{"as_of":"2026-08-10T14:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:39aea1384256a4006debbefc4f7093d436348bdc0bd466f6894d5b9d8bb5ca41","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:15:29.592118Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"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":"2026-07-12T01:24:17.156028Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.00136","snapshot_observed_at":"2026-07-12T01:24:17.156028Z","title":"Siddharth","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03580","last_updated":"2026-07-03T19:47:07Z","snapshot_observed_at":"2026-08-10T06:32:15.513383Z","submitted_at":"2026-07-03T19:47:07Z","title":"When Geometry Aligns: Dihedral Hidden-State Transformations in UNet, ViT, and DiT Architectures","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T01:24:17.156028Z"},"links":{"cited_paper":"/paper/2506.00136","citing_paper":"/paper/2607.03580"},"observation_digest":"sha256:4e42831d2c7b2765b3b86109d023626042f1fd1f2b6ecea411d1b8e3fe41a452","observation_id":"9759b947-03cd-455c-8a76-25e0cb2c811e","resolution":{"observed_at":"2026-07-12T01:24:17.156028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.00136/citation-record","integrity":"/paper/2506.00136/integrity","json":"/paper/2506.00136/citation-record.json","paper":"/paper/2506.00136"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:15:33.801185Z","title":"Vetrov, and Christian Andersson Naesseth","venue":null,"work_id":"898a2e2b-1cb8-4901-aae2-bc2247232414","year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.643552Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:932ee686b933b1fcdd0c73ef52739aec0bbab0388a6d8e0033a038bc017ec546","observation_id":"24653cc9-7a3d-4ced-a7ed-fb7c6772951e","resolution":{"observed_at":"2026-08-07T12:15:33.843282Z","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":"1801.04062","last_updated":"2021-08-14T18:35:05Z","snapshot_observed_at":"2026-08-06T22:27:17.572335Z","submitted_at":"2018-01-12T05:42:58Z","title":"MINE: Mutual Information Neural Estimation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.04062","snapshot_observed_at":"2026-08-07T12:15:26.677058Z","title":"Mine: Mutual information neural estimation, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.677058Z"},"links":{"cited_paper":"/paper/1801.04062","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:7b8f8f6085d9c4ff88f6f81f457da923a8b2a9aba4c1738f8e7790717b719d8b","observation_id":"18f8070f-1f99-4a59-b36f-019f150956cf","resolution":{"observed_at":"2026-08-07T12:15:26.677058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1206.5538","last_updated":"2014-04-23T11:48:51Z","snapshot_observed_at":"2026-08-04T23:10:50.439752Z","submitted_at":"2012-06-24T20:51:38Z","title":"Representation Learning: A Review and New Perspectives","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.5538","snapshot_observed_at":"2026-08-07T12:15:26.716912Z","title":"Representation learning: A review and new perspectives, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.716912Z"},"links":{"cited_paper":"/paper/1206.5538","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:042dd7ee5cb48637466352462a6e952a5532617b101a2b6159c465ef2517a959","observation_id":"23d62f9f-e72c-4565-bfaa-df4a1b39cb26","resolution":{"observed_at":"2026-08-07T12:15:26.716912Z","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":"2026-08-07T12:15:33.708680Z","title":"Pixelsnail: An improved autoregressive generative model","venue":null,"work_id":"bc39de3a-88d6-48b2-bf92-686369aa1285","year":2018},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.754682Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:81afe8bf02842b25ff23148b35be39465d51ebb9136b7ffdede90eee1a7ee3d3","observation_id":"8b93d918-6e37-473b-82f7-47db98fddfc8","resolution":{"observed_at":"2026-08-07T12:15:33.752192Z","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":"2026-08-07T12:15:33.569402Z","title":"Diffusion models beat gans on image syn- thesis","venue":null,"work_id":"8d6c45d3-f950-4b43-869b-5f0380faec27","year":2021},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.788523Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:1898a16adc8670cab9d4bbae030cbb1c2deb64990815b7b80c1ffb2ed8c78ff9","observation_id":"caf0a3a6-e2d5-4014-8776-626e4ac2d476","resolution":{"observed_at":"2026-08-07T12:15:33.630735Z","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":"2026-08-07T12:15:33.472850Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":"050d85a8-70fd-415a-927c-3fe7d97ebd12","year":2020},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.829511Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:39b5af988a8bdf1969267e97534964d9f35a1085c8a944f4da60293606b486fa","observation_id":"a47efc30-2422-44b0-b370-d733bfe02796","resolution":{"observed_at":"2026-08-07T12:15:33.534568Z","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":"2026-08-07T12:15:26.916334Z","title":"Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.916334Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:e8f6684c1dde8822d7bc2d546ad07dcdd305e38401fffa1dbb4d64568d407d80","observation_id":"95ca844c-ad1c-4b57-b384-1a4b640d0ab7","resolution":{"observed_at":"2026-08-07T12:15:26.916334Z","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":"2026-08-07T12:15:26.985692Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:26.985692Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:b6d5ac77e2c733d4c7d61b724ede033aa8599dabf4fe119b0e5cd4a0ea255749","observation_id":"72160000-33a0-4aa0-bdd8-89949c0425f4","resolution":{"observed_at":"2026-08-07T12:15:26.985692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-07T12:15:27.035476Z","title":"Kingma and Max Welling","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.035476Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:7108af5dd8d32af4ab0ae3a580561648aad07ec39b8bd1e08c848c36b39f2818","observation_id":"8a8db6b9-71b7-4518-929e-809d51944c39","resolution":{"observed_at":"2026-08-07T12:15:27.035476Z","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":"2026-08-07T12:15:27.068218Z","title":"Kingma, Tim Salimans, Ben Poole, and Jonathan Ho","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.068218Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:99cf91d0783c72e096d63bb36e9ffaaf510fc43402d0fb413032d87c871f596e","observation_id":"6a993358-700d-4809-8004-6729aeb37b84","resolution":{"observed_at":"2026-08-07T12:15:27.068218Z","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":"2026-08-07T12:15:27.148739Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.148739Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:a08a73152e4cb73117704b53e24cf07cfb03ab8b4da9d8adcd208032b06113b2","observation_id":"4cba30d0-116a-4847-ad90-f47c55b11b34","resolution":{"observed_at":"2026-08-07T12:15:27.148739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01373","last_updated":"2024-12-02T10:58:09Z","snapshot_observed_at":"2026-08-09T14:29:53.664470Z","submitted_at":"2024-12-02T10:58:09Z","title":"Hierarchical VAE with a Diffusion-based VampPrior","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.01373","snapshot_observed_at":"2026-08-07T12:15:27.185758Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.185758Z"},"links":{"cited_paper":"/paper/2412.01373","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:92e69ab1a1506319eed126bfc978b1f4da268535665f3d7e7804f79c4745ac7e","observation_id":"8b9aa703-b447-4af5-b03b-c2f5cd48aa74","resolution":{"observed_at":"2026-08-07T12:15:27.185758Z","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":"2026-08-07T12:15:33.345224Z","title":"Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","venue":null,"work_id":"eb0c6ff3-ada2-4a53-ba3f-a024ebc5a831","year":2022},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.272819Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:b46b1f328f2f64274b8f62c4e2136649a291d9af3441fd56a9ec94d646f8fd73","observation_id":"52e1d58c-6f48-429c-ab6b-dbc7d621d7a1","resolution":{"observed_at":"2026-08-07T12:15:33.397463Z","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":"2302.05872","last_updated":"2023-05-26T02:55:08Z","snapshot_observed_at":"2026-08-09T14:30:09.713768Z","submitted_at":"2023-02-12T08:35:39Z","title":"I$^2$SB: Image-to-Image Schr\\\"odinger Bridge","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.05872","snapshot_observed_at":"2026-08-07T12:15:27.342911Z","title":"Theodorou, Weili Nie, and Anima Anandkumar","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.342911Z"},"links":{"cited_paper":"/paper/2302.05872","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:846708126c67f34d33ead8d14cd73f35202f59848b2ff2ecbac8b5ec3afcc83b","observation_id":"c2084f6b-9b55-4f0f-a2f3-b280b0956327","resolution":{"observed_at":"2026-08-07T12:15:27.342911Z","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":"2026-08-07T12:15:33.222152Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":"fdecd2d7-7dbc-4d1d-b7bc-6932fafb4d99","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.392483Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:68e74568f0d2635648a14eb0215b32e50c6dd285c694638367c3024c0a61f32d","observation_id":"15739325-da92-4711-90f3-40096930a6ed","resolution":{"observed_at":"2026-08-07T12:15:33.286558Z","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":"2026-08-07T12:15:27.443580Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.443580Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:6ccff6094db5d65982cc4ee7169c0228c935182db85584ad5cd7443591c45655","observation_id":"35757f5e-0ace-4b47-9975-96fa7d8fdbb3","resolution":{"observed_at":"2026-08-07T12:15:27.443580Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-07T12:15:27.482848Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.482848Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:ff97b10a02bcb62c466c9d0796e18d837060c5b1ce11f0cf5730919424a6d74b","observation_id":"aa9d0639-1f01-498c-ae68-e8228f39ac6c","resolution":{"observed_at":"2026-08-07T12:15:27.482848Z","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":"2026-08-07T12:15:33.143112Z","title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","venue":null,"work_id":"d0e82cec-5b5e-4f37-93c2-e29e11c04196","year":2022},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.515584Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:c93ad17522c87ff17583255bd6c48e43339fd92f3f5b5bf7fd0770053fd9821d","observation_id":"1599c538-3e42-4a96-afa8-6c99edd747f6","resolution":{"observed_at":"2026-08-07T12:15:33.170252Z","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":"1705.05035","last_updated":"2019-06-08T00:56:16Z","snapshot_observed_at":"2026-08-09T14:30:10.563113Z","submitted_at":"2017-05-14T22:53:13Z","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","version":3},"cited_work":{"arxiv_id":"1705.05035","doi":null,"metadata_source":"pith","pith_arxiv_id":"1705.05035","snapshot_observed_at":"2026-08-07T12:15:30.063900Z","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","venue":"cs.LG","work_id":"56c0d0d0-0e0c-494c-98de-c5e2a6d8c3e9","year":2017},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.598184Z"},"links":{"cited_paper":"/paper/1705.05035","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:b9af768cb52cbf1b85a04b5260b840cf12eedbfb4ba414365ba4ed1010789d11","observation_id":"252582ec-a70e-4c1a-9c0b-b3745d231b1e","resolution":{"observed_at":"2026-08-07T12:15:30.124935Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:15:33.059751Z","title":null,"venue":null,"work_id":"9ecf005b-0166-4560-b0c4-d4aac6fa2bde","year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.681528Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:62a4772c03b8d926b3fa1697643e95beb51c1323baf4a86d2e1ef70f14bb57e7","observation_id":"185ce075-ee6f-4a18-a1ee-be89358a27fb","resolution":{"observed_at":"2026-08-07T12:15:33.097718Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:15:32.926773Z","title":"Diamos, Erich Elsen, David García, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu","venue":null,"work_id":"09c770ba-c608-4899-a6eb-169651bdc66f","year":2018},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.726139Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:e87d815af25b4892b81e94e321d58e8b8ae6a454260513e4bca74c3b6e093593","observation_id":"7759a2d9-dd1d-4b4f-964b-7ed0abfd7356","resolution":{"observed_at":"2026-08-07T12:15:32.998853Z","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":"2026-08-07T12:15:32.790961Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":"101ff90a-4e3e-451b-8ec7-f6e7d6dec3f9","year":2021},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.786308Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:8238d1ff6e5c97de535e23e86ef7ae6e616e88502ca9b8daa3468e1d673c1a17","observation_id":"e7756d94-98bd-4648-9bad-b3b85e9d9b5f","resolution":{"observed_at":"2026-08-07T12:15:32.830480Z","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":"2026-08-07T12:15:32.708074Z","title":"Diffenc: Variational diffusion with a learned encoder","venue":null,"work_id":"6cc02702-52b1-4b67-a1c3-2ec7d1110704","year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.823841Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:3276603424e3db5bfc4213d669126a291e2ef8cab62f94f5f922e4790ed1275d","observation_id":"b3383197-b190-42ab-a6b1-499de91a4285","resolution":{"observed_at":"2026-08-07T12:15:32.731714Z","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":"2026-08-07T12:15:32.489167Z","title":"Input perturbation reduces exposure bias in diffusion models","venue":null,"work_id":"a481bf7d-47f8-4add-8127-6a02a6bfd62a","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.865251Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:9a2390a2d35b1acd2eee0332e636c6e9a794f3d8d73a12ee8d6f12b4d0d9876d","observation_id":"ea9e6afd-0a20-4756-8bce-f154c1ddd719","resolution":{"observed_at":"2026-08-07T12:15:32.599781Z","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":"2026-08-07T12:15:32.387574Z","title":null,"venue":null,"work_id":"3f478610-3816-483f-a900-935dd3bf2fe3","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.918604Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:3d2687279456266190709d5da1e8a591405c255adec3c4136019829d95be5c29","observation_id":"b6a0034f-60e1-4462-b1ec-fa4c11464aab","resolution":{"observed_at":"2026-08-07T12:15:32.424299Z","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":{"arxiv_id":"2201.00308","last_updated":"2022-11-29T07:18:50Z","snapshot_observed_at":"2026-08-09T14:29:56.183606Z","submitted_at":"2022-01-02T06:44:23Z","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.00308","snapshot_observed_at":"2026-08-07T12:15:28.008310Z","title":"Diffusevae: Efficient, controllable and high-fidelity generation from low-dimensional latents, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.008310Z"},"links":{"cited_paper":"/paper/2201.00308","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:3e0544a80a666401fe497d6129d4a9b3bc8b0219204d82100c54eed6dab6e1cf","observation_id":"7f5aba87-e353-4e27-8b04-3aa56c29a17c","resolution":{"observed_at":"2026-08-07T12:15:28.008310Z","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":"2026-08-07T12:15:32.292732Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"60b1e5a9-69c4-46ae-b664-fb2cf91c6b12","year":2019},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.072409Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:30b9c33251c9c24a369d02bc2500446787669d5abf3dac9877351fdc3c8d9e2c","observation_id":"2beb397e-64d9-4f40-8247-c52ffec5f5c3","resolution":{"observed_at":"2026-08-07T12:15:32.328004Z","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":"2026-08-07T12:15:32.180085Z","title":"Diffusion autoencoders: Toward a meaningful and decodable representation","venue":null,"work_id":"b206a745-ebda-43f4-a484-733b51108509","year":2022},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.133825Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:5a8cdc3bd4d552fab8443ef0322a230668693287b34c043bae216b214c4e0458","observation_id":"35fbae26-b7e3-4f98-99a9-fea72015ed66","resolution":{"observed_at":"2026-08-07T12:15:32.238824Z","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":"2026-08-07T12:15:32.021030Z","title":"Generating diverse high-fidelity images with VQ-V AE-2","venue":null,"work_id":"8d569042-ab34-4945-b952-2e0c37156e49","year":2019},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.179701Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:8f894f111c3255952a899849f530ebb19bb57a2abd80a8ab3ae063f70ce03701","observation_id":"d1a99857-85ea-4540-bd74-710b52abd2b8","resolution":{"observed_at":"2026-08-07T12:15:32.090373Z","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":"2026-08-07T12:15:31.934501Z","title":"Discrete variational autoencoders","venue":null,"work_id":"ebefb76c-1aae-468c-bbfc-b72a0740d39b","year":2017},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.228710Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:63d251fda9db317dbe6df6788dc494c5c74afa3b7ef546513edf5d7e193f3f55","observation_id":"03cedc20-d178-456a-b09f-c3a28666ec7b","resolution":{"observed_at":"2026-08-07T12:15:31.965943Z","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":"2026-08-07T12:15:31.798246Z","title":"pytorch-fid: FID Score for PyTorch","venue":null,"work_id":"49af79fa-a971-439a-b367-5e0b65ebc19f","year":2020},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.287546Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:3298ae028a1fac4e23b8ada626c930c0a454234482fcae5ebd8a4de2aebe4603","observation_id":"bec70621-5ad4-43d9-ba6c-27cf7147830d","resolution":{"observed_at":"2026-08-07T12:15:31.881640Z","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":"2026-08-07T12:15:31.678229Z","title":"Denoising diffusion implicit models","venue":null,"work_id":"ceffcb6a-1e9b-44ac-8294-50678d16325e","year":2021},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.353276Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:2b3ad7b72f6090d5f4d94f44bdb1d2eafbbefcedfc84c2dd1a57b2c1dcc7bf86","observation_id":"c30fe125-0a22-4a8d-b406-2a2b57e10a73","resolution":{"observed_at":"2026-08-07T12:15:31.753617Z","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":"2026-08-07T12:15:31.593402Z","title":"Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole","venue":null,"work_id":"f5bcf418-b7ad-4d40-86b9-68abc25b76f3","year":2021},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.423511Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:9fe532c5ed473bd564c296b12bab4c6ad8b1bbb9df2e296d70f8adf19a2e8774","observation_id":"2c09add7-3915-47a9-9435-dbb32e6f3a90","resolution":{"observed_at":"2026-08-07T12:15:31.627946Z","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":"2026-08-07T12:15:31.517342Z","title":"Dual diffusion implicit bridges for image-to-image translation","venue":null,"work_id":"a21b8c59-e8ac-4997-999c-ba34acca1e18","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.460489Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:4d2a2ff0d99765abe8db24e0df990850a331637382b4665bbd1f6675876b7174","observation_id":"b098b91a-5218-4d0c-8591-869160cc4023","resolution":{"observed_at":"2026-08-07T12:15:31.556872Z","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":"2026-08-07T12:15:31.395117Z","title":"NV AE: A deep hierarchical variational autoencoder","venue":null,"work_id":"22b4d101-d4ca-409e-808d-97a00436c5d5","year":2020},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.541377Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:28360701eb274c0c6cecbe2235b03957e97539bd3f9240da6d0dbb6b00ed21bb","observation_id":"688790ce-fb0a-4907-9518-cb88b42d65a0","resolution":{"observed_at":"2026-08-07T12:15:31.449313Z","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":"2026-08-07T12:15:31.279375Z","title":"Macready, Zhengbing Bian, Amir Khoshaman, and Evgeny Andriyash","venue":null,"work_id":"468a6f6a-fbe8-4e54-afc8-6654f170011d","year":2018},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.602214Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:611399d6a3d1cc34abe28e1e61b4f40eb446484606e60e1e1c6eb12c954eba21","observation_id":"20cf8d6d-aa70-453e-86d9-3e2cc515128c","resolution":{"observed_at":"2026-08-07T12:15:31.328192Z","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":"2026-08-07T12:15:31.126801Z","title":"Neural discrete representation learning","venue":null,"work_id":"def30550-b6d9-4169-9af1-25905c68af3d","year":2017},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.692060Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:86081740077d46d51af782cfde02608c6238039b28f9251fa1d187ac254c6493","observation_id":"ee1ef2b5-afb6-4dc1-9489-e36a577aa474","resolution":{"observed_at":"2026-08-07T12:15:31.173011Z","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":"2026-08-07T12:15:30.986748Z","title":"Infodiffusion: Representation learning using information maximizing diffusion models","venue":null,"work_id":"d6b5802b-5e4a-4086-8f36-2bf4a581279d","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.752393Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:77c62fc389310de8fd08b4a8a403009c79e6285147fb2472f536386540431274","observation_id":"4f3348b9-b078-4327-96f8-431c153cdb08","resolution":{"observed_at":"2026-08-07T12:15:31.041344Z","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":"2026-08-07T12:15:28.816091Z","title":"Binary latent diffusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.816091Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:7ece84fe093bbf04f582239b8b553e192e4df5470dc33adc44c58b2a02073db5","observation_id":"6f3af21e-0358-44ef-9d79-cb3148e0e07b","resolution":{"observed_at":"2026-08-07T12:15:28.816091Z","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":"2026-08-07T12:15:30.865164Z","title":"Disdiff: Unsupervised disentanglement of diffusion probabilistic models","venue":null,"work_id":"3460a5b6-0119-48d0-9d82-266ea02c49af","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:28.957035Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:31e056ceb7e436851be854dfa2671fed640047ec3dbd904d6d3b31e71c39a07a","observation_id":"303b40ca-1588-4ddb-a258-4e28f6022e2e","resolution":{"observed_at":"2026-08-07T12:15:30.924493Z","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":"2026-08-07T12:15:29.048846Z","title":"Diffusion model as representation learner","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.048846Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:f0b9dfd65fc6df898e6b1554e09b56d9b80ef4ca30daeda5616fbb7375b70978","observation_id":"010eb39c-ebb0-4dc5-a011-2d5ea112e933","resolution":{"observed_at":"2026-08-07T12:15:29.048846Z","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":"2026-08-07T12:15:30.714376Z","title":"Exploring diffusion time-steps for unsupervised representation learning","venue":null,"work_id":"7060d09d-0c3a-4ba9-b38b-63861db2cd50","year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.151950Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:3b0448e35cc252c608da316972a01cad3670cd9b82722b539cc60ba2f96e9709","observation_id":"b8fdcd97-6542-4180-b9cd-c78a279efe5b","resolution":{"observed_at":"2026-08-07T12:15:30.795580Z","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":"2026-08-07T12:15:29.245040Z","title":"Efros, Eli Shechtman, and Oliver Wang","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.245040Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:c4b0ddb499f573a3850eaf93d88b1571bca136aba200a6c355e31539f3b89fbf","observation_id":"caa0228a-a387-4e01-babd-3f5e8ca402c8","resolution":{"observed_at":"2026-08-07T12:15:29.245040Z","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":"2026-08-07T12:15:30.616019Z","title":"Unsupervised representation learning from pre-trained diffusion probabilistic models","venue":null,"work_id":"10ee42d7-0c16-4407-8bc5-eab779ff85f5","year":2022},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.306865Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:5410bd5c9bb70d30e3ef78c86e6a5c1234e09faa6f0f5e663598ebf76fde3599","observation_id":"11bb0f8d-a602-4863-a057-bfe44e8ec68c","resolution":{"observed_at":"2026-08-07T12:15:30.663493Z","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":"2310.09912","last_updated":"2023-11-30T11:03:01Z","snapshot_observed_at":"2026-08-09T14:30:20.315696Z","submitted_at":"2023-10-15T18:44:30Z","title":"Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models","version":3},"cited_work":{"arxiv_id":"2310.09912","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.09912","snapshot_observed_at":"2026-08-07T12:15:29.753791Z","title":"Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models","venue":"cs.CV","work_id":"5fc74d24-9656-4285-b5ab-a70932b8303c","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.356448Z"},"links":{"cited_paper":"/paper/2310.09912","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:e165cc8297a77349f4a26d0bfe29f13ab62144fa38172082670eeb3d3686e625","observation_id":"798048a3-727e-4f86-a0a7-d9818d9ff850","resolution":{"observed_at":"2026-08-07T12:15:29.797908Z","resolver_source":"local_arxiv","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v37i3.25465","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":"Shiftddpms: Exploring conditional diffusion models by shifting diffusion trajectories","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"674d787d-cfd4-4cae-8661-c2f4c25ea3f5","year":2023},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.437512Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:16fce49efe7047e65920fb874705778d1103cc07c48e2eff590ca6357bc2db55","observation_id":"63678ac0-dbed-4bde-b9cb-294e0e0ef6f0","resolution":{"observed_at":"2026-08-07T12:15:30.560614Z","resolver_source":"doi","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"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02262","last_updated":"2018-05-30T17:28:31Z","snapshot_observed_at":"2026-07-06T05:45:57.083160Z","submitted_at":"2017-06-07T17:05:01Z","title":"InfoVAE: Information Maximizing Variational Autoencoders","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02262","snapshot_observed_at":"2026-08-07T12:15:29.489843Z","title":"Infovae: Information maximizing variational autoencoders, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.489843Z"},"links":{"cited_paper":"/paper/1706.02262","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:b428f0d0b6464e75454767afc5904340ceed9df0c556e06ed1c8ab92dfff88c1","observation_id":"53f1e01e-000c-478b-b769-60485a2c9204","resolution":{"observed_at":"2026-08-07T12:15:29.489843Z","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":"2026-08-07T12:15:30.364911Z","title":"Denoising diffusion bridge models","venue":null,"work_id":"1dbd6f4b-9d6c-4be0-b8ac-a08975499802","year":2024},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.552005Z"},"links":{"citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:7e745eb20e41a3cf97d3a77973b3f10e5e82b4fd9aed7390e9660d7eaeecc140","observation_id":"254de4e0-aed9-4cdc-90be-c14032053e7d","resolution":{"observed_at":"2026-08-07T12:15:30.438433Z","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":"1801.09797","last_updated":"2018-01-29T23:36:11Z","snapshot_observed_at":"2026-08-06T12:04:37.790363Z","submitted_at":"2018-01-29T23:36:11Z","title":"Discrete Autoencoders for Sequence Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.09797","snapshot_observed_at":"2026-08-07T12:15:29.592118Z","title":"Discrete autoencoders for sequence models, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:29.592118Z"},"links":{"cited_paper":"/paper/1801.09797","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:2c2fbefaca19cf5335afea24a5939b44392c56ed6b82862a0c4f6b992ed1b7f0","observation_id":"55d2cfb5-8192-4bfc-a63a-e5323178f232","resolution":{"observed_at":"2026-08-07T12:15:29.592118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.00630","last_updated":"2023-04-14T00:20:30Z","snapshot_observed_at":"2026-08-09T14:29:00.548718Z","submitted_at":"2021-07-01T17:43:20Z","title":"Variational Diffusion Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.00630","snapshot_observed_at":"2026-08-07T12:15:27.109183Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T12:15:27.109183Z"},"links":{"cited_paper":"/paper/2107.00630","citing_paper":"/paper/2506.00136"},"observation_digest":"sha256:5ef4dad371ebe3f18a40a2e2a0888db9b066efdfc3e5d29031cd15c259ffb152","observation_id":"d635b594-4b72-486f-8d1e-97e9ba49bcae","resolution":{"observed_at":"2026-08-07T12:15:27.109183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.00136","last_updated":"2025-05-30T18:14:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T21:08:12.140971Z","submitted_at":"2025-05-30T18:14:09Z","title":"On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":3,"verified_fuzzy":27},"total_outbound_references":50},"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 50 of 50 outbound references and 1 inbound Pith citation observation for arXiv:2506.00136."}