7680e-de3d-4125-98e0-ddfd78a7dc24","year":2019},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.176496Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:b5e413334bf93212a435229d75fdc2bf61e38ee7608968e14a93225e044c994f","observation_id":"9bccad06-b0b9-4d3d-a5b8-8c4981b9cdd0","resolution":{"observed_at":"2026-08-08T04:39:22.447483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-08T04:39:22.180296Z","title":"Stargan v2: Diverse image synthesis for multiple domains","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.180296Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:915b2e6bdb23aeafe4b1dabd5f4447303631f64ebeff3b9ca24693cf64582def","observation_id":"6bdff5c1-d156-41c5-833c-48cb3223ff77","resolution":{"observed_at":"2026-08-08T04:39:22.180296Z","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":"2026-08-08T04:39:22.186844Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.186844Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:744680d3e13e58279a37f33f6578bedf605acbe5874465338e74e47accfcbf05","observation_id":"b7901698-bd91-4ae4-abd7-0aee4df852a6","resolution":{"observed_at":"2026-08-08T04:39:22.186844Z","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":"2026-08-08T04:39:22.190598Z","title":"Tweedie’s formula and selection bias","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.190598Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:dff9beaa9f2f2aa5fc5254b2024ffe7b6554d61a67bd5ebf7fedf329fdb421c4","observation_id":"e5508456-e689-4aa2-a0c5-e8dea8d87c59","resolution":{"observed_at":"2026-08-08T04:39:22.190598Z","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":"2026-08-08T04:39:22.194541Z","title":"Applied Stochastic Differential Equations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-08T04:39:22.194541Z"},"links":{"citing_paper":"/paper/2502.08598"},"observation_digest":"sha256:2a60f9fac73916b2f02b2bbda6fd7d2b68f23bfa01240e7b7e2b2426c51ea1c7","observation_id":"17f63f86-335b-4064-9647-86bfce89fcaf","resolution":{"observed_at":"2026-08-08T04:39:22.194541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.08598","last_updated":"2025-06-02T10:48:00Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T13:33:32.857404Z","submitted_at":"2025-02-12T17:35:43Z","title":"Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":1,"verified_fuzzy":35},"total_outbound_references":62},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2502.08598."}