{"as_of":"2026-08-08T20:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e6ff09eb86736e8ff6afadc08270571af643c855b14e056fbcce09cb97eafa22","coverage":[{"denominator":90,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":90,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T01:07:12.734749Z","state":"measured"},{"denominator":90,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":90,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.03082/citation-record","integrity":"/paper/2608.03082/integrity","json":"/paper/2608.03082/citation-record.json","paper":"/paper/2608.03082"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T01:07:08.894872Z","title":"Rep- resentation alignment for generation: Training diffusion transformers is easier than you think,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:08.894872Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:47d391585a9125efe2175f7466d45a9cecc4350cbd991204b5ddc30c188f3a11","observation_id":"9eefebe5-f3e8-4a64-abe7-eadeca7d4602","resolution":{"observed_at":"2026-08-08T01:07:08.894872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.09027","last_updated":"2025-07-24T15:55:00Z","snapshot_observed_at":"2026-08-08T15:14:26.502885Z","submitted_at":"2025-06-10T17:53:29Z","title":"Diffuse and Disperse: Image Generation with Representation Regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.09027","snapshot_observed_at":"2026-08-08T01:07:08.944750Z","title":"Diffuse and disperse: Image generation with representation regularization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:08.944750Z"},"links":{"cited_paper":"/paper/2506.09027","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:13d5a245442c7501b1ec30588c1be1b8cf8082622336f04816529c598bee80a4","observation_id":"0c3606d6-35e8-43c3-8c95-8fe4987939d9","resolution":{"observed_at":"2026-08-08T01:07:08.944750Z","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":"2026-08-08T01:07:09.006801Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.006801Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:1cb998e4182ac6843efd4f340d05cf1cd2e1de8b111d9e034a53b7c6f52302a7","observation_id":"5c8996ab-23e1-4270-9de0-bc151040a849","resolution":{"observed_at":"2026-08-08T01:07:09.006801Z","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":"2026-08-08T01:07:09.054853Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.054853Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:a2b587bdce2a350db4056ab8b67f85b39633defdd9c3599380298acc7be88320","observation_id":"52697dd3-a854-4bc1-8e6b-1193f90ae653","resolution":{"observed_at":"2026-08-08T01:07:09.054853Z","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":"2026-08-08T01:07:09.084764Z","title":"Scalable diffusion models with transformers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.084764Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:9392b9722271d9f73154167cd7284b380ee95fd549aa19d29be383ea3f2964c5","observation_id":"b6d412d4-4b82-4054-a1db-979d6fb2c3d7","resolution":{"observed_at":"2026-08-08T01:07:09.084764Z","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":"2026-08-08T01:07:09.134854Z","title":"All are worth words: A vit backbone for diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.134854Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:71974886a1e3710f8ab83c1f79570bc5dd1128b0c613ed9036946b165959769b","observation_id":"ddc0f6bf-d64b-47e4-a42e-e2c72dad1b36","resolution":{"observed_at":"2026-08-08T01:07:09.134854Z","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":"2026-08-08T01:07:09.194760Z","title":"Sana: Efficient high-resolution text-to-image syn- thesis with linear diffusion transformers,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.194760Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:3fd6d07c481a09fed293c7d380f7ac733de3b64b252d9809b9f261dce59274ce","observation_id":"f78989f5-0236-4cf8-8a9e-bf96308ce537","resolution":{"observed_at":"2026-08-08T01:07:09.194760Z","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":"2026-08-08T01:07:09.246267Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.246267Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:4f80a94fa68a786338740440a584ce567a438879cbe95b8abce0fdab577997aa","observation_id":"c28791e2-3a2b-4166-9e1a-49c2050f2762","resolution":{"observed_at":"2026-08-08T01:07:09.246267Z","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":"2026-08-08T01:07:09.284755Z","title":"Cogvideox: Text-to-video diffusion models with an expert transformer,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.284755Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:a33472633ca8b77e1dca4b8bf5c28b3413aa62890b2cc4ff82fd96f81f8dd0db","observation_id":"0dfca87a-b90f-4f8d-80bb-5ac014aad640","resolution":{"observed_at":"2026-08-08T01:07:09.284755Z","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":"2026-08-08T01:07:09.314761Z","title":"Photorealistic video generation with diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.314761Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:3b4724e102566d593129efbdf3a5eedb3272e91d0c25480d9a486b76735cc655","observation_id":"5d2e2771-8153-4826-91a3-b1b56047e00f","resolution":{"observed_at":"2026-08-08T01:07:09.314761Z","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":"2026-08-08T01:07:09.354758Z","title":"Diffusion based representation learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.354758Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:fa26e4be0b0613149b885956dffeb519d5ebbaa06b2e5d9052ce1824e985ea8e","observation_id":"39d51981-72b7-4c3e-9c04-affec5a06a92","resolution":{"observed_at":"2026-08-08T01:07:09.354758Z","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":"2026-08-08T01:07:09.404753Z","title":"Deconstructing denoising diffusion models for self-supervised learning,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.404753Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:9bb495639e3935a3afd38be1e00d440233f99b00e125285bdc2b854755eb1ef2","observation_id":"134f6868-af80-41ee-931c-311937d7df17","resolution":{"observed_at":"2026-08-08T01:07:09.404753Z","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":"2026-08-08T01:07:09.444744Z","title":"Denoising diffusion autoencoders are unified self-supervised learners,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.444744Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:3da7a852c5d9ad44c3b8620dc7e02495943396896a42657d75a3fb425b6ada7f","observation_id":"dfeb2d4c-e52e-43f3-8a34-9d569ae32008","resolution":{"observed_at":"2026-08-08T01:07:09.444744Z","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":"2026-08-08T01:07:09.474754Z","title":"REPA-E: Unlocking vae for end-to-end tuning with latent diffusion transformers,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.474754Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:62c2a0e7bbcb3e9be5042236d1a21fd2e1f9d81f9dd0b1ab125df38a62c12df5","observation_id":"6c7ca48a-ffe0-4408-9d27-8222aecc8508","resolution":{"observed_at":"2026-08-08T01:07:09.474754Z","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":"2026-08-08T01:07:09.514854Z","title":"Representation entanglement for generation: Training diffusion transformers is much easier than you think,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.514854Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:208bb49fc32349c6d5086d1356538d22f84579db7e9a7d296f55a26f87a8e881","observation_id":"00d560bd-210f-4e98-a581-f411d87bc61b","resolution":{"observed_at":"2026-08-08T01:07:09.514854Z","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":"2026-08-08T01:07:09.565664Z","title":"No other representation component is needed: Diffusion transformers can provide representation guidance by themselves,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.565664Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:080964cbd78b1ceec5c8ac7d28ffb04f352a1ae97c966d3cf2b4ce06b8f72b41","observation_id":"182eee78-7985-4f0c-99b8-94008af7ee9a","resolution":{"observed_at":"2026-08-08T01:07:09.565664Z","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":"2026-08-08T01:07:09.606499Z","title":"Similarity of neural network representations revisited,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.606499Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:2f06c66d5ad5156063730e52be746c062d065457719a0abda4fe730d49ca4655","observation_id":"a13f6251-2b14-48b0-aba9-530e7f87c20b","resolution":{"observed_at":"2026-08-08T01:07:09.606499Z","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":"2026-08-08T01:07:09.654912Z","title":"Mean flows for one- step generative modeling,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.654912Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:03fb050a313bc20e51da11916c1de843b648c00564e6850f8644d758e788e583","observation_id":"d2e436a3-fea7-4f5b-9ef3-a60022f4ba23","resolution":{"observed_at":"2026-08-08T01:07:09.654912Z","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":"2026-08-08T01:07:09.684832Z","title":"Diversedit: Towards diverse representation learning in diffusion transformers,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.684832Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:22e0db3e98df9f7fdeb7315f54792e252a248b54b451ba95bebd7fde78ff8f21","observation_id":"dce06210-f13b-445c-996d-ba23df1e4ea0","resolution":{"observed_at":"2026-08-08T01:07:09.684832Z","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":"2026-08-08T01:07:09.734757Z","title":"Representation learning: A review and new perspectives,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.734757Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:c2708ac0cc549d82d85e83088a3a240b029a98cac4a4a0f931f77ecb8451769c","observation_id":"aa854ff2-394b-418c-bfa3-71900c02d30d","resolution":{"observed_at":"2026-08-08T01:07:09.734757Z","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":"2026-08-08T01:07:09.791000Z","title":"Disentangled rep- resentation learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.791000Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:170af7e8b7bbc291092062d806beea07e622061ac227ab32005ba43c3c2c2d91","observation_id":"b2620a47-e57f-41ad-a772-f0a5a4e3d689","resolution":{"observed_at":"2026-08-08T01:07:09.791000Z","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":"2026-08-08T01:07:09.814763Z","title":"Deep diversity- enhanced feature representation of hyperspectral images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.814763Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:95cc049eecc92e122580afb5a0445cbea13c229e5c3898e524bac6ba1ed8a052","observation_id":"4dfa7185-fcbd-4837-8fa0-1617ea2b6ec4","resolution":{"observed_at":"2026-08-08T01:07:09.814763Z","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":"2026-08-08T01:07:09.864757Z","title":"Self-supervised visual feature learning with deep neural networks: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.864757Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:3f3af5f9d82f3eab8d7aa9d3f9a53bfc1d6c81f25687fca858e2d05863b6b6e2","observation_id":"d16ef599-840f-4dcc-a1cc-f21bef074fe0","resolution":{"observed_at":"2026-08-08T01:07:09.864757Z","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":"2026-08-08T01:07:09.904753Z","title":"Bootstrap your own latent-a new approach to self-supervised learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.904753Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:a865965fd6a95624c41b8b10bc138284c4c8ab2f19ab6e77fd3da65cd469f49b","observation_id":"97fc1321-3aa8-4a65-8780-89cda0add52c","resolution":{"observed_at":"2026-08-08T01:07:09.904753Z","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":"2026-08-08T01:07:09.954757Z","title":"Dinov2: Learning robust visual features without supervision,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:09.954757Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:3ef4bcca41a3a9db5e6ccb0e0848d44c9b677bbc646f57de8077d4f49ebe15da","observation_id":"045253d3-f742-4e1e-a781-0083d5d47eed","resolution":{"observed_at":"2026-08-08T01:07:09.954757Z","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":"2026-08-08T01:07:10.014763Z","title":"An empirical study of training self- supervised vision transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.014763Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:7d70aa2e66b9b4db81dba146b8a7a13f9f2b09d094a96e92dadd29b31bc4fb29","observation_id":"f5e6173b-ea95-4242-8fa1-1da41529aff6","resolution":{"observed_at":"2026-08-08T01:07:10.014763Z","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":"2026-08-08T01:07:10.064753Z","title":"Auto-encoding variational bayes,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.064753Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:84bb5eb5858a0f68bd13eab070aca765906c8d110fd457e0a2ede0975c89b1d2","observation_id":"df93261b-da7a-4543-a7f2-7abb98f7cb74","resolution":{"observed_at":"2026-08-08T01:07:10.064753Z","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":"2026-08-08T01:07:10.094753Z","title":"Masked autoencoders are scalable vision learners,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.094753Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:80aa394bde810a6384a261341434fafe4bbfac50ba64098f35f04d6e42bb0ff7","observation_id":"b615f2e8-4ce1-4bd3-aa6f-64ff005a5201","resolution":{"observed_at":"2026-08-08T01:07:10.094753Z","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":"2026-08-08T01:07:10.134759Z","title":"Simmim: A simple framework for masked image modeling,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.134759Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:eb4d72d5831ef2efed6f2054411ae1630704744d70ef527dba5290cb8b3e8d16","observation_id":"1d1fc3f2-73ce-4d12-9048-f210b9797142","resolution":{"observed_at":"2026-08-08T01:07:10.134759Z","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":"2026-08-08T01:07:10.174755Z","title":"Diffusion model as representation learner,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.174755Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:05f72c0988e28ddc7e6276271658ce0d3d2c9b7bc7dddef28f83d1c989a1a5ab","observation_id":"c2f6e436-f2c7-4428-80aa-d911f8dd1002","resolution":{"observed_at":"2026-08-08T01:07:10.174755Z","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":"2026-08-08T01:07:10.224771Z","title":"Unsupervised representation learning from pre-trained diffusion probabilistic models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.224771Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:b44fc70be7bc84487b16602ecf99039efc9177e761da5bd897dc050d089c5895","observation_id":"820ecf71-70ac-46e4-8ab9-a338593886e9","resolution":{"observed_at":"2026-08-08T01:07:10.224771Z","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":"2026-08-08T01:07:10.268325Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.268325Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:a7719a5519670ba9c94e03cb63c140c0b4b2429844e6688a75c580fb7b05ea0e","observation_id":"64dfffef-6fe6-483c-a4ff-3eb9d8508720","resolution":{"observed_at":"2026-08-08T01:07:10.268325Z","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":"2026-08-08T01:07:10.314765Z","title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.314765Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:b265c8c81f11a7d33cb725d8f5490a70ed82f0fe2c2207d88ea3ca3605f0448d","observation_id":"df1ae8ef-787e-4670-b090-609aa3806bbc","resolution":{"observed_at":"2026-08-08T01:07:10.314765Z","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":"2026-08-08T01:07:10.364754Z","title":"Sigmoid loss for language image pre-training,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.364754Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:d81f5af2308fcd4f5e161127dbbfbddc0ad0dd8bd645beb66fc77b3ccc46de2a","observation_id":"0d1e3f80-8b2e-49e6-8016-eeefb1465306","resolution":{"observed_at":"2026-08-08T01:07:10.364754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14786","last_updated":"2025-02-20T18:08:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-20T18:08:29Z","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14786","snapshot_observed_at":"2026-08-08T01:07:10.414756Z","title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.414756Z"},"links":{"cited_paper":"/paper/2502.14786","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:60837c5ac41100be981587569b13539633f5b2bd554d1aa9297e877ce9d127e7","observation_id":"0a74da7e-a838-4e7d-90eb-1d97549d86e1","resolution":{"observed_at":"2026-08-08T01:07:10.414756Z","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":"2026-08-08T01:07:10.464762Z","title":"ImageNet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.464762Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:d93b535eab9bd46544ba70425537bcdae6ae3d5bc2a56845c6b940f78b785311","observation_id":"084034b7-379b-42a1-a139-7d9991483d1a","resolution":{"observed_at":"2026-08-08T01:07:10.464762Z","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":"2026-08-08T01:07:10.504751Z","title":"Assessing generative models via precision and recall,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.504751Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:c3272f664bc39d78f2bbd9eff008703ce6d62c8e154a0af7d154153a9d55f183","observation_id":"8703410c-28a3-4db6-87e0-b950e9513f3f","resolution":{"observed_at":"2026-08-08T01:07:10.504751Z","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":"2026-08-08T01:07:10.536725Z","title":"Im- proved precision and recall metric for assessing generative models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.536725Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:9b443d0732eac015c25ef0be547832028146dfcc685823bac9dd9db0fb9ab096","observation_id":"30cbd80b-7a25-4534-b916-da09ed29127a","resolution":{"observed_at":"2026-08-08T01:07:10.536725Z","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":"2026-08-08T01:07:10.564759Z","title":"Reliability of cka as a similarity measure in deep learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.564759Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:550ae304fbbd9d05b2575f816b239fee53ba810fb94543103758203c58eac15e","observation_id":"929e82ad-a828-485d-a77c-33df61671b56","resolution":{"observed_at":"2026-08-08T01:07:10.564759Z","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":"2026-08-08T01:07:10.604753Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.604753Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:935a81095ebc01032d2786ea9bae1c897f8dd74a194905a7df189d21811d86dc","observation_id":"79553ef7-e1e0-4086-8aa2-b6b6b6e34a9e","resolution":{"observed_at":"2026-08-08T01:07:10.604753Z","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":"2026-08-08T01:07:10.622310Z","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.622310Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:7f3eb63d3871e9dae7399b7ee111678e94fdea9eb0b894384c2629dd7c8fd6bb","observation_id":"ac5e7456-eff6-4fc3-9b75-214a98fa1b55","resolution":{"observed_at":"2026-08-08T01:07:10.622310Z","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":"2026-08-08T01:07:10.646417Z","title":"Generating images with sparse representations,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.646417Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:73d96d47fb4586315ea0ea2a73771d520e1828129a86b9a77e083b03759c14ca","observation_id":"2297a27f-cf5e-4dd2-8536-e8ce85b3d066","resolution":{"observed_at":"2026-08-08T01:07:10.646417Z","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":"2026-08-08T01:07:10.676665Z","title":"Denoising diffusion implicit models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.676665Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:face818f4b7cb5d380fbe41fc7b952a6950a14f7efb302d4852e6df05df2114e","observation_id":"136afa9d-5d3c-48f3-82d3-420633237ba4","resolution":{"observed_at":"2026-08-08T01:07:10.676665Z","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":"2026-08-08T01:07:10.724755Z","title":"Diffusion models in vision: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.724755Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:89ca0dcfd883b1acdbb63b4c65132c20366a8c38e50d6be423d7177605b91cc1","observation_id":"61814b8b-dc8c-471d-a5f1-e78f87021968","resolution":{"observed_at":"2026-08-08T01:07:10.724755Z","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":"2026-08-08T01:07:10.795236Z","title":"Pixart-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.795236Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:473ef9a892cefa527e2fb8dae1f4753a4660a15a120a22b3df688b76711908d2","observation_id":"5f1a1715-08bc-4edb-ab89-f07b934507ba","resolution":{"observed_at":"2026-08-08T01:07:10.795236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.03603","last_updated":"2025-03-11T08:14:25Z","snapshot_observed_at":"2026-08-03T00:44:01.942521Z","submitted_at":"2024-12-03T23:52:37Z","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.03603","snapshot_observed_at":"2026-08-08T01:07:10.844763Z","title":"Hunyuanvideo: A systematic framework for large video generative models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.844763Z"},"links":{"cited_paper":"/paper/2412.03603","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:2279e0d95e6a08b37a53a561a9a440d48ba902981d77f76675c44ba6d846e7d1","observation_id":"255cd55d-74ef-49f5-941f-441fa9942340","resolution":{"observed_at":"2026-08-08T01:07:10.844763Z","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":"2026-08-08T01:07:10.884755Z","title":"Flow matching for generative modeling,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.884755Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:90f50423748050a21c960c6f2c44cbe89dbc1328a86c1221f7a4d9d6e05e392c","observation_id":"61e9b3e3-67db-4f82-bf2d-17a73de12051","resolution":{"observed_at":"2026-08-08T01:07:10.884755Z","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":"2026-08-08T01:07:10.934754Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.934754Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:4b9c5b0a33694db72a8404b4a38b9d38f28e3b131f8b132dc1e11357f4494ee1","observation_id":"ecbf091d-6e10-4cfb-a831-f9db4212463b","resolution":{"observed_at":"2026-08-08T01:07:10.934754Z","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":"2026-08-08T01:07:10.984766Z","title":"Diffusion models beat gans on image synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:10.984766Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:af2031beba3c6b0f794fe35092ce95eb1dd4394895ccb6b087777947cfad6601","observation_id":"ee89fc97-8b15-467d-80ab-571d0f097323","resolution":{"observed_at":"2026-08-08T01:07:10.984766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-07T21:47:08.589400Z","submitted_at":"2023-11-25T22:28:38Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15127","snapshot_observed_at":"2026-08-08T01:07:11.034752Z","title":"Stable video diffusion: Scaling latent video diffusion models to large datasets,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.034752Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:b89ca7bf516d59a3a71daa8961eb21d66657653cf8b98b9ac0e3f4643e251ce8","observation_id":"43d895ed-75b8-4200-8b2a-7fc497534bea","resolution":{"observed_at":"2026-08-08T01:07:11.034752Z","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":"2026-08-08T01:07:11.094755Z","title":"SiT: Exploring flow and diffusion-based generative models with scalable interpolant transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.094755Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:9098fc6c3e92708c249c43c040788f18b8cd8c70fc8618ae3125418d9027444d","observation_id":"82c735ed-e854-45bd-95b9-333e2380d152","resolution":{"observed_at":"2026-08-08T01:07:11.094755Z","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":"2026-08-08T01:07:11.144768Z","title":"Dreamteacher: Pretraining image backbones with deep generative models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.144768Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:5d848d70f022e840c77ca9bb6fb3b42d122324d68a62e72aa92bbb0206a7fb10","observation_id":"44bcbdd8-fe9d-4ad4-9146-68cc19ab9595","resolution":{"observed_at":"2026-08-08T01:07:11.144768Z","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":"2026-08-08T01:07:11.194754Z","title":"Diffusion models and representation learning: A survey,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.194754Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:8cb8b0ee8bd17a0b5754e96b31684f93506c13b30ac45101e219d99f03ac356a","observation_id":"66e61252-2632-4578-864f-1ed3563b7360","resolution":{"observed_at":"2026-08-08T01:07:11.194754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08253","last_updated":"2025-03-11T10:17:32Z","snapshot_observed_at":"2026-08-07T17:13:41.536737Z","submitted_at":"2025-03-11T10:17:32Z","title":"SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08253","snapshot_observed_at":"2026-08-08T01:07:11.234772Z","title":"SARA: Structural and adversarial representation alignment for training-efficient diffusion models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.234772Z"},"links":{"cited_paper":"/paper/2503.08253","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:042f50c6115a019632c8930adaaf50a13bea91fa63ea3f7ae0745f9905666561","observation_id":"fc4ad0a0-471d-4bea-a2b0-4bfc0d587da1","resolution":{"observed_at":"2026-08-08T01:07:11.234772Z","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":"2026-08-08T01:07:11.274756Z","title":"Aligning text to image in diffusion models is easier than you think,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.274756Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:d1ca95bd7f2e09e26e50dfd5fc50304653233aae67980cc915c7fe4841991e09","observation_id":"08bfffde-d632-4c85-b63d-1a75b20dc617","resolution":{"observed_at":"2026-08-08T01:07:11.274756Z","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":"2026-08-08T01:07:11.324756Z","title":"Learning diffusion models with flexible representation guidance,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.324756Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:cefcbcb5d215c6baab4082c521226df4636c6d9201877eb08f5f6b27f737b6fc","observation_id":"f980f830-eb3f-4f76-9951-a0e3e5ffdd28","resolution":{"observed_at":"2026-08-08T01:07:11.324756Z","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":"2026-08-08T01:07:19.474751Z","title":"What matters for representation alignment: Global information or spatial structure?","venue":null,"work_id":"1fdc2760-189e-4017-b2f7-fb59aa3d05dd","year":2026},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.350618Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:20302c609d19d45a76c4e650bbc8a1a1e874bd8ebe673fc983023a87f93e7c37","observation_id":"6af938d4-c781-4599-83a2-5f13a29641cf","resolution":{"observed_at":"2026-08-08T01:07:19.514752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:19.294741Z","title":"Generative flows on discrete state-spaces: enabling multimodal flows with applications to protein co-design,","venue":null,"work_id":"e9e3a88e-05f1-4340-b7c7-b61d2174e9b2","year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.395415Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:deba22127690a0aa26bca6b6ca655ea210e1e3bd2207a594d99b9f9c61112c06","observation_id":"32c32a77-a467-439e-bfba-8aaa1c4ddfe4","resolution":{"observed_at":"2026-08-08T01:07:19.364756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:19.144733Z","title":"Ro- bust deep learning–based protein sequence design using proteinmpnn,","venue":null,"work_id":"d91b7982-6b3c-4349-a9b2-ae12495e0a21","year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.447051Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:20f70d2373f5849f14eb326ee60057b835802fa98a757a2727da488cf593569e","observation_id":"aabccb85-3476-4fdf-9922-0995e0497758","resolution":{"observed_at":"2026-08-08T01:07:19.184733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:19.004752Z","title":"MiDi: Mixed graph and 3d denoising diffusion for molecule generation,","venue":null,"work_id":"7d17fbde-267d-4da1-b141-be9e22b797ff","year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.494752Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:1bbff4718cb498417c0e2e942929cbd38d1dcc29660669553692c01bed9b1391","observation_id":"11d7d31f-1d1d-4df3-b7af-1bb3516aa3eb","resolution":{"observed_at":"2026-08-08T01:07:19.044752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:18.844765Z","title":"Navigating the design space of equivariant diffusion-based generative models for de novo 3d molecule generation,","venue":null,"work_id":"d490d45a-5083-4906-93ff-1e2f17488642","year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.536918Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:0f8d99b7f2d8a2f4bd7d2bab9165e3936ecce8f901a3de90b476fb85046ada97","observation_id":"a9e81d4d-55c4-468d-810e-a5502143546e","resolution":{"observed_at":"2026-08-08T01:07:18.884747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07266","last_updated":"2025-02-28T16:56:08Z","snapshot_observed_at":"2026-07-06T18:28:55.652937Z","submitted_at":"2024-06-11T13:51:51Z","title":"SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07266","snapshot_observed_at":"2026-08-08T01:07:11.574870Z","title":"Semlaflow–efficient 3d molecular generation with latent attention and equivariant flow matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.574870Z"},"links":{"cited_paper":"/paper/2406.07266","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:441cb286f9498022d2d8f73005d985a787309b7ddbaca384b141c75396dd49be","observation_id":"ff7431ac-8849-44f8-b3f0-5a26904dfc7e","resolution":{"observed_at":"2026-08-08T01:07:11.574870Z","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":"2026-08-08T01:07:18.674757Z","title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3,","venue":null,"work_id":"2c32e507-17b2-4678-87c1-c73d634bff70","year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.605259Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:559adc218a8c8c3242d14de43b683efd024ceb149324d0ff7263f655a6dd7ee6","observation_id":"b9bccc26-39ed-4697-81eb-ea51ad6b02bc","resolution":{"observed_at":"2026-08-08T01:07:18.714751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:18.514750Z","title":"Uni-mol: A universal 3d molecular representation learning framework,","venue":null,"work_id":"8e0bc321-f4cf-4838-9e89-5543cd4ddce9","year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.655094Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:b52c7e60ce12fe75154b8cfade36a4f27b906a21ec238cc2e9f9d3413947e787","observation_id":"02c3c8e0-99d9-4631-9cab-f2083ae1807e","resolution":{"observed_at":"2026-08-08T01:07:18.554739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:18.364745Z","title":"Measuring statistical dependence with hilbert-schmidt norms,","venue":null,"work_id":"784a1b6f-d4a3-40f5-a020-0a883f53d9eb","year":2005},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.684825Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:12124dd4b9ddf274cbf459f1577d27cb1892a0a049c8cbef908895af1f22c491","observation_id":"50ff010f-6e7c-4c55-8ce7-3a3f43d2aaa0","resolution":{"observed_at":"2026-08-08T01:07:18.404738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:18.216327Z","title":"Masked autoencoders are scalable vision learners,","venue":null,"work_id":"e3b548b5-9558-4fcf-aac3-f15084aa9ab5","year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.696522Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:9ca619f2c876f719b1af0a4cb42e0d2e2bcc7242fe601cc350f1d2f9604ede32","observation_id":"bc09b4bf-f238-4a22-ab58-f3958c660956","resolution":{"observed_at":"2026-08-08T01:07:18.255945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:18.084514Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":"9787a08f-95bf-43c3-ad2d-b5199d900430","year":2009},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.714296Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:4f167114ab10999a902576a1aa7e62f8abb7e4e068364907aa7364f696fa1bda","observation_id":"e7ca1dc6-5518-4125-b080-dd5d081c1401","resolution":{"observed_at":"2026-08-08T01:07:18.117941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:17.945129Z","title":"Improved techniques for training gans,","venue":null,"work_id":"68372b59-4afd-49bf-a74d-e515a6b7b19d","year":2016},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.734764Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:55973f6e5f86f74cf7ba5a6ce399a8124f3c15c3a68fe416f250a1d1b6b83fc2","observation_id":"fede1e98-bd61-42cc-a291-859df32f5aa6","resolution":{"observed_at":"2026-08-08T01:07:17.986698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-08T01:07:11.768695Z","title":"Classifier-free diffusion guidance,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.768695Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:4f349bec149cf23fcc7f688085cee15465bf445f25b4ba8095c8d6b193b3b986","observation_id":"d1eee231-7846-4424-ad9a-f9e09e377b9f","resolution":{"observed_at":"2026-08-08T01:07:11.768695Z","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":"2026-08-08T01:07:17.764753Z","title":"Understanding diffusion objectives as the elbo with simple data augmentation,","venue":null,"work_id":"e8e153a1-44ba-40df-a6b6-0fa951415f26","year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.834752Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:b1e685b8007185b1be631ab3d23a2a3eca9586c290a1a4cb02aa079360ca7b7d","observation_id":"6e9ca393-77d6-456a-b9a3-42739ece78cd","resolution":{"observed_at":"2026-08-08T01:07:17.814773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:17.564751Z","title":"Cascaded diffusion models for high fidelity image generation,","venue":null,"work_id":"bf6ef8b2-5ee4-4584-911e-9ee32f203b3c","year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.874768Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:aa65ab883383a4292a3dc48c2abcd9321a9b2e5748c1a2989ded3471d926b659","observation_id":"070fbff6-e2bf-4b7a-9271-360dd458fe47","resolution":{"observed_at":"2026-08-08T01:07:17.614743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:17.394745Z","title":"Sd- dit: Unleashing the power of self-supervised discrimination in diffusion transformer,","venue":null,"work_id":"d6493953-86e9-4da9-ab70-b5f08067ab66","year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.924758Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:e00aa50bbafe4e5d5217a9d5d72646e724d188c39d3c0a2ee3c4f3bc8d066d6d","observation_id":"c1c96284-a72f-4c44-b406-4281586cd685","resolution":{"observed_at":"2026-08-08T01:07:17.444739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09305","last_updated":"2024-03-05T01:10:18Z","snapshot_observed_at":"2026-08-03T18:21:25.175322Z","submitted_at":"2023-06-15T17:38:48Z","title":"Fast Training of Diffusion Models with Masked Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09305","snapshot_observed_at":"2026-08-08T01:07:11.974745Z","title":"Fast train- ing of diffusion models with masked transformers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:11.974745Z"},"links":{"cited_paper":"/paper/2306.09305","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:abcd38fa19d8a11a83b7ccbce3da5fd33d543a1c92fb34864244e6711bd5449f","observation_id":"51831a14-7900-4cd2-95da-7d1eb6f19e1f","resolution":{"observed_at":"2026-08-08T01:07:11.974745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14389","last_updated":"2024-02-21T15:45:20Z","snapshot_observed_at":"2026-07-06T15:07:52.629778Z","submitted_at":"2023-03-25T07:47:21Z","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.14389","snapshot_observed_at":"2026-08-08T01:07:12.008720Z","title":"Mdtv2: Masked dif- fusion transformer is a strong image synthesizer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.008720Z"},"links":{"cited_paper":"/paper/2303.14389","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:f7623d224f15d68b9f5660dd38f19b24f361dda3a7c31eb5e2cd4ee8a7e6aecb","observation_id":"9cad9d96-40dd-4e63-920c-63489b70685c","resolution":{"observed_at":"2026-08-08T01:07:12.008720Z","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":"2026-08-08T01:07:17.224757Z","title":"Improved techniques for training consistency models,","venue":null,"work_id":"28a942c6-c195-478a-a32e-916b9a3dd817","year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.055622Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:93eabafc5d01f02413226e564f6493bb3dfbcc5928fe682543bc44cb0aa21a2d","observation_id":"d4a9e613-a062-4272-9861-37d5bbeac011","resolution":{"observed_at":"2026-08-08T01:07:17.274753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:17.090443Z","title":"One step diffusion via shortcut models,","venue":null,"work_id":"1d812ab6-6469-4ae2-97f8-4c02083c2e34","year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.095872Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:03d94bab94e4a6177c071b3df4cc68d9b75f032f038feba6036e9c46045593b8","observation_id":"cbff9c18-fa9f-4c0b-848e-11d6308fb232","resolution":{"observed_at":"2026-08-08T01:07:17.124756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.964755Z","title":"Inductive moment matching,","venue":null,"work_id":"107879b7-6fe1-4d92-af8a-3135ae0443e7","year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.134828Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:6bf0b5e6d2c7264605642caa18e86d6712d9feb376b6e6d24ca05b450b2aa96e","observation_id":"14e727ac-74af-4882-85c5-c01b9c5ac2f6","resolution":{"observed_at":"2026-08-08T01:07:16.993642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.764756Z","title":"Fine-tuning discrete diffusion models via reward optimization with applications to dna and protein design,","venue":null,"work_id":"0a2ad25d-eed6-4289-b4f2-068faab4a854","year":2025},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.184755Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:ae4a19277b1d2e16fb973928f13392764788a5abfe32b268471ee3965f6c9389","observation_id":"a9e5a9fa-c527-4811-8b76-a2a4122f859d","resolution":{"observed_at":"2026-08-08T01:07:16.852501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.634758Z","title":"Evolutionary-scale prediction of atomic-level protein structure with a language model,","venue":null,"work_id":"36d1d776-74fe-4392-9c0c-d14e2f87bd99","year":2023},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.225000Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:ee4f9bb848f3cfb7914802550b6808b9c7447b46aa0a21501b8ec6a66816b217","observation_id":"ae672168-234c-4205-b02c-324d239b27ca","resolution":{"observed_at":"2026-08-08T01:07:16.664776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.494754Z","title":"GEOM, energy-annotated molecular conformations for property prediction and molecular genera- tion,","venue":null,"work_id":"103a2424-25dd-4dd3-b7ba-3eefd2961426","year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.275185Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:e6ba282446539911e1f26d07b65ac21371849cfd5abfc1a1fbfbb5c255372035","observation_id":"10890b9d-2310-4ed7-8e11-d3236f9972a2","resolution":{"observed_at":"2026-08-08T01:07:16.544764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.314753Z","title":"Quantum chemistry structures and properties of 134 kilo molecules,","venue":null,"work_id":"b1c46720-20c1-42b8-9fbc-68e18b3278c7","year":2014},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.324753Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:8d401c539e54042dff1df08e36e94f570b99011842749ff001362575824d0506","observation_id":"27c457d6-3c5f-4d48-890e-0319c40eb4d3","resolution":{"observed_at":"2026-08-08T01:07:16.374762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.180128Z","title":"The effective rank: A measure of effective dimensionality,","venue":null,"work_id":"d3ce1394-aeb0-4672-b1c4-60b3384c3146","year":null},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.362872Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:f6a11ba8ce00a37f409079905f21a2444d48958ecb82c10a55a0d856a6daab75","observation_id":"b17bd7fa-2365-4ddf-b18a-1042c16dcffc","resolution":{"observed_at":"2026-08-08T01:07:16.206741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:16.057164Z","title":"Visualizing and understanding convolu- tional networks,","venue":null,"work_id":"61beb5b9-decf-4186-8f23-feb07f654e1b","year":2014},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.424756Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:356cfaaba14a48c8f9bbb577a36d212983853f5ccfa5fde2987b565a6d15206f","observation_id":"7aef3941-e08d-47c2-aa7c-1da82381b31b","resolution":{"observed_at":"2026-08-08T01:07:16.079223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.11215","last_updated":"2023-04-15T22:24:53Z","snapshot_observed_at":"2026-07-06T13:55:19.848757Z","submitted_at":"2022-09-22T17:55:01Z","title":"Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.11215","snapshot_observed_at":"2026-08-08T01:07:12.475484Z","title":"Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.475484Z"},"links":{"cited_paper":"/paper/2209.11215","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:f45e0f4a55b9679fb27e011d62a1c8f59fabd808fe674ac076a946d80939a243","observation_id":"b0815330-f90f-4575-85c1-22442a96095a","resolution":{"observed_at":"2026-08-08T01:07:12.475484Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-08T01:07:12.504753Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.504753Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:a3b650e63b647e8bd2fb82aba2981b3a98615ee956126260e6129ddbdba035f7","observation_id":"e2b44cc8-b3b3-4a69-8f19-f2297294924a","resolution":{"observed_at":"2026-08-08T01:07:12.504753Z","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":"2026-08-08T01:07:15.883794Z","title":"Return of unconditional generation: A self- supervised representation generation method,","venue":null,"work_id":"88024037-e4e6-4187-8f0a-cf2b6f136b3e","year":2024},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.555109Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:beabcb150237cd4fbf2e2e5df9da5f8a43c8bf3ab83fd35430f1b31811442e80","observation_id":"1d3a38bd-8e8c-4fcc-9c24-4ee085baa1fc","resolution":{"observed_at":"2026-08-08T01:07:15.934755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:15.735761Z","title":"Momentum contrast for unsupervised visual representation learning,","venue":null,"work_id":"81c3e155-b056-4226-aff8-280a7b9bde0c","year":2020},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.604754Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:1dbe99319a5737cef74187e0ac97d984678e6b221ceef5f1a4e87414beb15728","observation_id":"65f2cd6f-3a54-42bc-827e-bc94ecdfe500","resolution":{"observed_at":"2026-08-08T01:07:15.765775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04297","last_updated":"2020-03-09T17:56:49Z","snapshot_observed_at":"2026-07-06T09:03:25.467987Z","submitted_at":"2020-03-09T17:56:49Z","title":"Improved Baselines with Momentum Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04297","snapshot_observed_at":"2026-08-08T01:07:12.658352Z","title":"Improved baselines with mo- mentum contrastive learning,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.658352Z"},"links":{"cited_paper":"/paper/2003.04297","citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:f50d85d87f6c57b6120e996f5986ac263abf9763fab66acc203dc7b97bf55b88","observation_id":"43dcd4b5-e794-44e7-b260-a4fde22e7df3","resolution":{"observed_at":"2026-08-08T01:07:12.658352Z","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":"2026-08-08T01:07:15.552395Z","title":"Rethinking the inception architecture for computer vision,","venue":null,"work_id":"53b0114c-292b-4b3a-8cd5-07f8067a6464","year":2016},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.694758Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:55991a784a902ceab2777672a0bb7b8ddd319ab0c79a2a92e6c7765037f3d46f","observation_id":"30ffb1e3-d539-40b8-a591-e5559fa428f4","resolution":{"observed_at":"2026-08-08T01:07:15.604752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-08T01:07:15.404846Z","title":"Improved denoising diffusion probabilis- tic models,","venue":null,"work_id":"f948dc95-10d0-4bc3-a4b7-cb31bf2b6e9d","year":2021},"citing_paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-08T01:07:12.734749Z"},"links":{"citing_paper":"/paper/2608.03082"},"observation_digest":"sha256:774477aba8f76a35e700998a2716eb49a441fe9bc3d4e2e374c9cc1bc3ca5547","observation_id":"b32ea848-d074-4bd9-9950-2ff780e351d8","resolution":{"observed_at":"2026-08-08T01:07:15.455042Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.03082","last_updated":"2026-08-04T03:51:15Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T15:16:52.081280Z","submitted_at":"2026-08-04T03:51:15Z","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers"},"reference_resolution":{"displayed":90,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":63,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":90},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 90 of 90 outbound references and 0 inbound Pith citation observations for arXiv:2608.03082."}