{"as_of":"2026-08-22T18:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae304b5eab2432a9c0873d11e5cbc1e3497565524bc3d69fa738ecb112e01391","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:31:13.109226Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:40:50.026085Z","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":"2026-07-04T13:39:50.654553Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"cited_work":{"arxiv_id":"2508.16211","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.16211","snapshot_observed_at":"2026-07-04T13:39:50.654553Z","title":"Forecast then calibrate: Feature caching as ode for efficient diffusion transformers","venue":null,"work_id":"14af804f-b4df-4a25-8341-b0622255dd40","year":2025},"citing_paper":{"arxiv_id":"2604.15911","last_updated":"2026-04-17T10:11:39Z","snapshot_observed_at":"2026-08-20T15:11:48.430991Z","submitted_at":"2026-04-17T10:11:39Z","title":"Efficient Video Diffusion Models: Advancements and Challenges","version":1},"reference_index":199,"source":"pdf_text","source_observed_at":"2026-05-10T08:28:29.706249Z"},"links":{"cited_paper":"/paper/2508.16211","citing_paper":"/paper/2604.15911"},"observation_digest":"sha256:9bea850a622934de04666ba4014614b040727dcd7ccb235648a14110b4892c5d","observation_id":"9e623894-7925-418d-a1af-7d91d53b22f5","resolution":{"observed_at":"2026-05-10T09:03:26.095810Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"cited_work":{"arxiv_id":"2508.16211","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.16211","snapshot_observed_at":"2026-07-04T13:39:50.654553Z","title":"Forecast then calibrate: Feature caching as ode for efficient diffusion transformers","venue":null,"work_id":"14af804f-b4df-4a25-8341-b0622255dd40","year":2025},"citing_paper":{"arxiv_id":"2605.02152","last_updated":"2026-05-04T02:30:24Z","snapshot_observed_at":"2026-08-15T15:34:44.619582Z","submitted_at":"2026-05-04T02:30:24Z","title":"SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-09T16:48:58.121156Z"},"links":{"cited_paper":"/paper/2508.16211","citing_paper":"/paper/2605.02152"},"observation_digest":"sha256:1767c2e764582822c7f9007637d6a987c17cecaf6b97eb36e667b21bd1359230","observation_id":"d5e6ea67-d0c6-41eb-9d76-78f1c9d25720","resolution":{"observed_at":"2026-05-11T16:26:09.598029Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"cited_work":{"arxiv_id":"2508.16211","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.16211","snapshot_observed_at":"2026-07-04T13:39:50.654553Z","title":"Forecast then calibrate: Feature caching as ode for efficient diffusion transformers","venue":null,"work_id":"14af804f-b4df-4a25-8341-b0622255dd40","year":2025},"citing_paper":{"arxiv_id":"2605.21042","last_updated":"2026-05-20T11:24:02Z","snapshot_observed_at":"2026-08-13T20:17:26.551686Z","submitted_at":"2026-05-20T11:24:02Z","title":"Dynamic Video Generation: Shaping Video Generation Across Time and Space","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-21T05:42:41.925474Z"},"links":{"cited_paper":"/paper/2508.16211","citing_paper":"/paper/2605.21042"},"observation_digest":"sha256:74781b4540736dfcc377fcc2cb16fd1cbe94a3191f1861f1eedc550c6b872d67","observation_id":"2e028472-761e-40a9-a321-0fda207401ef","resolution":{"observed_at":"2026-05-21T05:43:58.855234Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"cited_work":{"arxiv_id":"2508.16211","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.16211","snapshot_observed_at":"2026-07-04T13:39:50.654553Z","title":"Forecast then calibrate: Feature caching as ode for efficient diffusion transformers","venue":null,"work_id":"14af804f-b4df-4a25-8341-b0622255dd40","year":2025},"citing_paper":{"arxiv_id":"2606.26769","last_updated":"2026-06-25T08:54:17Z","snapshot_observed_at":"2026-08-13T13:44:57.594169Z","submitted_at":"2026-06-25T08:54:17Z","title":"ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-06-26T05:03:22.182138Z"},"links":{"cited_paper":"/paper/2508.16211","citing_paper":"/paper/2606.26769"},"observation_digest":"sha256:a42f6804024a0dfc5b53350619683895b743ff34a792403b93b1d260d0414da4","observation_id":"5bdaee97-b2bf-4bbd-9844-a2c85e52791b","resolution":{"observed_at":"2026-07-04T13:39:50.656817Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.16211","snapshot_observed_at":"2026-08-11T00:40:50.026085Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.07572","last_updated":"2026-08-04T11:24:53Z","snapshot_observed_at":"2026-08-14T01:58:25.699315Z","submitted_at":"2026-08-04T11:24:53Z","title":"BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T00:40:50.026085Z"},"links":{"cited_paper":"/paper/2508.16211","citing_paper":"/paper/2608.07572"},"observation_digest":"sha256:f00bdc9978290c17a320cc0c171f69d321cb3205c7d7591ba0baf5daf919d68a","observation_id":"d0054720-05ea-41ad-b5d5-0a9432a0c937","resolution":{"observed_at":"2026-08-11T00:40:50.026085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2508.16211/citation-record","integrity":"/paper/2508.16211/integrity","json":"/paper/2508.16211/citation-record.json","paper":"/paper/2508.16211"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.17604","last_updated":"2023-03-30T17:59:58Z","snapshot_observed_at":"2026-08-17T22:43:12.250466Z","submitted_at":"2023-03-30T17:59:58Z","title":"Token Merging for Fast Stable Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17604","snapshot_observed_at":"2026-08-05T17:31:13.006011Z","title":"arXiv preprint arXiv:2303.17604","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.006011Z"},"links":{"cited_paper":"/paper/2303.17604","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:35b9fbe47c03915b4d10097b2cd9c011931d6de1dca464628f4d05aa685a3fb9","observation_id":"6716ca51-e5fe-4812-8cd8-565942f36ea9","resolution":{"observed_at":"2026-08-05T17:31:13.006011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00426","last_updated":"2023-12-29T16:42:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-30T16:18:00Z","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00426","snapshot_observed_at":"2026-08-05T17:31:13.009858Z","title":"arXiv preprint arXiv:2310.00426","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.009858Z"},"links":{"cited_paper":"/paper/2310.00426","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:3e9b46b8721bbbbd5d0c24511a73baf1e045f355260a3f6a3129cf584b4c59df","observation_id":"a114b720-4bdf-4469-b1ab-c5eb94a14c41","resolution":{"observed_at":"2026-08-05T17:31:13.009858Z","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":"2026-08-19T22:00:25.980434Z","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":"2026-08-05T17:31:13.021492Z","title":"arXiv preprint arXiv:2305.10924","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.021492Z"},"links":{"cited_paper":"/paper/2305.10924","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:de39e24e6fefa0050a72263fd39889d51926e4ed728d3d3bfbbcf3635b52e86c","observation_id":"d14cb7c2-7df6-4ec0-bf88-a154b6b794d9","resolution":{"observed_at":"2026-08-05T17:31:13.021492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17982","last_updated":"2023-11-29T18:39:01Z","snapshot_observed_at":"2026-08-17T16:46:45.172471Z","submitted_at":"2023-11-29T18:39:01Z","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17982","snapshot_observed_at":"2026-08-05T17:31:13.039875Z","title":"arXiv preprint arXiv:2311.17982","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.039875Z"},"links":{"cited_paper":"/paper/2311.17982","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:199da58d8167872ea32fa6ec5189385f421664637b4f21c7d7060823cc7061eb","observation_id":"ba92620b-78f7-4168-89e8-e4ed17d4dff0","resolution":{"observed_at":"2026-08-05T17:31:13.039875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.11211","last_updated":"2025-01-20T01:03:50Z","snapshot_observed_at":"2026-08-17T13:44:00.120667Z","submitted_at":"2025-01-20T01:03:50Z","title":"Ditto: Accelerating Diffusion Model via Temporal Value Similarity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.11211","snapshot_observed_at":"2026-08-05T17:31:13.043232Z","title":"arXiv preprint arXiv:2501.11211","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.043232Z"},"links":{"cited_paper":"/paper/2501.11211","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:6575c39451106442e6e37d61ae8315d4b04ad6c619093f66aaf13804b8642e18","observation_id":"0d67f577-97a3-4981-b603-7a593a19b6d7","resolution":{"observed_at":"2026-08-05T17:31:13.043232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.04304","last_updated":"2023-06-08T09:21:05Z","snapshot_observed_at":"2026-08-20T20:07:52.811169Z","submitted_at":"2023-02-08T19:38:59Z","title":"Q-Diffusion: Quantizing Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04304","snapshot_observed_at":"2026-08-05T17:31:13.046427Z","title":"arXiv preprint arXiv:2302.04304","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.046427Z"},"links":{"cited_paper":"/paper/2302.04304","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:32b816b499408d52655bb40a0b2328311224cc3e81405c0ca4a010d0440052c8","observation_id":"d95f1001-e8a8-4adc-b50f-b96ef7d1a462","resolution":{"observed_at":"2026-08-05T17:31:13.046427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.06923","last_updated":"2024-06-10T10:18:08Z","snapshot_observed_at":"2026-08-17T04:27:06.815726Z","submitted_at":"2024-03-11T17:11:31Z","title":"A unified diagrammatic approach to quantum transport in few-level junctions for bosonic and fermionic reservoirs: Application to the quantum Rabi model","version":3},"cited_work":{"arxiv_id":"2403.06923","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.06923","snapshot_observed_at":"2026-08-05T17:31:13.330661Z","title":"A unified diagrammatic approach to quantum transport in few-level junctions for bosonic and fermionic reservoirs: Application to the quantum Rabi model","venue":"quant-ph","work_id":"8a725f59-89ff-4507-a25d-9224b7ee416a","year":2024},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.049780Z"},"links":{"cited_paper":"/paper/2403.06923","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:12ee0937f7be6149f3dbbe072225e7dae1d5b8bef3d60a4f1ff8f8c69feb2a84","observation_id":"e3d65d8d-74f0-46cd-8d66-1b5739cfc5e4","resolution":{"observed_at":"2026-08-05T17:31:13.334199Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00927","last_updated":"2022-10-13T12:04:36Z","snapshot_observed_at":"2026-08-20T12:54:48.114323Z","submitted_at":"2022-06-02T08:43:16Z","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00927","snapshot_observed_at":"2026-08-05T17:31:13.056183Z","title":"arXiv preprint arXiv:2206.00927","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.056183Z"},"links":{"cited_paper":"/paper/2206.00927","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:d55a1e9e0f574e61c5f966a9f6f74ea2f378593ba0bd56acf47532316d287988","observation_id":"27756745-3a06-43e3-9888-b3bd5afb98b6","resolution":{"observed_at":"2026-08-05T17:31:13.056183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00858","last_updated":"2023-12-07T17:24:18Z","snapshot_observed_at":"2026-08-21T13:20:13.035247Z","submitted_at":"2023-12-01T17:01:06Z","title":"DeepCache: Accelerating Diffusion Models for Free","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00858","snapshot_observed_at":"2026-08-05T17:31:13.059315Z","title":"arXiv preprint arXiv:2312.00858","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.059315Z"},"links":{"cited_paper":"/paper/2312.00858","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:9c5fcf38fbaa57f19307839ff27b4f42e34f261fbfa12df4fe3b3cd6a7c53b0c","observation_id":"bf12e93d-4608-4944-9a35-f83ce48aebea","resolution":{"observed_at":"2026-08-05T17:31:13.059315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09748","last_updated":"2023-03-02T09:06:55Z","snapshot_observed_at":"2026-08-17T19:22:44.145403Z","submitted_at":"2022-12-19T18:59:58Z","title":"Scalable Diffusion Models with Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09748","snapshot_observed_at":"2026-08-05T17:31:13.062385Z","title":"arXiv preprint arXiv:2212.09748","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.062385Z"},"links":{"cited_paper":"/paper/2212.09748","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:c901f16db513eb4a4b8cd3feb7efae13b947da23e5aca7856af533cb6cfefb09","observation_id":"3df1577b-477f-412f-811b-937959185f61","resolution":{"observed_at":"2026-08-05T17:31:13.062385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.11487","last_updated":"2022-05-23T17:42:53Z","snapshot_observed_at":"2026-08-17T05:51:02.087480Z","submitted_at":"2022-05-23T17:42:53Z","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.11487","snapshot_observed_at":"2026-08-05T17:31:13.068649Z","title":"arXiv preprint arXiv:2205.11487","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.068649Z"},"links":{"cited_paper":"/paper/2205.11487","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:0768f57850af6c04c5a5c81c941a094f6f6bbd3c72181ae53084f391df4a1bf7","observation_id":"6e140743-5c09-4f27-b7f8-4770c6e513e1","resolution":{"observed_at":"2026-08-05T17:31:13.068649Z","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":"2026-08-05T17:31:13.071944Z","title":"arXiv preprint arXiv:2407.01425","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.071944Z"},"links":{"cited_paper":"/paper/2407.01425","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:ba23d0b3332c6c385fc33587ba727a35cc6161e4e2664f03369300610dbbd636","observation_id":"48ee7a54-07d5-4221-a77c-79b6bf54124e","resolution":{"observed_at":"2026-08-05T17:31:13.071944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.03585","last_updated":"2015-11-18T21:50:51Z","snapshot_observed_at":"2026-08-21T03:32:27.484213Z","submitted_at":"2015-03-12T04:51:37Z","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.03585","snapshot_observed_at":"2026-08-05T17:31:13.074938Z","title":"arXiv preprint arXiv:1503.03585","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.074938Z"},"links":{"cited_paper":"/paper/1503.03585","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:35eba9f7d3e9a2f0ca22f98dbf3d345bd8735384d09b028e9bbb37566cd4b109","observation_id":"a142503b-79ac-4d0e-8818-a0402cf1f143","resolution":{"observed_at":"2026-08-05T17:31:13.074938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-05T17:31:13.078322Z","title":"arXiv preprint arXiv:2010.02502","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.078322Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:be9c26c05a100822b362ca7d28ff7cd243af2ba8f7fb46f51adec2c4be75845f","observation_id":"0f6e0a47-031a-4c45-8503-0ad4d6c8e793","resolution":{"observed_at":"2026-08-05T17:31:13.078322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.01469","last_updated":"2023-05-31T06:17:10Z","snapshot_observed_at":"2026-08-15T07:00:23.337991Z","submitted_at":"2023-03-02T18:30:16Z","title":"Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.01469","snapshot_observed_at":"2026-08-05T17:31:13.081347Z","title":"arXiv preprint arXiv:2303.01469","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.081347Z"},"links":{"cited_paper":"/paper/2303.01469","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:7a53fd920e2844356114a1777edd6ffd1f138f2ff5b5e4345e5d73ea07e1bb59","observation_id":"db9a10d9-7fd0-42e1-8bda-b93d483f057f","resolution":{"observed_at":"2026-08-05T17:31:13.081347Z","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":"2026-08-05T17:31:13.084588Z","title":"arXiv preprint arXiv:2411.02265","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.084588Z"},"links":{"cited_paper":"/paper/2411.02265","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:25884c60d05c791dfac3c334624c2ffd9cc6a4034493ea9662653643b744485a","observation_id":"b81d3c45-33be-48b0-bd2e-52187fc54264","resolution":{"observed_at":"2026-08-05T17:31:13.084588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03209","last_updated":"2024-01-12T09:26:45Z","snapshot_observed_at":"2026-08-16T14:37:18.669386Z","submitted_at":"2023-12-06T00:51:38Z","title":"Cache Me if You Can: Accelerating Diffusion Models through Block Caching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03209","snapshot_observed_at":"2026-08-05T17:31:13.087612Z","title":"arXiv preprint arXiv:2312.03209","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.087612Z"},"links":{"cited_paper":"/paper/2312.03209","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:750274039e6577fae7e231c8730cf8681432e95117db0b174882680539f03e86","observation_id":"394ca040-c0c2-42be-a3ce-75b95f07a77e","resolution":{"observed_at":"2026-08-05T17:31:13.087612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05977","last_updated":"2023-12-28T14:13:35Z","snapshot_observed_at":"2026-08-20T07:28:19.493559Z","submitted_at":"2023-04-12T16:58:13Z","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05977","snapshot_observed_at":"2026-08-05T17:31:13.090698Z","title":"Yang, Z.; Jiang, H.; Hong, W.; Teng, J.; Zheng, W.; Dong, Y .; Ding, M.; and Tang, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.090698Z"},"links":{"cited_paper":"/paper/2304.05977","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:a9fca3365a66a8899d46aa046e8dce4e49a328039c09c9ffed2208099abb606f","observation_id":"daa0ffd2-6861-4203-9c19-0f6db8c57089","resolution":{"observed_at":"2026-08-05T17:31:13.090698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.04312","last_updated":"2024-05-08T07:17:12Z","snapshot_observed_at":"2026-08-16T13:54:41.966029Z","submitted_at":"2024-05-07T13:35:58Z","title":"Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer","version":2},"cited_work":{"arxiv_id":"2405.04312","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.04312","snapshot_observed_at":"2026-08-05T17:31:13.203333Z","title":"Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer","venue":"cs.CV","work_id":"94655504-335d-44b4-ae07-22c6c633c773","year":2024},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.093635Z"},"links":{"cited_paper":"/paper/2405.04312","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:0576e49962eea518087546b8df432cd4f6d00e4db37149ddc80cd6a9a3bf08c6","observation_id":"fde88d4c-e1e2-4d00-9f0e-6e7510664d66","resolution":{"observed_at":"2026-08-05T17:31:13.207281Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08552","last_updated":"2024-10-18T12:05:21Z","snapshot_observed_at":"2026-08-21T21:11:03.686888Z","submitted_at":"2024-06-12T18:00:08Z","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08552","snapshot_observed_at":"2026-08-05T17:31:13.096559Z","title":"arXiv preprint arXiv:2406.08552","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.096559Z"},"links":{"cited_paper":"/paper/2406.08552","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:b6dfe0aa6f31f1a4f4df3f50132853073b56bbd9ed4bc04edf0351c86be8be8a","observation_id":"743e656b-1d9c-49d3-9c35-0a4365b2cdf1","resolution":{"observed_at":"2026-08-05T17:31:13.096559Z","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":"2026-08-05T17:31:13.099733Z","title":"arXiv preprint arXiv:2408.12588","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.099733Z"},"links":{"cited_paper":"/paper/2408.12588","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:4c7db7a87a347b596ced0f064471f5b2389480917833a245b463e1f2e3582feb","observation_id":"a1faab66-0305-46d0-a4c1-b0635b35f7ac","resolution":{"observed_at":"2026-08-05T17:31:13.099733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13268","last_updated":"2023-10-28T07:03:14Z","snapshot_observed_at":"2026-08-16T14:50:30.188090Z","submitted_at":"2023-10-20T04:23:12Z","title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13268","snapshot_observed_at":"2026-08-05T17:31:13.102906Z","title":"arXiv preprint arXiv:2310.13268","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.102906Z"},"links":{"cited_paper":"/paper/2310.13268","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:ddb211ae8bd961eff06ac4eaef799644ca3df3bc8faa88bdaa1a85dad761d11f","observation_id":"1c4c6a98-83da-4791-bf44-be76ed7aa0cd","resolution":{"observed_at":"2026-08-05T17:31:13.102906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16942","last_updated":"2024-10-22T12:18:24Z","snapshot_observed_at":"2026-08-16T13:07:01.667321Z","submitted_at":"2024-10-22T12:18:24Z","title":"DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization","version":1},"cited_work":{"arxiv_id":"2410.16942","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.16942","snapshot_observed_at":"2026-08-05T17:31:13.152334Z","title":"DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization","venue":"cs.CV","work_id":"04ae2348-1b1b-4e63-8251-ab341f2c9a71","year":2024},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.106202Z"},"links":{"cited_paper":"/paper/2410.16942","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:92fdb1fe4a5cc674c873bd3f2028cfcc289a432bb1a9b0c4c67f6244383c76ea","observation_id":"a39bcbdc-3dcd-49fe-b2fb-09311a6b7151","resolution":{"observed_at":"2026-08-05T17:31:13.157842Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05317","last_updated":"2025-02-19T10:39:58Z","snapshot_observed_at":"2026-08-19T20:02:47.466774Z","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":"2026-08-05T17:31:13.109226Z","title":"arXiv preprint arXiv:2410.05317","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.109226Z"},"links":{"cited_paper":"/paper/2410.05317","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:8538f5704089c8db15f01575e1683d0d740ce0613526a23bbd96381fcd53f31d","observation_id":"9f0e57be-8ab7-4cd4-958a-beab243af77c","resolution":{"observed_at":"2026-08-05T17:31:13.109226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1505.04597","last_updated":"2015-05-18T11:28:37Z","snapshot_observed_at":"2026-08-15T21:30:31.645090Z","submitted_at":"2015-05-18T11:28:37Z","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.04597","snapshot_observed_at":"2026-08-05T17:31:13.065597Z","title":"arXiv preprint arXiv:1505.04597","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.065597Z"},"links":{"cited_paper":"/paper/1505.04597","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:74ea2222b8aa87bb8dcbc2b30886a4f643a40347873b3925027f63ccf8dc1dd7","observation_id":"e5910081-7368-403c-952a-bb068c196cc0","resolution":{"observed_at":"2026-08-05T17:31:13.065597Z","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":"2026-08-05T17:31:13.439206Z","title":"In Ad- vances in Neural Information Processing Systems 30 (NIPS 2017)","venue":null,"work_id":"c3cc8014-76c9-4286-bf4a-cea0224c9c66","year":2017},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.032003Z"},"links":{"citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:57eb374263e36787732c817c936a56a8df4c4319731c8fc67f5cbacb5a742d2d","observation_id":"e3b05b1f-637b-4a25-b609-0d9b74ca59fb","resolution":{"observed_at":"2026-08-05T17:31:13.442159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-05T17:31:13.448698Z","title":"In 2019 IEEE/CVF International Confer- ence on Computer Vision Workshop (ICCVW), 512–520","venue":null,"work_id":"a3f0bc0f-d861-4d9e-b4ed-a2e668842be5","year":2019},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.025299Z"},"links":{"citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:bb53b4748e149fcc61bc59f0c57113f4b973db72fd959d0646681904700c4527","observation_id":"d21e9708-90bc-4247-b61b-5ef6f5e36b28","resolution":{"observed_at":"2026-08-05T17:31:13.451813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11239","last_updated":"2020-12-16T21:15:05Z","snapshot_observed_at":"2026-08-10T05:21:27.485481Z","submitted_at":"2020-06-19T17:24:44Z","title":"Denoising Diffusion Probabilistic Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11239","snapshot_observed_at":"2026-08-05T17:31:13.036056Z","title":"arXiv preprint arXiv:2006.11239","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.036056Z"},"links":{"cited_paper":"/paper/2006.11239","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:d5392def55b32cb11d74e4ab050eecdd57ec372d3a7f260ec1b15f66b2ccf8b0","observation_id":"74b62f1d-aab7-4abf-83f3-8fc486c18978","resolution":{"observed_at":"2026-08-05T17:31:13.036056Z","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":"2026-08-05T17:31:13.028828Z","title":"arXiv preprint arXiv:2104.08718","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.028828Z"},"links":{"cited_paper":"/paper/2104.08718","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:0255027104476bea7c04ff860d14d5dcc13bee760ae3b33927b6c081cacc6b64","observation_id":"854f6125-ac1b-49e9-ab97-e398eb621038","resolution":{"observed_at":"2026-08-05T17:31:13.028828Z","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":"2026-08-05T17:31:13.052988Z","title":"arXiv preprint arXiv:2209.03003","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.052988Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:5851288e457b6d76fbd5319092d2d2e60b561ef89926356bffbe834a29581cc3","observation_id":"725f2a67-d236-4e36-8809-b63e20261048","resolution":{"observed_at":"2026-08-05T17:31:13.052988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-20T09:39:07.545813Z","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":"2026-08-05T17:31:13.001967Z","title":"arXiv preprint arXiv:2311.15127","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.001967Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:1a2c664b9246bde46f31508c7ab8d1cc8700d5e0c43f94f94963161def6cde80","observation_id":"af9a5ef3-ec67-48e1-8c28-caba19680914","resolution":{"observed_at":"2026-08-05T17:31:13.001967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09068","last_updated":"2024-03-14T03:19:31Z","snapshot_observed_at":"2026-08-16T14:09:58.445889Z","submitted_at":"2024-03-14T03:19:31Z","title":"Self-enhanced mobility enables vortex pattern formation in living matter","version":1},"cited_work":{"arxiv_id":"2403.09068","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.09068","snapshot_observed_at":"2026-08-05T17:31:13.403716Z","title":"Self-enhanced mobility enables vortex pattern formation in living matter","venue":"physics.bio-ph","work_id":"e8679f41-4327-42f8-b867-3574fcad8d22","year":2024},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.013865Z"},"links":{"cited_paper":"/paper/2403.09068","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:e4ec260b964a27c39788d11a00ba00cfb6a167b4fcd79e20842990e7a5c07ff3","observation_id":"48a51896-efe4-452b-9f81-49446461045b","resolution":{"observed_at":"2026-08-05T17:31:13.406916Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-05T17:31:13.017504Z","title":"arXiv preprint arXiv:2502.00433","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T17:31:13.017504Z"},"links":{"cited_paper":"/paper/2502.00433","citing_paper":"/paper/2508.16211"},"observation_digest":"sha256:3351d47a06329d1245fb367311ba9d884e8475674cf52f5e0feaf2bf8b7c1973","observation_id":"5826e9cf-f797-437d-aeeb-142cc0929323","resolution":{"observed_at":"2026-08-05T17:31:13.017504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.16211","last_updated":"2025-08-22T08:34:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T04:26:24.384790Z","submitted_at":"2025-08-22T08:34:03Z","title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":4,"parse_uncertain":0,"unresolved":27,"verified_exact":0,"verified_fuzzy":2},"total_outbound_references":33},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 5 inbound Pith citation observations for arXiv:2508.16211."}