{"as_of":"2026-08-18T03:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ee770fb19a964b7477302f5ccc3870ece88b1393f292147c8786c0ce18088c6","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:00:04.717936Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2509.10312/citation-record","integrity":"/paper/2509.10312/integrity","json":"/paper/2509.10312/citation-record.json","paper":"/paper/2509.10312"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-17T12:45:30.627161Z","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":"2026-08-15T16:00:04.556692Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.556692Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:5a39783b3ab512085af9db025811d6c2d6f24739fde37c22251c52c2732e2315","observation_id":"058d41a5-9136-4860-a338-ad554fda30c6","resolution":{"observed_at":"2026-08-15T16:00:04.556692Z","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":"2026-08-15T16:00:04.561208Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.561208Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:0532c303720b1bb7855b514d848f4168d214aa63d07c9928fe54a4c065de7304","observation_id":"d9a97f24-f720-4731-a050-b9618ceb665e","resolution":{"observed_at":"2026-08-15T16:00:04.561208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01125","last_updated":"2024-06-03T09:10:44Z","snapshot_observed_at":"2026-08-16T13:46:50.271264Z","submitted_at":"2024-06-03T09:10:44Z","title":"$\\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01125","snapshot_observed_at":"2026-08-15T16:00:04.565031Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.565031Z"},"links":{"cited_paper":"/paper/2406.01125","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:361d5933ce6ac75d66335eab92c98f57f9ee04c39a71d23921ad1f7add539b7f","observation_id":"d1c2e42c-e277-46a4-ad82-a257e0fc15ce","resolution":{"observed_at":"2026-08-15T16:00:04.565031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.00433","last_updated":"2025-02-01T13:46:02Z","snapshot_observed_at":"2026-08-15T08:08:52.669892Z","submitted_at":"2025-02-01T13:46:02Z","title":"CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.00433","snapshot_observed_at":"2026-08-15T16:00:04.569320Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.569320Z"},"links":{"cited_paper":"/paper/2502.00433","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:71324e5ff182bd6a0edd9053e4c647b40fe92555de66c7f0d7bb44732f33b12c","observation_id":"f47fe44b-6239-4014-9199-31eaa92905b7","resolution":{"observed_at":"2026-08-15T16:00:04.569320Z","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":"2026-08-15T16:00:04.574086Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.574086Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:0fbc70444eee4adb11389c788611a542627ae21a7094d11dfe8a8145b4e75867","observation_id":"9721c0aa-b98a-4976-b87a-0662910e07c7","resolution":{"observed_at":"2026-08-15T16:00:04.574086Z","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":"2026-08-15T16:00:04.577923Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.577923Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:58ebd612b41c2259af1002cac1b950c2b727f42e74e5d560f6f0895804100d72","observation_id":"1afe14a7-8723-47cb-8101-fd021d6ddac6","resolution":{"observed_at":"2026-08-15T16:00:04.577923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10924","last_updated":"2023-09-30T12:05:20Z","snapshot_observed_at":"2026-08-16T15:32:02.053300Z","submitted_at":"2023-05-18T12:38:21Z","title":"Structural Pruning for Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10924","snapshot_observed_at":"2026-08-15T16:00:04.581901Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.581901Z"},"links":{"cited_paper":"/paper/2305.10924","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:f441224f0303bcbeaacb441614fc33f4abd5875f2b7b7f88537e4e9ac5ade617","observation_id":"1873f300-ea1c-424c-a9f1-c266874b7c0d","resolution":{"observed_at":"2026-08-15T16:00:04.581901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08718","last_updated":"2022-03-23T19:47:21Z","snapshot_observed_at":"2026-07-06T11:01:02.207193Z","submitted_at":"2021-04-18T05:00:29Z","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08718","snapshot_observed_at":"2026-08-15T16:00:04.586808Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.586808Z"},"links":{"cited_paper":"/paper/2104.08718","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:556f793971d3c221bc5c2f3cc1e08eac4246a3a89fdefe52d15b2e641b18647a","observation_id":"fc8d4ee0-54cc-43ec-abab-67b36e9718d6","resolution":{"observed_at":"2026-08-15T16:00:04.586808Z","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":"2026-08-15T16:00:05.159363Z","title":null,"venue":null,"work_id":"ae0935ab-2ee4-4053-8444-0a6731b78f75","year":2017},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.590298Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:7ffbe4cca27e37ab61c2cfb4593cc039bcb063d2f7ff9c6c594258ef8987d2aa","observation_id":"7d5a6839-89dc-4e48-a60d-ef2bcd68c7dd","resolution":{"observed_at":"2026-08-15T16:00:05.162838Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:00:04.594070Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.594070Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:f349e02196ee7c82f732ff09f9cbf1d672e9ebac7e7b8ca39581a8749c73f0b2","observation_id":"37666179-b508-4330-9544-ae39dce02a7c","resolution":{"observed_at":"2026-08-15T16:00:04.594070Z","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":"2026-08-15T16:00:04.597647Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.597647Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:10e77dcf74331ff1c737dcecd6a9ce221bfac5d6602fee4147204fe8448808d3","observation_id":"f02d1b60-09b2-43f5-9149-ec1d6d2b4b27","resolution":{"observed_at":"2026-08-15T16:00:04.597647Z","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":"2026-08-15T16:00:04.601345Z","title":"2021.OpenCLIP","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.601345Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:82faf084fb31757e6807614f4ddc584f965dbb3d2deca3aa1a1ad91dcbe525cb","observation_id":"1f30e3c6-eff8-4422-aaeb-d056aeefa4f6","resolution":{"observed_at":"2026-08-15T16:00:04.601345Z","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":"2026-08-15T16:00:05.135101Z","title":null,"venue":null,"work_id":"14f29c85-7558-4426-845c-89befa3a2c6c","year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.605067Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:2adf5a6a3c6bfd7184f257251b57634cbd5bdcd464845fa10d043a5050c9dde3","observation_id":"1c1b4a85-90a4-4013-8647-d8e83fc59db1","resolution":{"observed_at":"2026-08-15T16:00:05.138663Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T16:00:05.124608Z","title":null,"venue":null,"work_id":"373f65b6-726d-499b-a8d7-d51027e105ff","year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.608753Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:8a6f4f7f3685a33101076c05978cb47c6114171838e2a3ce70f67bfbe21a65dd","observation_id":"e036a25f-e864-4cc9-ac0e-03f74f338304","resolution":{"observed_at":"2026-08-15T16:00:05.128182Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:00:04.612195Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.612195Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:f0803ca1ac619e4fe16c9711120b2c4c85169860a5f766c6e6cf6b9ed817b8ca","observation_id":"f76de5ed-e0ed-4acc-a0e0-1a6d08de6aa3","resolution":{"observed_at":"2026-08-15T16:00:04.612195Z","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":"2026-08-15T16:00:04.615413Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.615413Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:2b5e7f222b735167fd7047a444d04dbb44904a24fac708a1dec54d589db23877","observation_id":"06957f6e-bc6c-420b-8d2e-428360841337","resolution":{"observed_at":"2026-08-15T16:00:04.615413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08748","last_updated":"2024-05-14T16:33:25Z","snapshot_observed_at":"2026-07-06T18:14:16.386835Z","submitted_at":"2024-05-14T16:33:25Z","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08748","snapshot_observed_at":"2026-08-15T16:00:04.618874Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.618874Z"},"links":{"cited_paper":"/paper/2405.08748","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:25de4da4c616de6f98c517b79f68b9b3d7760b0e355ecd6eecf2ec1e005c7231","observation_id":"f70f34df-e7cb-4993-9ec6-9e54491e60ec","resolution":{"observed_at":"2026-08-15T16:00:04.618874Z","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":"2026-08-15T16:00:04.622768Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.622768Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:25c6ad74c70879cfcded180d9d8e5f511beb5b527ea17da7c12823374d2787bb","observation_id":"cbb6b98f-d91e-4745-b11e-d61beba67fdb","resolution":{"observed_at":"2026-08-15T16:00:04.622768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06923","last_updated":"2025-08-11T14:15:27Z","snapshot_observed_at":"2026-08-16T12:51:40.344654Z","submitted_at":"2025-03-10T05:09:42Z","title":"From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06923","snapshot_observed_at":"2026-08-15T16:00:04.630162Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.630162Z"},"links":{"cited_paper":"/paper/2503.06923","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:ee4d7399767df93bc57de7db2102d03a5789e97f953e88c3be9657e4ef6423c0","observation_id":"a7b34d7c-adb6-4a2d-9ba4-16d2d1f92807","resolution":{"observed_at":"2026-08-15T16:00:04.630162Z","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":"2026-08-15T16:00:04.633599Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.633599Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:b3c2bb9e91efbb371ed55f74c1b6f9812a05c0a219465ed142e1ced4d04d5a64","observation_id":"68ca05bf-ae3e-4b22-8775-2124e809e2af","resolution":{"observed_at":"2026-08-15T16:00:04.633599Z","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":"2026-08-15T16:00:04.637651Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.637651Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:59932bd9321b4d04ae140f857e595555dcfd378adcb705fcb32a26e214067006","observation_id":"4add4b82-6899-4a87-a62a-362625f59115","resolution":{"observed_at":"2026-08-15T16:00:04.637651Z","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":"2026-08-15T16:00:05.082051Z","title":null,"venue":null,"work_id":"f403895e-d1e3-4a99-8985-1289100564f2","year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.644848Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:c0c20a83178967c9a74ea6d0f063714c746a5a9fa6ec4c8964a1ffb4f139d6ab","observation_id":"ff263077-dbd6-4fd6-8281-9fa23b255020","resolution":{"observed_at":"2026-08-15T16:00:05.085939Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:00:04.648530Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.648530Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:ee7528b7e39ecc86ac2c6cb190fbbfbc1a882acf2fc56fcec44424451d33d1d3","observation_id":"e4eabdc7-4873-4a0a-a07d-d87406d38f92","resolution":{"observed_at":"2026-08-15T16:00:04.648530Z","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":"2026-08-15T16:00:04.652009Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.652009Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:08a5fa7f01913b1f57224eec766e4d83065d61044a5effe3ffacbfda195e355b","observation_id":"aa7a89f9-0770-4f68-aa47-5fa9061c7ac3","resolution":{"observed_at":"2026-08-15T16:00:04.652009Z","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":"2026-08-15T16:00:04.655411Z","title":"Bernstein, Alexander C","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.655411Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:dff243b516c7f1c79ff45b1f1b5b22c7b0cdf778f0491e0c718cf1011cec8d58","observation_id":"9ddabb62-4160-4187-843b-f787eb53a9c2","resolution":{"observed_at":"2026-08-15T16:00:04.655411Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00946","last_updated":"2025-01-01T20:16:27Z","snapshot_observed_at":"2026-08-16T01:02:32.426073Z","submitted_at":"2025-01-01T20:16:27Z","title":"Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00946","snapshot_observed_at":"2026-08-15T16:00:04.659371Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.659371Z"},"links":{"cited_paper":"/paper/2501.00946","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:03aae607d6a6f0b59c3c7817d090f0af0543b263dca61221ee55d137ba2e74d5","observation_id":"af6fca12-d057-4f41-af2a-8fc8583e679a","resolution":{"observed_at":"2026-08-15T16:00:04.659371Z","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":"2026-08-15T16:00:04.662949Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.662949Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:03f8e9f5d13bcb4910c84ed2215f3729ae00379bbdfdea659702aea7684571d7","observation_id":"3e7324a8-09fd-42d4-b082-287df92cf66c","resolution":{"observed_at":"2026-08-15T16:00:04.662949Z","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":"2026-08-15T16:00:04.666480Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.666480Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:c8e523648d041165c84ec72db36d9fd5d6d35e43d4a8dfadb4b8824312eeb191","observation_id":"455fba30-e9f7-4a78-bc3a-edebb529084a","resolution":{"observed_at":"2026-08-15T16:00:04.666480Z","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":"2026-08-15T16:00:05.044095Z","title":null,"venue":null,"work_id":"bf0d7429-e307-4f8f-91d4-0b153d4bcd03","year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.673931Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:390c0eb9debb8c75747e572872c06a54a883e0a1c3d22ceb20ef6aa2d592efba","observation_id":"b19fcbf8-8699-44f1-b27b-23cc6fb56ccd","resolution":{"observed_at":"2026-08-15T16:00:05.047918Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-15T16:00:04.677056Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.677056Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:1ada99381187d44ed46d7e294d6eb3fa19879c93ea43730fb3eabce5e4dbe051","observation_id":"a0f8df3a-d811-4154-8086-ddd26f2f12fd","resolution":{"observed_at":"2026-08-15T16:00:04.677056Z","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":"2026-08-15T16:00:04.680428Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.680428Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:80ecda63aa23599e393eefb9bd9d1761e48093ae68bc7ba3f5edf165b2a49bf4","observation_id":"0bfa11a1-00c8-4f6d-9e28-d20aad5af4b0","resolution":{"observed_at":"2026-08-15T16:00:04.680428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02265","last_updated":"2024-11-06T09:15:27Z","snapshot_observed_at":"2026-08-16T13:03:06.425740Z","submitted_at":"2024-11-04T16:56:26Z","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.02265","snapshot_observed_at":"2026-08-15T16:00:04.683744Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.683744Z"},"links":{"cited_paper":"/paper/2411.02265","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:3c0951d39218e20261c89be58aecd5ac4f52555f8d63e0026c457df3ee5a5d30","observation_id":"5396dafc-31f9-4c07-ad12-a08a9989cc6b","resolution":{"observed_at":"2026-08-15T16:00:04.683744Z","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":"2026-08-15T16:00:04.687926Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.687926Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:6f49c1d2ac1db3e01481dffc5ab505631245fb6dbefe8ad5d1167d1a2cad2797","observation_id":"6dda3abf-ef0b-4ffc-84b3-0c6737881bf8","resolution":{"observed_at":"2026-08-15T16:00:04.687926Z","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":"2026-08-15T16:00:04.691368Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.691368Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:ba7f0bdf0e2a73a748edba8ecaef68723bab018a1a59d087356505fee4ab30b6","observation_id":"2be9a560-3b9b-47d1-843a-8b6107e3a7fc","resolution":{"observed_at":"2026-08-15T16:00:04.691368Z","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":"2026-08-15T16:00:04.694816Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.694816Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:06f2f7eabc886b6bc2f5c0161565994c4587e1f53d11a22fe029fb9d0bc4dd35","observation_id":"629338d1-ce8b-40f1-b966-826b00429170","resolution":{"observed_at":"2026-08-15T16:00:04.694816Z","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":"2026-08-15T16:00:05.002835Z","title":null,"venue":null,"work_id":"495ceb3d-bf6e-42fc-afe4-662cfc8e04c5","year":2025},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.698262Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:c19840b91ad5cfd1238bae894f71d599a60227a6da296cc6c9d6a21be64890da","observation_id":"fbcc28c8-016d-43a5-8bf9-4f455a24f936","resolution":{"observed_at":"2026-08-15T16:00:05.006962Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00375","last_updated":"2024-12-31T09:56:40Z","snapshot_observed_at":"2026-08-12T14:26:38.597825Z","submitted_at":"2024-12-31T09:56:40Z","title":"Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00375","snapshot_observed_at":"2026-08-15T16:00:04.701651Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.701651Z"},"links":{"cited_paper":"/paper/2501.00375","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:7d1601a0a3e08ac40fa3b6835506b9193188ce0e4faf00aea0eaef1897430ec1","observation_id":"6db59fbc-f665-4589-988b-355f70187b19","resolution":{"observed_at":"2026-08-15T16:00:04.701651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12588","last_updated":"2025-02-27T07:00:30Z","snapshot_observed_at":"2026-08-16T13:24:31.259921Z","submitted_at":"2024-08-22T17:54:21Z","title":"Real-Time Video Generation with Pyramid Attention Broadcast","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12588","snapshot_observed_at":"2026-08-15T16:00:04.705327Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.705327Z"},"links":{"cited_paper":"/paper/2408.12588","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:adca3e89b16446a197bc711c216e27490b7a4dc3536a385c36af1ee8c1df6fd7","observation_id":"8b8c803f-53b2-4c72-bd44-bc0f096d354a","resolution":{"observed_at":"2026-08-15T16:00:04.705327Z","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":"2026-08-15T16:00:04.988854Z","title":null,"venue":null,"work_id":"0f9080ab-4961-4e90-b350-7feb9a0ce2a6","year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.709659Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:a25d1ebaeac3b088c547bec0f456af4cbd999ff5acd4b80b2d432e98d26956d8","observation_id":"5cb23c91-c754-4d49-b19e-948b6ad917d5","resolution":{"observed_at":"2026-08-15T16:00:04.993770Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05317","last_updated":"2025-02-19T10:39:58Z","snapshot_observed_at":"2026-08-16T13:12:23.456074Z","submitted_at":"2024-10-05T03:47:06Z","title":"Accelerating Diffusion Transformers with Token-wise Feature Caching","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05317","snapshot_observed_at":"2026-08-15T16:00:04.713445Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.713445Z"},"links":{"cited_paper":"/paper/2410.05317","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:987e6f2f11c57d167ae15777fc57d918f25d04052c5b251dd6fcc304b4fe50dc","observation_id":"a255dfb8-29c5-4c75-adf1-4a74fdb61f9f","resolution":{"observed_at":"2026-08-15T16:00:04.713445Z","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":"2026-08-15T16:00:04.717936Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.717936Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:01bbc25e81b1725dc82f8345e42b32ffd4c8c4c062d33d0f3b7075d7ea1a9762","observation_id":"5da77cae-40ae-47d9-a0a5-5ee01009ea30","resolution":{"observed_at":"2026-08-15T16:00:04.717936Z","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":"2026-08-15T16:00:04.641358Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.641358Z"},"links":{"citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:609d1f09a2dffcef6ccd192f1652766c49b952b4f733ac4088df9e383d18165a","observation_id":"25338665-1a4d-4fd4-a75b-91e4e26ca5df","resolution":{"observed_at":"2026-08-15T16:00:04.641358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01425","last_updated":"2024-07-01T16:14:37Z","snapshot_observed_at":"2026-08-16T13:38:03.111467Z","submitted_at":"2024-07-01T16:14:37Z","title":"FORA: Fast-Forward Caching in Diffusion Transformer Acceleration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01425","snapshot_observed_at":"2026-08-15T16:00:04.670136Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T16:00:04.670136Z"},"links":{"cited_paper":"/paper/2407.01425","citing_paper":"/paper/2509.10312"},"observation_digest":"sha256:7602d610eda9438c3d44af4e9f306b72bd2fb5aa8490141a6e3f08cc8e4f2764","observation_id":"c5e210b5-9653-4a58-a457-f1fba6231e80","resolution":{"observed_at":"2026-08-15T16:00:04.670136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.10312","last_updated":"2025-09-12T14:53:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T01:17:58.579534Z","submitted_at":"2025-09-12T14:53:45Z","title":"Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":43},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2509.10312."}