{"as_of":"2026-08-15T23:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:73e113cbfaeb01ff44df86f71c6f846a3186e955919897cb2e0ab703cc54df95","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:42:59.707495Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T12:12:37.241869Z","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":"2026-06-30T12:34:39.313043Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"cited_work":{"arxiv_id":"2508.16212","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.16212","snapshot_observed_at":"2026-06-30T12:34:39.313043Z","title":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei","venue":null,"work_id":"e12dcf19-3dd4-41a9-bcb1-99f6bfaba9ca","year":null},"citing_paper":{"arxiv_id":"2605.24870","last_updated":"2026-05-24T05:00:06Z","snapshot_observed_at":"2026-08-02T08:49:22.239542Z","submitted_at":"2026-05-24T05:00:06Z","title":"Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-30T12:12:37.241869Z"},"links":{"cited_paper":"/paper/2508.16212","citing_paper":"/paper/2605.24870"},"observation_digest":"sha256:8197f1849b67e2f57e42323a22fa41c9e174164d93d98fbbbb1665516fcbf8a0","observation_id":"89952db7-e8e7-4ae8-b54b-0b2c6d9358dc","resolution":{"observed_at":"2026-06-30T12:34:39.314612Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.16212/citation-record","integrity":"/paper/2508.16212/integrity","json":"/paper/2508.16212/citation-record.json","paper":"/paper/2508.16212"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T17:42:55.570492Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.570492Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:b9663ad988f00f978ed388fa103337b5780c5d452ced2cae1d05901c5696f114","observation_id":"2f9f10b2-1769-47df-ac63-540853750d0f","resolution":{"observed_at":"2026-08-05T17:42:55.570492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07309","last_updated":"2022-06-15T05:42:48Z","snapshot_observed_at":"2026-08-13T15:23:39.706970Z","submitted_at":"2022-06-15T05:42:48Z","title":"Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.07309","snapshot_observed_at":"2026-08-05T17:42:55.639983Z","title":"Estimating the optimal covariance with imperfect mean in diffusion probabilistic models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.639983Z"},"links":{"cited_paper":"/paper/2206.07309","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:30153fc5bc9fc727f34c31c77ae388f6df806f909f0f831b5a672513e03dab5a","observation_id":"dd1a55cf-3f4e-477e-bc0e-b852b72b2965","resolution":{"observed_at":"2026-08-05T17:42:55.639983Z","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":"2026-08-05T17:43:06.190460Z","title":"All are worth words: A vit backbone for diffusion models","venue":null,"work_id":"2119e090-bfe2-4488-9bb4-cb010f835995","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.717082Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:e7250304c07c649b97b55d7e177dac4c06cb996609594bb8d33121e34204d3d8","observation_id":"782fd43d-8f4d-447e-a385-7c199f0b5a41","resolution":{"observed_at":"2026-08-05T17:43:06.292942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:06.008573Z","title":"Video generation models as world simulators","venue":null,"work_id":"7f91e91a-3862-4a84-9014-195360cabcf5","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.809091Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:cf3297924aadc6baaa9266ec09047c722de255db81073350d1e5dbda74583e23","observation_id":"5cf32fbf-2dee-47ad-916f-7fb40fe48d12","resolution":{"observed_at":"2026-08-05T17:43:06.091165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07920","last_updated":"2023-09-15T07:56:34Z","snapshot_observed_at":"2026-08-15T19:39:19.595255Z","submitted_at":"2023-09-14T17:59:53Z","title":"Large-Vocabulary 3D Diffusion Model with Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07920","snapshot_observed_at":"2026-08-05T17:42:55.882896Z","title":"Large-vocabulary 3d diffusion model with transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.882896Z"},"links":{"cited_paper":"/paper/2309.07920","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:f012665c17a1b87d03d746ce115bd589e5134d3ed0f19025383793838b0ec73d","observation_id":"23f8e435-7ad4-4e75-868f-9a26e22af23e","resolution":{"observed_at":"2026-08-05T17:42:55.882896Z","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":"2026-08-05T17:43:05.841526Z","title":"On the trajectory regularity of ode-based diffusion sampling","venue":null,"work_id":"02ecfdcf-86e4-43b0-890d-b29881b75e1b","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.952461Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:3b840be3f8f799ca6869a658a08c331f85cf2d87fe4a69bf85374dcc11966026","observation_id":"11cd7ea5-5441-4e0b-8055-247260460736","resolution":{"observed_at":"2026-08-05T17:43:05.913520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:05.682956Z","title":"Tgate: Accelerating cross-attention in diffusion models via token-level cache reuse","venue":null,"work_id":"80b353f3-9056-4818-b9aa-735bdc79318e","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:55.996753Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:bcdd577b1420edd92a7f89571e352e673ada66f7ba85dee7215e8174387e2811","observation_id":"7422e3c4-1286-4eb1-bf8b-4c7d9eb3aad0","resolution":{"observed_at":"2026-08-05T17:43:05.756342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01125","last_updated":"2024-06-03T09:10:44Z","snapshot_observed_at":"2026-08-15T10:51:52.846309Z","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":"2026-08-05T17:42:56.072860Z","title":"\\( \\)-dit: A training-free acceleration method tailored for diffusion transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.072860Z"},"links":{"cited_paper":"/paper/2406.01125","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:ff6872cd0fc5218c4694f02c3fa4c527a3c0e6c42ac4f9628eaa69cb4141a6a2","observation_id":"77c6a61b-7d68-4908-b7ea-1a9aa6be668a","resolution":{"observed_at":"2026-08-05T17:42:56.072860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04557","last_updated":"2024-06-02T09:30:39Z","snapshot_observed_at":"2026-08-15T10:38:03.782417Z","submitted_at":"2023-12-07T18:59:30Z","title":"GenTron: Diffusion Transformers for Image and Video Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04557","snapshot_observed_at":"2026-08-05T17:42:56.097312Z","title":"Gentron: Delving deep into diffusion transformers for image and video generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.097312Z"},"links":{"cited_paper":"/paper/2312.04557","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:da6aed6890d9f72423c70258a71ad5b6aaa00a92d5bf6437275442d1804b2403","observation_id":"3a0add5c-329f-4352-8623-a0b73598ee75","resolution":{"observed_at":"2026-08-05T17:42:56.097312Z","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":"2026-08-05T17:43:05.492688Z","title":"Qncd: Quantization noise correction for diffusion models","venue":null,"work_id":"16984b0b-8757-4aef-8bfd-6cd9818841a9","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.144439Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:b1ff4804dfef1a6bf6d0a3d99eafe15695d841577db862d21166b78e84cae45e","observation_id":"52a4abfa-71ed-45ed-b907-20d0825f3c21","resolution":{"observed_at":"2026-08-05T17:43:05.573947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:42:56.237857Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.237857Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:2886edcb3d906cc71a96bbd9bd194970ceff64e28ae49cbc551af946fa2f7a06","observation_id":"1d3dbab7-0ff3-4ba9-b68d-4debd9860640","resolution":{"observed_at":"2026-08-05T17:42:56.237857Z","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":"2026-08-05T17:43:05.273294Z","title":"Structural pruning for diffusion models","venue":null,"work_id":"409d8769-99e1-4bfb-aa2a-702d004e077d","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.290067Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:ca32758f9ff89bc825780ed577a2dd597fb12abe6cd3ef5030f044afae70db9d","observation_id":"8e1ab0ae-3df4-4253-aaf6-ffa0b6bee895","resolution":{"observed_at":"2026-08-05T17:43:05.378262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:42:56.389849Z","title":"Generative adversarial networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.389849Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:4629a9ac6b394e9373426b3e52c0383dea2080ccd454672af69f579e3dcf5f91","observation_id":"34c5bd87-0a9d-4563-8611-05bc1e7df4a4","resolution":{"observed_at":"2026-08-05T17:42:56.389849Z","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":"2026-08-05T17:42:56.427032Z","title":"Ptqd: Accurate post-training quantization for diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.427032Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:9ea89bc99b0efbdea3f9ce2a543ffc8fdcaedc38c751e4a3f0b36a1acb53dab0","observation_id":"8c8cba25-4d71-4faa-a9a6-5c40adae0692","resolution":{"observed_at":"2026-08-05T17:42:56.427032Z","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":"2026-08-05T17:43:05.008650Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":"c5dd56c4-a1ce-4c67-afce-65fce6ddd66f","year":2017},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.469902Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:9ec6ab5c38c426f1ed92ab36593b832d1bfcf929627c03a1a45faeeb17346c4d","observation_id":"e0428e58-af30-4438-a332-5dc128d4f49e","resolution":{"observed_at":"2026-08-05T17:43:05.125961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:04.721745Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":"2265d7af-46de-4de7-8bc4-081b9aa377b6","year":2020},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.579127Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:af0505413c00bceca19b169edfb75937131f79dc189f230e5c2ff3f4c7cef0c9","observation_id":"6de2980c-d3a6-4631-88ac-13455977db56","resolution":{"observed_at":"2026-08-05T17:43:04.827119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.02037","last_updated":"2022-02-01T21:32:15Z","snapshot_observed_at":"2026-08-15T00:56:20.174938Z","submitted_at":"2021-10-05T13:36:55Z","title":"Autoregressive Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02037","snapshot_observed_at":"2026-08-05T17:42:56.624311Z","title":"Autoregressive diffusion models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.624311Z"},"links":{"cited_paper":"/paper/2110.02037","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:79d4fd2a771e7311675b8b8fbb240c1a438cf4bfdf37abd88203a6d7ce718841","observation_id":"5065df35-0709-41e3-a4bf-381cc512b54a","resolution":{"observed_at":"2026-08-05T17:42:56.624311Z","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":"2026-08-05T17:43:04.491291Z","title":"Vbench: A comprehensive benchmark for video generation","venue":null,"work_id":"59af2537-9543-4d35-b793-1303eedea56d","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.689939Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:b2feaab361bf8976b3ec3954a5c73ce9f73945b89b99f656d1705b8438370d1e","observation_id":"d69a980f-0566-4f6e-9fcb-22a2029ffca3","resolution":{"observed_at":"2026-08-05T17:43:04.595867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:04.310587Z","title":"Schuller","venue":null,"work_id":"e26f606f-48c4-40ab-aeb7-2cf67f127763","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.726949Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:1f07f574701f14f200cb5dc9256be64622db708504d057848a808e94c67bac22","observation_id":"4993b47c-1b09-4dc0-83d5-cf9a0fba4a7c","resolution":{"observed_at":"2026-08-05T17:43:04.393349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02397","last_updated":"2024-11-07T17:06:32Z","snapshot_observed_at":"2026-08-12T22:07:57.696425Z","submitted_at":"2024-11-04T18:59:44Z","title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.02397","snapshot_observed_at":"2026-08-05T17:42:56.759377Z","title":"Adaptive caching for faster video generation with diffusion transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.759377Z"},"links":{"cited_paper":"/paper/2411.02397","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:55d77871ef623ea4fa129a95257de639803779c2dc1dcbbdb3d60b5a83810ce0","observation_id":"480257cb-4be5-45de-9852-68f348a4eed2","resolution":{"observed_at":"2026-08-05T17:42:56.759377Z","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":"2026-08-05T17:43:04.083537Z","title":"Bk-sdm: Architecturally compressed stable diffusion for efficient text-to-image generation","venue":null,"work_id":"2903a044-f147-4ebb-a13e-a3b173c1b353","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.845391Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:054027682f4da4a060a93aaaf64c2665d21bff6f29a6a854cb812d32e140e148","observation_id":"815a2912-fd6f-41a1-af1a-905260b164fe","resolution":{"observed_at":"2026-08-05T17:43:04.185303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:03.895026Z","title":"Kv caching in transformers for efficient inference","venue":null,"work_id":"4de659ec-5af0-4f8d-9e4c-72d3643dbbbb","year":2020},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.896015Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:a312798fc264bb0206facb879cd4c88e22f26a3181ef509494b151e431e6dd4b","observation_id":"e20ae314-702c-4d80-9500-8b1f84ebbbf5","resolution":{"observed_at":"2026-08-05T17:43:03.972807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:03.725280Z","title":"Improved precision and recall metric for assessing generative models","venue":null,"work_id":"4cf689f0-f6b8-46c9-aab0-c5ec84fa8357","year":2019},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:56.987318Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:78ce5f5ea4e782e82c194504efe92698b280740467cdba307c728ab5134937ae","observation_id":"f5af8b1c-4ca1-4234-bc28-6289e99c6e70","resolution":{"observed_at":"2026-08-05T17:43:03.799378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:03.521957Z","title":"Q-align: A quality alignment metric for image-to-video generation","venue":null,"work_id":"7a65431c-e3d0-48fd-84ff-9b2789f39731","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.019015Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:6296edc053ba74db3ab0dd4a5050386cf2bd315157b26a24290d2a36c8ced4fe","observation_id":"0f8b6887-3bcc-4a7e-9c0b-6bb1d4ad9c4f","resolution":{"observed_at":"2026-08-05T17:43:03.617359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:03.331508Z","title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds","venue":null,"work_id":"2b126376-7e04-40cb-91c6-c67890299630","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.104324Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:7e86d12b143161c6e26c656506e4179713791a9187c86dd0d4a2c3418089ad4f","observation_id":"fd7a6221-1800-4ea6-a2c4-7c2cd5ffb63e","resolution":{"observed_at":"2026-08-05T17:43:03.423775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19108","last_updated":"2025-03-18T04:49:23Z","snapshot_observed_at":"2026-08-12T10:29:40.066151Z","submitted_at":"2024-11-28T12:50:05Z","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19108","snapshot_observed_at":"2026-08-05T17:42:57.175316Z","title":"Timestep embedding tells: It's time to cache for video diffusion model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.175316Z"},"links":{"cited_paper":"/paper/2411.19108","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:f3c63e14bbc97210e09073eeb85a0706d4e98616fa2a5b90cae9bd6dadfdfa57","observation_id":"88147c4c-c151-485e-8aa9-0310db47931c","resolution":{"observed_at":"2026-08-05T17:42:57.175316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12708","last_updated":"2024-04-21T07:17:14Z","snapshot_observed_at":"2026-08-14T19:26:12.177741Z","submitted_at":"2023-05-22T04:37:41Z","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12708","snapshot_observed_at":"2026-08-05T17:42:57.228657Z","title":"Vit-tts: Visual text-to-speech with scalable diffusion transformer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.228657Z"},"links":{"cited_paper":"/paper/2305.12708","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:c6b1c90cd65d0c27db04f481769c53cedf1aeecc4c8af696e946e3c03d17ffae","observation_id":"3b5b277b-5ef8-4ed6-9797-1bd7b85d147d","resolution":{"observed_at":"2026-08-05T17:42:57.228657Z","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":"2026-08-05T17:42:57.327895Z","title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.327895Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:b20a3e8b2118e38f1f698730a8416de0f1ff5246531f5dae9ed7442731d2980e","observation_id":"701807cd-c8ed-4f85-9217-a1690752422b","resolution":{"observed_at":"2026-08-05T17:42:57.327895Z","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":"2026-08-05T17:43:03.120888Z","title":"Vdt: General-purpose video diffusion transformers via mask modeling","venue":null,"work_id":"cb933336-32c4-4354-9eec-5cde0f05f834","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.392614Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:84f3b59de61b86b0d461d3d5c099924565fac50d25eac866d812217b28679678","observation_id":"51ada3d1-5a9d-4908-a94d-e4f5c4996435","resolution":{"observed_at":"2026-08-05T17:43:03.192315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.02388","last_updated":"2021-01-07T06:12:28Z","snapshot_observed_at":"2026-08-14T18:54:24.557628Z","submitted_at":"2021-01-07T06:12:28Z","title":"Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.02388","snapshot_observed_at":"2026-08-05T17:42:57.472910Z","title":"Knowledge distillation in iterative generative models for improved sampling speed","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.472910Z"},"links":{"cited_paper":"/paper/2101.02388","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:b60f555aa4769163a823526761c1d46f63f82df5bbafe735aad0c2be81b0ca30","observation_id":"c24a2195-cafe-4ea9-9243-89bbc13b1128","resolution":{"observed_at":"2026-08-05T17:42:57.472910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04378","last_updated":"2023-10-06T17:11:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-06T17:11:58Z","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04378","snapshot_observed_at":"2026-08-05T17:42:57.538988Z","title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.538988Z"},"links":{"cited_paper":"/paper/2310.04378","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:365f21635532778403a3e9c60cfa996e24c957f96127e31a738507eb3846b7ad","observation_id":"c185d0d0-cb3f-4c60-b359-5141ff5456a5","resolution":{"observed_at":"2026-08-05T17:42:57.538988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12524","last_updated":"2022-05-30T03:13:08Z","snapshot_observed_at":"2026-08-14T00:36:06.045125Z","submitted_at":"2022-05-25T06:40:09Z","title":"Accelerating Diffusion Models via Early Stop of the Diffusion Process","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12524","snapshot_observed_at":"2026-08-05T17:42:57.635646Z","title":"Accelerating diffusion models via early stop of the diffusion process","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.635646Z"},"links":{"cited_paper":"/paper/2205.12524","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:2eba4d610ff7b4c4c9f4ddaa9826a7ad9382298ba708f1763f61e99703843168","observation_id":"2f0dad2f-8868-4515-881b-66e7dd11a670","resolution":{"observed_at":"2026-08-05T17:42:57.635646Z","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":"2026-08-13T05:12:18.337935Z","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":"2026-08-05T17:42:57.744949Z","title":"Deepcache: Accelerating diffusion models for free","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.744949Z"},"links":{"cited_paper":"/paper/2312.00858","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:ba6550375dc1909f644909ec8f2a19ff86eb039642d3584cb94100f73763186b","observation_id":"34fd749d-2f1e-4ec3-97fe-75d5edfb5e0b","resolution":{"observed_at":"2026-08-05T17:42:57.744949Z","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":"2026-08-05T17:43:02.853383Z","title":"Learning-to-cache: Accelerating diffusion transformer via layer caching","venue":null,"work_id":"042f1f04-4276-4563-b7de-8cbcc2b88601","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.823238Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:5ae427f3a688443a3556c1566586d5b0d6afb79f4b6de295f564efd342406f25","observation_id":"5b2c0b85-d4b4-40ee-b5cd-006668574ff7","resolution":{"observed_at":"2026-08-05T17:43:02.981603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03048","last_updated":"2025-05-01T09:40:21Z","snapshot_observed_at":"2026-08-13T10:28:06.516901Z","submitted_at":"2024-01-05T19:55:15Z","title":"Latte: Latent Diffusion Transformer for Video Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03048","snapshot_observed_at":"2026-08-05T17:42:57.900344Z","title":"Latte: Latent diffusion transformer for video generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.900344Z"},"links":{"cited_paper":"/paper/2401.03048","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:f38204c24c1831221eb0cc275e342cbfb986118a72f1399e8f03926e5f57c5a7","observation_id":"451bb4eb-9bbf-45b9-96f0-e572bef1bbdf","resolution":{"observed_at":"2026-08-05T17:42:57.900344Z","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":"2026-08-05T17:43:02.555007Z","title":"Dit-3d: Exploring plain diffusion transformers for 3d shape generation","venue":null,"work_id":"b8ac853e-ff6d-4719-99b9-4bf1e1ddf108","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:57.962316Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:176cc6d75c431b3e08be91bac314c0f6a9b7ec47961deb28f62778cd432863d4","observation_id":"04bf5014-ec7b-41c5-9c40-f78c86994f05","resolution":{"observed_at":"2026-08-05T17:43:02.651822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:02.327349Z","title":"Advances in kv caching techniques for large-scale language models","venue":null,"work_id":"28e7ea41-793e-46bc-81e7-fd7ee2caa4b8","year":2021},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.027805Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:47895215f8f4901d99a6de16f5c1473f7d5d286e2f4f0e90a7828290bdbf1fb9","observation_id":"a04ec3dc-44ce-4b52-a5c9-2f3dd3fbc017","resolution":{"observed_at":"2026-08-05T17:43:02.438571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:02.181194Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"4f25e89f-a503-440b-b15e-cb56bd6e86ce","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.099759Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:60e2518f2e20fb4b7f12555b27e9beb70a7a19b99e835731124834f6136057b8","observation_id":"2caaa207-2ab2-4afa-a5f3-16fef4d988ce","resolution":{"observed_at":"2026-08-05T17:43:02.254559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:01.952192Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"ea74993d-cd4e-492a-a8ca-c4fa58e72a3e","year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.191703Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:1d0ec0e4b72c8e5001e0bbc434f40f92c2f6905bac87892a111d57b4800dd135","observation_id":"6e415b17-2c1f-441b-aa9f-17af4b1aa071","resolution":{"observed_at":"2026-08-05T17:43:02.013517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.00512","last_updated":"2022-06-07T09:17:35Z","snapshot_observed_at":"2026-08-12T01:14:44.484432Z","submitted_at":"2022-02-01T16:07:25Z","title":"Progressive Distillation for Fast Sampling of Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.00512","snapshot_observed_at":"2026-08-05T17:42:58.257264Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.257264Z"},"links":{"cited_paper":"/paper/2202.00512","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:19a56f80badeb1415da2e32472ec43bac48d9cc2fb62d37e970ab3114b6be863","observation_id":"cbdf1a6e-3c6d-4499-bd87-a2ad6308f842","resolution":{"observed_at":"2026-08-05T17:42:58.257264Z","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":"2026-08-12T23:31:08.447888Z","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":"2026-08-05T17:42:58.320777Z","title":"Fora: Fast-forward caching in diffusion transformer acceleration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.320777Z"},"links":{"cited_paper":"/paper/2407.01425","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:e2b77351ac1a8e67cba7bdf6a8a7f675373adbb7c5b9e2877078a549540fabbc","observation_id":"c7812908-9857-477c-8c4f-c480df3182dd","resolution":{"observed_at":"2026-08-05T17:42:58.320777Z","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":"2026-08-05T17:43:01.784564Z","title":"Post-training quantization on diffusion models","venue":null,"work_id":"4a582da2-d45a-427e-a48d-12093f10869d","year":1972},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.385372Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:7c87a1ba375fee14fb5f6826734e2942087b3958087b76c878b47e8258e9d7e0","observation_id":"2523338d-7cf3-4ec0-af21-b13715a6b69b","resolution":{"observed_at":"2026-08-05T17:43:01.878695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:42:58.454684Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.454684Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:5ef26d4d05cc0f361c11aab0a034415853bdb832639fcad63b3148ade4774336","observation_id":"b73abb57-d5a5-4f55-806c-4c11ffe91da1","resolution":{"observed_at":"2026-08-05T17:42:58.454684Z","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":"2026-08-05T17:42:58.521805Z","title":"Generative modeling by estimating gradients of the data distribution","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.521805Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:a4445ed87e42edcadd822c6b534835efeb7a66180895912bd2582fc7f53d43e3","observation_id":"c0072b3e-bb4b-4b0a-a561-cf3ed34e9287","resolution":{"observed_at":"2026-08-05T17:42:58.521805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-05T17:42:58.606461Z","title":"Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.606461Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:8d781fcb0545799255930944688749da9d6276e1d10ab02829264fdbf1bfe626","observation_id":"ef9970c7-0be4-4c91-848d-ac2ab4430773","resolution":{"observed_at":"2026-08-05T17:42:58.606461Z","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":"2026-08-05T17:42:58.676382Z","title":"Consistency models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.676382Z"},"links":{"cited_paper":"/paper/2303.01469","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:8eba9e5ce7511fd60779e7df0a9f852e14796df68a7f0381f0d5c6cf16b367e3","observation_id":"869816ab-fade-41b2-9cea-6fdc4087e380","resolution":{"observed_at":"2026-08-05T17:42:58.676382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10468","last_updated":"2024-07-15T06:49:05Z","snapshot_observed_at":"2026-08-15T00:25:09.108789Z","submitted_at":"2024-07-15T06:49:05Z","title":"LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis","version":1},"cited_work":{"arxiv_id":"2407.10468","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.10468","snapshot_observed_at":"2026-08-05T17:43:00.355395Z","title":"LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis","venue":"cs.SD","work_id":"704bcad1-6705-4f13-8d3f-6ccabc21a7c2","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.735042Z"},"links":{"cited_paper":"/paper/2407.10468","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:72a0450044c00470f86be0e14a30152ed044d2ce829d37ed3dbff718e894283c","observation_id":"7e193516-ba77-4deb-8f9b-97a7830df2a9","resolution":{"observed_at":"2026-08-05T17:43:00.429011Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:43:01.598401Z","title":"Efficient diffusion models for vision: A survey, 2022","venue":null,"work_id":"4a69be20-ded7-4497-a43f-db8555361fe1","year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.819444Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:db976edf444e40ba0ee6b49281b037e3c8732ca35ebc75d5967cea3ef662e276","observation_id":"fabcdf7f-b5e6-4fcf-aa10-6a877e91ecc9","resolution":{"observed_at":"2026-08-05T17:43:01.670929Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:42:58.889769Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:58.889769Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:676a6e72d33564f07818cc3460ea67385c059e73fe190a3521cb744a54a5e25a","observation_id":"dca399a7-9243-43b7-8fa1-c0e6a17b737c","resolution":{"observed_at":"2026-08-05T17:42:58.889769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07209","last_updated":"2025-03-04T06:21:26Z","snapshot_observed_at":"2026-08-15T02:15:11.970170Z","submitted_at":"2024-06-11T12:32:53Z","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07209","snapshot_observed_at":"2026-08-05T17:42:59.002057Z","title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.002057Z"},"links":{"cited_paper":"/paper/2406.07209","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:c04da10cc03fa29bf731e7512ecb800b358a2b8991a41e2882ee20ddd8e68a51","observation_id":"1e93c7eb-55eb-448e-8970-9f027a610277","resolution":{"observed_at":"2026-08-05T17:42:59.002057Z","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":"2026-08-05T17:43:01.430264Z","title":null,"venue":null,"work_id":"7189175c-1e7c-47b1-94c4-31fea9288e91","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.076518Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:e74f579d7255fa92a3cd6f7e4f35d97acee80418b4d0fb1f75cc6ba398cb2a86","observation_id":"3556d15f-c57e-4651-a88a-c97f02f53835","resolution":{"observed_at":"2026-08-05T17:43:01.523531Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-05T17:42:59.161687Z","title":"Image quality assessment: from error visibility to structural similarity","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.161687Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:8eda98785e8427e64d0f4a8996defce9fe0478d9d9e6f79d50662db1049bcc90","observation_id":"213e406b-e47f-4540-ba98-9d2eaa922d8e","resolution":{"observed_at":"2026-08-05T17:42:59.161687Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02262","last_updated":"2023-08-25T16:33:42Z","snapshot_observed_at":"2026-08-13T15:29:47.952455Z","submitted_at":"2022-06-05T20:45:01Z","title":"Diffusion-GAN: Training GANs with Diffusion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.02262","snapshot_observed_at":"2026-08-05T17:42:59.199332Z","title":"Diffusion-gan: Training gans with diffusion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.199332Z"},"links":{"cited_paper":"/paper/2206.02262","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:a1b02e88043ec6997e7043bc47edd66b94faadf45424cf32677b18cfd59877bd","observation_id":"2dfe65dd-df14-46ca-b941-162c25f74a6d","resolution":{"observed_at":"2026-08-05T17:42:59.199332Z","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":"2026-08-15T04:22:11.316850Z","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":"2026-08-05T17:42:59.272072Z","title":"Cache me if you can: Accelerating diffusion models through block caching","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.272072Z"},"links":{"cited_paper":"/paper/2312.03209","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:044c6f4221b677aca50fe69b0e65402f15a1dbdbe9c55b5ad3186d8137d94e58","observation_id":"7668766f-2985-4265-b106-c34655861005","resolution":{"observed_at":"2026-08-05T17:42:59.272072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01776","last_updated":"2025-04-27T00:10:11Z","snapshot_observed_at":"2026-08-15T20:59:30.034825Z","submitted_at":"2025-02-03T19:29:16Z","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01776","snapshot_observed_at":"2026-08-05T17:42:59.370738Z","title":"Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.370738Z"},"links":{"cited_paper":"/paper/2502.01776","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:f397b4e7eaeade37c526d42e2d9986eaf240762155b9b8c97d18a56a9ddff50b","observation_id":"2ffb7943-4b97-4d80-80f5-79b3fd6fc82c","resolution":{"observed_at":"2026-08-05T17:42:59.370738Z","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":"2026-08-05T17:43:01.260148Z","title":"Diffusion probabilistic model made slim","venue":null,"work_id":"1e7a8981-7e6d-46ae-9c57-222a5bcb3262","year":2023},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.417938Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:dfd6ee96f58bf2914a22e57af37158d73086d38a4a6abd33fa7c95d4f1979d82","observation_id":"3f7678c2-adf3-4862-aab0-b35a1a35e478","resolution":{"observed_at":"2026-08-05T17:43:01.282516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.06072","last_updated":"2025-03-26T08:33:10Z","snapshot_observed_at":"2026-08-15T19:52:28.153954Z","submitted_at":"2024-08-12T11:47:11Z","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.06072","snapshot_observed_at":"2026-08-05T17:42:59.458131Z","title":"Cogvideox: Text-to-video diffusion models with an expert transformer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.458131Z"},"links":{"cited_paper":"/paper/2408.06072","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:c1eed0534c92979f4ac8806c9bd54f87784a8b62349a060576f084e35a6f5020","observation_id":"63c1fa28-411a-494a-b230-64530bd37447","resolution":{"observed_at":"2026-08-05T17:42:59.458131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.05564","last_updated":"2023-03-23T11:50:36Z","snapshot_observed_at":"2026-08-13T15:25:34.388859Z","submitted_at":"2022-06-11T16:57:23Z","title":"gDDIM: Generalized denoising diffusion implicit models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.05564","snapshot_observed_at":"2026-08-05T17:42:59.481754Z","title":"Gddim: Generalized denoising diffusion implicit models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.481754Z"},"links":{"cited_paper":"/paper/2206.05564","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:2d7f8669c122700b86224d21f439e8ab6e5e6421885e4025bb5a8704c5a314f2","observation_id":"a546c11a-f7eb-4f3e-813c-c5c9e7cc086a","resolution":{"observed_at":"2026-08-05T17:42:59.481754Z","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":"2026-08-05T17:42:59.533080Z","title":"The unreasonable effectiveness of deep features as a perceptual metric","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.533080Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:62104668a0a803c02cc0e4b12096da9b2c868c763c6a9db6f62b0044889ac6f7","observation_id":"52b497b1-f6e5-425c-898f-2163c94639f5","resolution":{"observed_at":"2026-08-05T17:42:59.533080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02747","last_updated":"2025-02-26T10:49:33Z","snapshot_observed_at":"2026-08-15T12:23:54.078172Z","submitted_at":"2024-04-03T13:44:41Z","title":"Faster Diffusion via Temporal Attention Decomposition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02747","snapshot_observed_at":"2026-08-05T17:42:59.602947Z","title":"T-gate: Accelerating cross-attention in diffusion models via cache reuse","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.602947Z"},"links":{"cited_paper":"/paper/2404.02747","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:070bcf75c85fb37e4ee3fad322726f71e64a01b874807bfeb7557fd21cc57bcd","observation_id":"1e74756a-da7e-4336-8cc5-4c70a28b921e","resolution":{"observed_at":"2026-08-05T17:42:59.602947Z","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":"2026-08-12T22:59:05.586923Z","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":"2026-08-05T17:42:59.655799Z","title":"Pab: Pyramid attention broadcast for real-time video generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.655799Z"},"links":{"cited_paper":"/paper/2408.12588","citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:d6342a6f984d1ad3e0192e9e152b7d8a576452dd389f39207ebcd1110c14d3e7","observation_id":"c388957f-a811-4dc3-b526-d985494b933b","resolution":{"observed_at":"2026-08-05T17:42:59.655799Z","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":"2026-08-05T17:43:01.052847Z","title":"Opensora: Democratizing efficient video production for all, 2024","venue":null,"work_id":"8f02a627-e964-4d8e-b094-ff9899e7d949","year":2024},"citing_paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-05T17:42:59.707495Z"},"links":{"citing_paper":"/paper/2508.16212"},"observation_digest":"sha256:34c7c99c470a676dd66b26e0e5644618c5c01819ee50c7ba5037624360687c31","observation_id":"cf4abd45-1425-47ed-8fe2-68499e2a6e8a","resolution":{"observed_at":"2026-08-05T17:43:01.166587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.16212","last_updated":"2025-08-25T03:07:02Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T18:02:44.608518Z","submitted_at":"2025-08-22T08:36:58Z","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":62},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2508.16212."}