{"as_of":"2026-08-23T11:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb697d76c56b5ad86def55aff25bc9419da95487250540e38f69dce402d8789a","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T01:25:20.669732Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T22:05:03.106403Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T15:38:33.091132Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2605.15193","last_updated":"2026-05-14T17:59:37Z","snapshot_observed_at":"2026-08-15T12:57:52.080059Z","submitted_at":"2026-05-14T17:59:37Z","title":"Aligning Latent Geometry for Spherical Flow Matching in Image Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-30T20:34:54.023368Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2605.15193"},"observation_digest":"sha256:535ee0b37891c562c371e5797b5914413000ae15f620512c7f1b8db862b1e52e","observation_id":"0e727666-8cc9-48e4-aa3a-65241a5f8d23","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2605.21981","last_updated":"2026-05-21T04:21:43Z","snapshot_observed_at":"2026-08-18T09:55:48.302854Z","submitted_at":"2026-05-21T04:21:43Z","title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-22T07:50:29.461854Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2605.21981"},"observation_digest":"sha256:8d234005f15126f8ba7999268d739fd52c8182e3793e08241b7993ec0b41271e","observation_id":"13d7dae4-76bf-4b83-badd-41cdbafc3715","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2605.23028","last_updated":"2026-05-21T20:51:00Z","snapshot_observed_at":"2026-08-19T05:41:35.053678Z","submitted_at":"2026-05-21T20:51:00Z","title":"RADAR: Relative Angular Divergence Across Representations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-25T05:39:39.765999Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2605.23028"},"observation_digest":"sha256:bda0f3a6ca191d8c5faf21347addc8f524e7dd1cde87ef5ba354a96f4b2ce3a4","observation_id":"01986bf7-1538-4c38-9d6c-09f08596eb7c","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2605.26230","last_updated":"2026-05-25T18:01:05Z","snapshot_observed_at":"2026-08-15T16:53:28.323305Z","submitted_at":"2026-05-25T18:01:05Z","title":"Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-29T23:08:52.333329Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2605.26230"},"observation_digest":"sha256:8e831c4338485c3307cf70ef94cc9e1a9d2e6cdf69ffaf05f7f6340eebce5233","observation_id":"c629e20b-65d6-4f6f-98b7-687a8b94dcb9","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2606.00094","last_updated":"2026-07-01T12:56:35Z","snapshot_observed_at":"2026-07-06T23:40:51.363776Z","submitted_at":"2026-05-25T08:43:14Z","title":"Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-29T22:44:39.440271Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2606.00094"},"observation_digest":"sha256:08ab5f8b65f5c7aad2aa80a88dbf34cae6f25d0b3eb5c645c11814d771e3c35a","observation_id":"baa6197c-38c9-4c47-a7f3-f5b2268596a4","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2606.00094","last_updated":"2026-07-01T12:56:35Z","snapshot_observed_at":"2026-07-06T23:40:51.363776Z","submitted_at":"2026-05-25T08:43:14Z","title":"Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-02T23:11:14.733439Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2606.00094"},"observation_digest":"sha256:aa4564ba9f169bfead4f4544d5f7fe07dd1fbaa97ce6e921208dfbcb2585177f","observation_id":"fa13c96b-2a64-4fe7-932c-01fabdcbf9f5","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2606.07036","last_updated":"2026-06-05T08:26:44Z","snapshot_observed_at":"2026-08-03T17:33:35.170027Z","submitted_at":"2026-06-05T08:26:44Z","title":"STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T22:38:58.456728Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2606.07036"},"observation_digest":"sha256:dd1abd54a0d11cc0b68bd1cd0cbae62a606f59fca7a19046fa52a1b41521b020","observation_id":"05f948e6-456a-4b1f-8e7d-1a416b52507b","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":"2602.10099","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-07-07T03:17:18.364333Z","title":"arXiv preprint arXiv:2602.10099 (2026)","venue":null,"work_id":"83f9e7b1-8f01-4420-b583-db376125e216","year":2026},"citing_paper":{"arxiv_id":"2607.01987","last_updated":"2026-07-02T10:18:02Z","snapshot_observed_at":"2026-08-15T16:18:23.348676Z","submitted_at":"2026-07-02T10:18:02Z","title":"Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-03T15:34:54.954593Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2607.01987"},"observation_digest":"sha256:0a6c5ba097d0a8facb127fef7cbf3b6e6e3a39f58e7cc6d2f2613df03e28122b","observation_id":"0bffc623-12ab-479c-8529-707d76fd3664","resolution":{"observed_at":"2026-07-07T03:17:18.364333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-08-01T22:05:03.106403Z","title":"Learning on the manifold: Unlocking standard diffusion transformers with representation encoders.arXiv preprint arXiv:2602.10099, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15898","last_updated":"2026-07-17T12:12:33Z","snapshot_observed_at":"2026-08-11T13:11:46.722346Z","submitted_at":"2026-07-17T12:12:33Z","title":"Orbis 2: A Hierarchical World Model for Driving","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T22:05:03.106403Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2607.15898"},"observation_digest":"sha256:cea580e82826422024e6c9d69922e9deef6fb87e1a0536218d56fb3a57edc297","observation_id":"b1c7e787-9e28-4427-9497-f7eb3f79c8a0","resolution":{"observed_at":"2026-08-01T22:05:03.106403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.10099","snapshot_observed_at":"2026-08-01T13:27:14.205124Z","title":"arXiv preprint arXiv:2602.10099 (2026) 2, 3, 4, 5","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19120","last_updated":"2026-07-21T14:06:04Z","snapshot_observed_at":"2026-08-18T17:28:49.715104Z","submitted_at":"2026-07-21T14:06:04Z","title":"Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T13:27:14.205124Z"},"links":{"cited_paper":"/paper/2602.10099","citing_paper":"/paper/2607.19120"},"observation_digest":"sha256:cf24d5b8485ea0904cc5d01dbad2e691d6c0575f4e4ba7d94292337a3d2586ea","observation_id":"88c9440e-8d78-49ac-bb48-08962577f69a","resolution":{"observed_at":"2026-08-01T13:27:14.205124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2602.10099/citation-record","integrity":"/paper/2602.10099/integrity","json":"/paper/2602.10099/citation-record.json","paper":"/paper/2602.10099"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.15571","last_updated":"2023-03-09T15:18:40Z","snapshot_observed_at":"2026-08-14T22:23:53.150627Z","submitted_at":"2022-09-30T16:30:31Z","title":"Building Normalizing Flows with Stochastic Interpolants","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15571","snapshot_observed_at":"2026-08-03T01:25:17.458196Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:17.458196Z"},"links":{"cited_paper":"/paper/2209.15571","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:8c93fe3e4c0be132834bfc1d4d9b546e06ccba81ab3b903b5ee66fb86f939b0d","observation_id":"c414567e-6bd5-4d0b-b158-59f04d859ef3","resolution":{"observed_at":"2026-08-03T01:25:17.458196Z","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":"2026-08-18T21:22:33.938641Z","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":"2026-08-03T01:25:17.988811Z","title":"Mdtv2: Masked diffusion transformer is a strong image synthe- sizer.arXiv preprint arXiv:2303.14389,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:17.988811Z"},"links":{"cited_paper":"/paper/2303.14389","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:91128a8407ab29640c96de7968caea10889aad214425ad94fbd785b51ecb5ddb","observation_id":"58183840-cbc9-43e1-9211-a898cf2618d1","resolution":{"observed_at":"2026-08-03T01:25:17.988811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.11972","last_updated":"2023-06-14T03:32:57Z","snapshot_observed_at":"2026-08-16T16:06:32.038168Z","submitted_at":"2022-12-22T18:55:45Z","title":"Scalable Adaptive Computation for Iterative Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.11972","snapshot_observed_at":"2026-08-03T01:25:18.304484Z","title":"Scalable adaptive computation for iterative generation.arXiv preprint arXiv:2212.11972,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.304484Z"},"links":{"cited_paper":"/paper/2212.11972","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:47396a8ac5aa47faf38f370cd1e917c8597ec764f5a388c54511c167092c243e","observation_id":"6b9c539e-fd14-451c-b761-35959c8aebef","resolution":{"observed_at":"2026-08-03T01:25:18.304484Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-03T01:25:18.471858Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.471858Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:2d9f932fd80f15d99731e708f4081d82f6996a2513cc9c2988794f04570a2054","observation_id":"930a2b28-873c-4d75-af8e-f76aed292e40","resolution":{"observed_at":"2026-08-03T01:25:18.471858Z","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":"2026-08-03T01:25:18.844250Z","title":"Repa-e: Unlocking vae for end-to-end tuning with latent diffusion transformers.arXiv preprint arXiv:2504.10483,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.844250Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:39eb099ad8a504f8a6904e6ae313ff816a7b9a9661f2ec98e55461c0d836f25c","observation_id":"7700bd73-61a1-45da-8724-23139655ff59","resolution":{"observed_at":"2026-08-03T01:25:18.844250Z","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":"2026-08-03T01:25:18.948817Z","title":"Flow matching meets biology and life science: a survey.arXiv preprint arXiv:2507.17731,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.948817Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:7855357ecef930eedac2d7f917c3a75706eddb599ff7519452f67f40677c03e4","observation_id":"f4022457-828c-43ca-979b-e36958b2a273","resolution":{"observed_at":"2026-08-03T01:25:18.948817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-03T01:25:19.044725Z","title":"T., Ben-Hamu, H., Nickel, M., and Le, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.044725Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:48c032e7622d2b44f74792ced81fb79b64055cdbc9a3c73597878d48a3839e23","observation_id":"962d1c2c-0165-4a7d-ae2f-22ae7dcc4871","resolution":{"observed_at":"2026-08-03T01:25:19.044725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-03T01:25:19.211343Z","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":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.211343Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:88306cd84be4bbc1cd0100120bfffa0a9200e3ccab03b40dc45e582b686ebc3f","observation_id":"7ddad068-87fb-4570-a681-3ca918980259","resolution":{"observed_at":"2026-08-03T01:25:19.211343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-17T13:03:40.359628Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-03T01:25:19.298369Z","title":"Dinov2: Learning robust visual features without supervision.arXiv preprint arXiv:2304.07193,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.298369Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:2b24054930c29997c5a7182e30626608e372a98898128b65c355cd5e98f4d95b","observation_id":"43c44386-2072-4e4d-919f-13637c9ba042","resolution":{"observed_at":"2026-08-03T01:25:19.298369Z","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":"2026-08-03T01:25:19.376198Z","title":"Semantics lead the way: Harmonizing semantic and texture modeling with asynchronous latent diffusion.arXiv preprint arXiv:2512.04926,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.376198Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:b5c1a3be315e88d39af99934112caba43089562b51a1a381e75d26c5741a4605","observation_id":"c85c86d4-7caf-4f1d-b37d-d48721fe8789","resolution":{"observed_at":"2026-08-03T01:25:19.376198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08894","last_updated":"2021-04-18T16:29:23Z","snapshot_observed_at":"2026-08-19T11:24:30.934275Z","submitted_at":"2021-04-18T16:29:23Z","title":"The Intrinsic Dimension of Images and Its Impact on Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08894","snapshot_observed_at":"2026-08-03T01:25:19.486213Z","title":"The intrinsic dimension of images and its impact on learning.arXiv preprint arXiv:2104.08894,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.486213Z"},"links":{"cited_paper":"/paper/2104.08894","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:15b27e040d1e00b463a66a8144390b248056bc8222a4673de18cc904e28de419","observation_id":"f4f08cea-1ab8-47ce-a24f-041952cfa32d","resolution":{"observed_at":"2026-08-03T01:25:19.486213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-03T01:25:19.654186Z","title":"P., Kumar, A., Er- mon, S., and Poole, B","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.654186Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:3d35cdc00cb364fd2e5a09bd7ab0482e942edede5ece2b151eb6e854af650b1b","observation_id":"63c912a2-0d18-46ff-8ba1-2209d3fe4efb","resolution":{"observed_at":"2026-08-03T01:25:19.654186Z","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":"2026-08-03T01:25:19.809711Z","title":"Represen- tation entanglement for generation: Training diffusion transformers is much easier than you think.arXiv preprint arXiv:2507.01467,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.809711Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:3e761ebe4d5ee630d8e2b2cab2f3730c5ebdc0f5cc4f8c558a277c28ae14848b","observation_id":"dd63506a-1ecf-4069-97fa-70108a5772f9","resolution":{"observed_at":"2026-08-03T01:25:19.809711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05297","last_updated":"2023-10-10T19:01:24Z","snapshot_observed_at":"2026-08-18T18:18:17.500992Z","submitted_at":"2023-10-08T21:55:00Z","title":"Fast protein backbone generation with SE(3) flow matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05297","snapshot_observed_at":"2026-08-03T01:25:19.975899Z","title":"Y ., Gastegger, M., Jim´enez-Luna, J., Lewis, S., Satorras, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.975899Z"},"links":{"cited_paper":"/paper/2310.05297","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:950bab051a9f9f38021057b7287c07ba63b84f1c4db9f8c369db930051a38418","observation_id":"e601d539-2c0d-4786-a7fa-29b5e976a89f","resolution":{"observed_at":"2026-08-03T01:25:19.975899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06940","last_updated":"2025-06-18T04:35:42Z","snapshot_observed_at":"2026-07-06T19:30:26.233621Z","submitted_at":"2024-10-09T14:34:53Z","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.06940","snapshot_observed_at":"2026-08-03T01:25:20.038005Z","title":"Representation alignment for generation: Training diffusion transformers is easier than you think","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.038005Z"},"links":{"cited_paper":"/paper/2410.06940","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:9a38161fd3c7f6445fd23f47db89dd702ee083bf5de1619bb53228f4263c194d","observation_id":"6fc8c8bc-3666-447b-a5b4-0bf62c2af5fe","resolution":{"observed_at":"2026-08-03T01:25:20.038005Z","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":"2026-08-03T01:25:20.162558Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.162558Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:351e1067ae173aee2bbaea9961933b243f2c3a3e4734588e5edc31e5707bacf6","observation_id":"053033eb-5afa-478c-a1b3-5fc4a8dd9a1f","resolution":{"observed_at":"2026-08-03T01:25:20.162558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.11690","last_updated":"2025-10-13T17:51:39Z","snapshot_observed_at":"2026-08-13T23:51:28.874833Z","submitted_at":"2025-10-13T17:51:39Z","title":"Diffusion Transformers with Representation Autoencoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.11690","snapshot_observed_at":"2026-08-03T01:25:20.278991Z","title":"Diffusion trans- formers with representation autoencoders.arXiv preprint arXiv:2510.11690,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.278991Z"},"links":{"cited_paper":"/paper/2510.11690","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:fc61e84927e33dc8f674ed02cd491904878fb1f9546ec23ed7ecef3bdf60bded","observation_id":"489428bc-d619-4cc6-b733-425431578899","resolution":{"observed_at":"2026-08-03T01:25:20.278991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09305","last_updated":"2024-03-05T01:10:18Z","snapshot_observed_at":"2026-08-16T15:23:34.823593Z","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":"2026-08-03T01:25:20.415023Z","title":"Fast training of diffusion models with masked transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.415023Z"},"links":{"cited_paper":"/paper/2306.09305","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:31c7cc30d18cfe3a4239f3fba70062ad4eab148713659177d616d1881adef79a","observation_id":"de8052a5-d3d6-4468-a7ba-8a3cf75730a6","resolution":{"observed_at":"2026-08-03T01:25:20.415023Z","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":"2026-08-03T01:25:20.488954Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.488954Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:34c964262108562d42ef3c3b91518a58ec644a67f526210a49e2eb8a7d4a317e","observation_id":"980aa1fb-c98e-4f79-aaa1-aa3f53ba27a0","resolution":{"observed_at":"2026-08-03T01:25:20.488954Z","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":"2026-08-03T01:25:20.603230Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.603230Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:82769472c8b873be13c6d7f6d227870160a7d89623426dfa92f16ba2242a1257","observation_id":"20927835-6509-4759-899a-a454d5e62652","resolution":{"observed_at":"2026-08-03T01:25:20.603230Z","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":"2026-08-03T01:25:20.666077Z","title":"Standard FM constructs probability paths via linear interpolation in Euclidean space, regressing a velocity field to guide samples from a source distribution to the data","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.666077Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:7fa5c27d4bdd3e822816262ec559a034afe4947e38ffdafae9b1a4948e495834","observation_id":"f3166030-8cae-4a42-8e17-1e7c93511d02","resolution":{"observed_at":"2026-08-03T01:25:20.666077Z","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":"2026-08-03T01:25:20.669732Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:20.669732Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:83f4f3bf2b6888a0403e8a0c7ec22491ad86b7a6cdfcddc52fb19e19f284019a","observation_id":"eb4c80f8-39b5-4109-ac79-b95ecf17e053","resolution":{"observed_at":"2026-08-03T01:25:20.669732Z","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":"2026-08-03T01:25:18.600301Z","title":"9 Kouzelis, T., Karypidis, E., Kakogeorgiou, I., Gidaris, S., and Komodakis, N","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.600301Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:1831e0a93f3884fe365726171ae7a10c93bef362b90625c0e276a8caa31f7e71","observation_id":"739e2641-4995-4230-b847-f52a23c84321","resolution":{"observed_at":"2026-08-03T01:25:18.600301Z","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":"2026-08-03T01:25:19.569478Z","title":"Latent diffusion model without variational autoencoder.arXiv preprint arXiv:2510.15301,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.569478Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:f6640e45532d62f91dd7dc7ecb12a9f9f43722c89449a8ad2f89b8be92cde86d","observation_id":"6185bba6-5d86-4144-a674-ab4700807a58","resolution":{"observed_at":"2026-08-03T01:25:19.569478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19324","last_updated":"2025-03-22T19:42:20Z","snapshot_observed_at":"2026-08-21T23:49:21.530972Z","submitted_at":"2024-10-25T06:20:06Z","title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19324","snapshot_observed_at":"2026-08-03T01:25:18.188399Z","title":"Simpler diffusion (sid2): 1.5 fid on imagenet512 with pixel-space diffusion.arXiv preprint arXiv:2410.19324,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.188399Z"},"links":{"cited_paper":"/paper/2410.19324","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:627d3d0f35e72544fc3c9964b8cae187a0e81829914c92333f2bf2d786dfdd6a","observation_id":"c2bb4f0e-3be0-4f65-8f2e-70ad8a9a946f","resolution":{"observed_at":"2026-08-03T01:25:18.188399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.23268","last_updated":"2025-08-04T02:46:11Z","snapshot_observed_at":"2026-08-16T05:36:31.451201Z","submitted_at":"2025-07-31T06:07:20Z","title":"PixNerd: Pixel Neural Field Diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.23268","snapshot_observed_at":"2026-08-03T01:25:19.705115Z","title":"Pixnerd: Pixel neural field diffusion.arXiv preprint arXiv:2507.23268, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:19.705115Z"},"links":{"cited_paper":"/paper/2507.23268","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:cb28d24d95a49f6eeddaae1aa40a08724fed5d2c2332165e8009757cb74f3f79","observation_id":"eda630be-4b6e-4800-ad88-7fa0895801be","resolution":{"observed_at":"2026-08-03T01:25:19.705115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02391","last_updated":"2024-04-11T16:29:12Z","snapshot_observed_at":"2026-08-18T18:21:15.865456Z","submitted_at":"2023-10-03T19:24:24Z","title":"SE(3)-Stochastic Flow Matching for Protein Backbone Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02391","snapshot_observed_at":"2026-08-03T01:25:17.591097Z","title":"J., Akhound-Sadegh, T., Huguet, G., Fatras, K., Rector-Brooks, J., Liu, C.-H., Nica, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:17.591097Z"},"links":{"cited_paper":"/paper/2310.02391","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:999305f60bcc381e8cf58df014f5f6acd454dfa2e26e47985ebebee48205c60b","observation_id":"b0caa131-570b-445a-89ad-9b7ad40d240f","resolution":{"observed_at":"2026-08-03T01:25:17.591097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.07963","last_updated":"2025-04-10T17:59:56Z","snapshot_observed_at":"2026-08-20T00:31:23.282464Z","submitted_at":"2025-04-10T17:59:56Z","title":"PixelFlow: Pixel-Space Generative Models with Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.07963","snapshot_observed_at":"2026-08-03T01:25:17.920187Z","title":"Pixelflow: Pixel-space generative models with flow.arXiv preprint arXiv:2504.07963,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:17.920187Z"},"links":{"cited_paper":"/paper/2504.07963","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:e3503808327cc744e9969bf84f45a41f1c59ff870e4d0817057a8cb93cabd0c9","observation_id":"39c7df84-4c10-46fe-a1a4-c25de5e9be75","resolution":{"observed_at":"2026-08-03T01:25:17.920187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.03660","last_updated":"2024-02-26T17:52:00Z","snapshot_observed_at":"2026-08-16T15:57:01.124521Z","submitted_at":"2023-02-07T18:21:24Z","title":"Flow Matching on General Geometries","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.03660","snapshot_observed_at":"2026-08-03T01:25:17.735813Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:17.735813Z"},"links":{"cited_paper":"/paper/2302.03660","citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:6de909b654440563801ff6e1f4797066ed8919cd4c7685d9530d0ee55018f647","observation_id":"02b7d741-2aa1-48d3-8647-843c9bdeb8a1","resolution":{"observed_at":"2026-08-03T01:25:17.735813Z","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":"2026-08-03T01:25:18.724656Z","title":"A., Hu, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-03T01:25:18.724656Z"},"links":{"citing_paper":"/paper/2602.10099"},"observation_digest":"sha256:c80338eaeb55f86e0bc4f60a9f16911f43f6b63e100803cfd5896f0718bb6217","observation_id":"c9f3d890-97e3-4883-9133-d3000e38b020","resolution":{"observed_at":"2026-08-03T01:25:18.724656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.10099","last_updated":"2026-07-03T15:19:24Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T13:12:50.611733Z","submitted_at":"2026-02-10T18:58:04Z","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":30},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 10 inbound Pith citation observations for arXiv:2602.10099."}