{"as_of":"2026-08-05T08:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c213a130357340ce35fd8c7439fe04ca488d548ee8ee1f364ccba555d0239fb3","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T23:18:25.154970Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.24027/citation-record","integrity":"/paper/2607.24027/integrity","json":"/paper/2607.24027/citation-record.json","paper":"/paper/2607.24027"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:18:25.043094Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.043094Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:44b589d6b807cb734e12bc46a62629834e903904028538bcc589bedca1f03888","observation_id":"d3fcb42d-4df4-41f2-9cef-4d52bb821a7c","resolution":{"observed_at":"2026-07-31T23:18:25.043094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20314","last_updated":"2025-04-19T02:22:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-26T08:25:43Z","title":"Wan: Open and Advanced Large-Scale Video Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20314","snapshot_observed_at":"2026-07-31T23:18:25.046300Z","title":"Wan: Open and advanced large-scale video generative models.arXiv preprint arXiv:2503.20314, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.046300Z"},"links":{"cited_paper":"/paper/2503.20314","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:a0aa60fbc3bba22b13a569756989582cb39d196fdfb5bf0c7b699ce01b61af5e","observation_id":"1541a1c4-3c16-4ae6-b0a5-3a264bfc5a22","resolution":{"observed_at":"2026-07-31T23:18:25.046300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.03603","last_updated":"2025-03-11T08:14:25Z","snapshot_observed_at":"2026-08-03T00:44:01.942521Z","submitted_at":"2024-12-03T23:52:37Z","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.03603","snapshot_observed_at":"2026-07-31T23:18:25.049155Z","title":"HunyuanVideo: A systematic framework for large video generative models.arXiv preprint arXiv:2412.03603, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.049155Z"},"links":{"cited_paper":"/paper/2412.03603","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:2275bb0f7e54d27498ac803fbc2dd840294dc29d0134401b9d4f8d91978ce9bf","observation_id":"fb1ec3ed-a732-470f-8328-a844bf982535","resolution":{"observed_at":"2026-07-31T23:18:25.049155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00103","last_updated":"2024-12-30T19:00:25Z","snapshot_observed_at":"2026-07-06T20:14:54.297131Z","submitted_at":"2024-12-30T19:00:25Z","title":"LTX-Video: Realtime Video Latent Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00103","snapshot_observed_at":"2026-07-31T23:18:25.051746Z","title":"LTX-Video: Realtime video latent diffusion.arXiv preprint arXiv:2501.00103, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.051746Z"},"links":{"cited_paper":"/paper/2501.00103","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:7ff457e2ea82cbec1a79a236f205951c744d7550ab5394ecb05674713efd4d49","observation_id":"acb61bc1-abb3-4e79-9b56-d43b0f4543f4","resolution":{"observed_at":"2026-07-31T23:18:25.051746Z","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":"2026-07-31T23:18:25.054335Z","title":"LTX-2.3 Model Card","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.054335Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:0967c11c35a54a92dd4bb3b9cb1c2275dadd8f909fd27f3cbc38c7c6a6afcb4c","observation_id":"832ab346-283f-429b-927e-ced71769d193","resolution":{"observed_at":"2026-07-31T23:18:25.054335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.17800","last_updated":"2026-06-16T11:25:37Z","snapshot_observed_at":"2026-07-06T23:53:21.186284Z","submitted_at":"2026-06-16T11:25:37Z","title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.17800","snapshot_observed_at":"2026-07-31T23:18:25.056705Z","title":"MaineCoon: Pursuing a real-time audio-visual social world model.arXiv preprint arXiv:2606.17800, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.056705Z"},"links":{"cited_paper":"/paper/2606.17800","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:5b750e260902231b1b9b4595c0d562cecd171eaeb3c2672d774b8acb8fde3513","observation_id":"de100b1b-32d7-4f31-953b-d86a1aa7ae46","resolution":{"observed_at":"2026-07-31T23:18:25.056705Z","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":"2026-07-31T23:18:25.059024Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.059024Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:d5e6e720440e305b4838eb2a5d9e5c78efb22e69fd34a99888edb803a0f4176a","observation_id":"2ce8c061-9569-46cd-a21b-6e5ddf743c59","resolution":{"observed_at":"2026-07-31T23:18:25.059024Z","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":"2026-07-31T23:18:25.061350Z","title":"Sparse VideoGen2: Accelerate video generation with sparse attention via semantic-aware permutation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.061350Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:c8250dce45aafb6817acbde8d7883f64e95b79e55cf3620ed1ba52578efa9327","observation_id":"4eb0677d-e64b-4ed5-9ab9-f629d79d1248","resolution":{"observed_at":"2026-07-31T23:18:25.061350Z","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":"2026-07-31T23:18:25.063422Z","title":"SpargeAttention: Accurate and training-free sparse attention accelerating any model inference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.063422Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:44545ed147bf1065bcb28edc8933c38b39568549ac01dde26538b6ad74977387","observation_id":"e2f4544a-ebb0-495a-9f92-ea7028eb54c9","resolution":{"observed_at":"2026-07-31T23:18:25.063422Z","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":"2026-07-31T23:18:25.065344Z","title":"XAttention: Block sparse attention with antidiagonal scoring","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.065344Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:2b94977e183b5ae3ad4b4bc11ad12969099c374ea91e1632060ceb7505d88dc6","observation_id":"7224edef-c8d0-4f00-93d5-35e3ddca1c17","resolution":{"observed_at":"2026-07-31T23:18:25.065344Z","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":"2026-07-31T23:18:25.067507Z","title":"PISA: Piecewise sparse attention is wiser for efficient diffusion transformers.arXiv preprint arXiv:2602.01077, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.067507Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:f01558d763ddd23fe8164df1eee622cb4e15581ff535a95274bacfba353c9fcb","observation_id":"3501a7eb-148a-4f40-814e-f423a54b239b","resolution":{"observed_at":"2026-07-31T23:18:25.067507Z","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":"2026-07-31T23:18:25.069827Z","title":"Fu, Stefano Ermon, Atri Rudra, and Christopher Ré","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.069827Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:2aea08ab2312f26cb64fe4a8f9ad619c4464a098aebb26f5a0fdfcbae9180abd","observation_id":"3533da2c-cdd0-4f28-9d02-81ecb344dc86","resolution":{"observed_at":"2026-07-31T23:18:25.069827Z","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":"2026-07-31T23:18:25.072103Z","title":"LIVEditor-14B: Lightning unified video editing via in-context sparse attention","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.072103Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:f91e5bf1686bc600f4137f067feb0c2ea2a07a60a2b23fbe8ac1c71d1a7af1f4","observation_id":"54ee9e97-2425-451d-bf08-ee12bb49ba61","resolution":{"observed_at":"2026-07-31T23:18:25.072103Z","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":"2026-07-31T23:18:25.074401Z","title":"Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.074401Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:72628e3b606aabcc09c19380b71ca67b56a2c2aaf25fcb7a9c362d384805a231","observation_id":"683926f1-9870-4be4-95bc-344ba50fae4d","resolution":{"observed_at":"2026-07-31T23:18:25.074401Z","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":"2026-07-31T23:18:25.076396Z","title":"Optimizing mixture of block attention.arXiv preprint arXiv:2511.11571, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.076396Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:f7968c171ccb1a98c73ef605cf7e21c3df0502f7e7b606091f0e7a45651f61da","observation_id":"96b84db7-c5d4-4cc2-a945-99b7e811bf8c","resolution":{"observed_at":"2026-07-31T23:18:25.076396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.22344","last_updated":"2026-05-21T11:30:29Z","snapshot_observed_at":"2026-07-06T23:32:39.761431Z","submitted_at":"2026-05-21T11:30:29Z","title":"Bernini: Latent Semantic Planning for Video Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.22344","snapshot_observed_at":"2026-07-31T23:18:25.078416Z","title":"Bernini: Latent semantic planning for video diffusion.arXiv preprint arXiv:2605.22344, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.078416Z"},"links":{"cited_paper":"/paper/2605.22344","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:c574dd95bbe4257aa70db9543d2dbba40a79198e0ab2f2cef0a72f43d4d27aa1","observation_id":"83483f21-e69b-427d-aa65-24b24fb608d6","resolution":{"observed_at":"2026-07-31T23:18:25.078416Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.15178","last_updated":"2026-05-14T17:58:03Z","snapshot_observed_at":"2026-08-01T20:39:32.341477Z","submitted_at":"2026-05-14T17:58:03Z","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.15178","snapshot_observed_at":"2026-07-31T23:18:25.080728Z","title":"SANA-WM: Efficient minute-scale world modeling with hybrid linear diffusion transformer.arXiv preprint arXiv:2605.15178, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.080728Z"},"links":{"cited_paper":"/paper/2605.15178","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:4d40e99dcc8feeacb4fdf6f912c8c54aa5b7f2da6f10c3dbc1424ac3068601c4","observation_id":"31e28a19-dbe4-4ed1-bc30-540ec11f0d91","resolution":{"observed_at":"2026-07-31T23:18:25.080728Z","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":"2026-07-31T23:18:25.083345Z","title":"Ideogram 4.https://ideogram.ai/blog/ideogram-4.0/, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.083345Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:ea7c6b301f5ffbe2d43af2fe138109ed4c41498e407a1562c6f1c6b9dc5c0355","observation_id":"8f919d37-0d40-4b0c-85db-48cad58168b7","resolution":{"observed_at":"2026-07-31T23:18:25.083345Z","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":"2026-07-31T23:18:25.085421Z","title":"VBench: Comprehensive benchmark suite for video generative models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.085421Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:87c7586cd7a0654fc495c6d6bc65f20e8862b85d20d7967e285c2e17459a07d1","observation_id":"ab2b203e-2d67-4d1c-a1f7-4efa589157a0","resolution":{"observed_at":"2026-07-31T23:18:25.085421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.28091","last_updated":"2026-06-25T07:49:03Z","snapshot_observed_at":"2026-07-06T23:37:45.223562Z","submitted_at":"2026-05-27T07:46:43Z","title":"Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.28091","snapshot_observed_at":"2026-07-31T23:18:25.087956Z","title":"Qwen-Image-Bench: From generation to creation in text-to-image evaluation.arXiv preprint arXiv:2605.28091, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.087956Z"},"links":{"cited_paper":"/paper/2605.28091","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:d54ceb7c97da0c368dd4373880eb9a963238f9a4c9fcf4724bc88edf226f5310","observation_id":"c64ac7b5-84d1-435c-8694-d160c18970d3","resolution":{"observed_at":"2026-07-31T23:18:25.087956Z","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":"2026-07-31T23:18:25.090205Z","title":"FlashAttention-3: Fast and accurate attention with asynchrony and low-precision","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.090205Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:39e19e225de9ebd067f4b077003c5124f2f941ca4e5f1008af016688f49ffea3","observation_id":"a43b9576-f702-4671-8e59-2eb181d79493","resolution":{"observed_at":"2026-07-31T23:18:25.090205Z","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":"2026-07-31T23:18:25.092176Z","title":"FlashAttention-4: Algorithm and kernel pipelining co-design for asymmetric hardware scaling.arXiv preprint arXiv:2603.05451, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.092176Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:0cce8c03b0a072a6e7e137846b4d75afd4ea4a21f68f3ccb780b0ed2b08df445","observation_id":"262c25b3-48ab-4029-922c-c7a9cb80b297","resolution":{"observed_at":"2026-07-31T23:18:25.092176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.02860","last_updated":"2025-07-03T17:59:54Z","snapshot_observed_at":"2026-07-06T21:51:52.256162Z","submitted_at":"2025-07-03T17:59:54Z","title":"Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.02860","snapshot_observed_at":"2026-07-31T23:18:25.094374Z","title":"Less is enough: Training-free video diffusion acceleration via runtime-adaptive caching.arXiv preprint arXiv:2507.02860, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.094374Z"},"links":{"cited_paper":"/paper/2507.02860","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:a6d5eecbc31e7c69744a1ccec262c74b643eb34442d12978e6d79726afec7a05","observation_id":"a4bdc148-4a71-40a0-9059-007ce0831a5c","resolution":{"observed_at":"2026-07-31T23:18:25.094374Z","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":"2026-07-31T23:18:25.096389Z","title":"Timestep embedding tells: It’s time to cache for video diffusion model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.096389Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:15ebc3f96aa9688872d9dc0c6bab03a74c2f770a05089b06eba964d405834c00","observation_id":"8519c4e9-cdec-487a-b603-07932f114f93","resolution":{"observed_at":"2026-07-31T23:18:25.096389Z","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":"2026-07-31T23:18:25.098333Z","title":"From reusing to forecasting: Accelerating diffusion models with TaylorSeers","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.098333Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:2b0199314fb0de9e4a7f974f7634d85dd2eee8df2215d81dabc2720e2d1e2085","observation_id":"eb1589cd-19d9-407f-a8ed-49bf188d7a36","resolution":{"observed_at":"2026-07-31T23:18:25.098333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.23743","last_updated":"2026-06-24T14:59:15Z","snapshot_observed_at":"2026-07-06T23:58:25.400508Z","submitted_at":"2026-06-21T17:23:20Z","title":"Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.23743","snapshot_observed_at":"2026-07-31T23:18:25.100314Z","title":"Sol video inference engine: Agent-native full-stack acceleration framework for efficient video generation.arXiv preprint arXiv:2606.23743, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.100314Z"},"links":{"cited_paper":"/paper/2606.23743","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:6407c1d96ca73008b62bc126d9997ed5f26d33c039ac76cd311a5cabd86e9ab7","observation_id":"97b2ca5d-4735-4231-858f-85bd5eb2e954","resolution":{"observed_at":"2026-07-31T23:18:25.100314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.10509","last_updated":"2019-04-23T19:29:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-04-23T19:29:47Z","title":"Generating Long Sequences with Sparse Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.10509","snapshot_observed_at":"2026-07-31T23:18:25.102673Z","title":"Generating long sequences with sparse transformers.arXiv preprint arXiv:1904.10509, 2019","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.102673Z"},"links":{"cited_paper":"/paper/1904.10509","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:8e1cc6f7af6bd0b9d59b807229bf7dbe43fa5e1a40fe32d0406d012b29039e49","observation_id":"e26f0c16-6cc2-4f51-9583-b72cd8fbf110","resolution":{"observed_at":"2026-07-31T23:18:25.102673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-07-31T23:18:25.104985Z","title":"Peters, and Arman Cohan","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.104985Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:1cd2cca4bf59785904e5441134a3d2d70fee1fbca1e09ad9279174c7bed5ed40","observation_id":"497f7ef4-ded1-4fe1-b023-75a7a179efae","resolution":{"observed_at":"2026-07-31T23:18:25.104985Z","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":"2026-07-31T23:18:25.107060Z","title":"Big bird: Transformers for longer sequences","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.107060Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:b46760f21cbf73283a7d112fe013247de4489082758886e4d7e0e98c5708d850","observation_id":"962a8905-2dbc-4fac-82de-cb36f0a2c1f5","resolution":{"observed_at":"2026-07-31T23:18:25.107060Z","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":"2026-07-31T23:18:25.108978Z","title":"Reformer: The efficient transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.108978Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:96b1f36c66077de6f675083898e37ec7fc6d291624ffe2b4ebedeac3d6b678af","observation_id":"f77cb24f-3fe2-4c50-9904-341560c67805","resolution":{"observed_at":"2026-07-31T23:18:25.108978Z","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":"2026-07-31T23:18:25.110829Z","title":"Efficient content-based sparse attention with routing transformers.Transactions of the Association for Computational Linguistics, 9:53–68, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.110829Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:7a3a4b2cca1df62c29468b0ea5827e0287937214237dc1578722768e44d662a0","observation_id":"b89c33f3-0d75-4781-8932-11456f65adef","resolution":{"observed_at":"2026-07-31T23:18:25.110829Z","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":"2026-07-31T23:18:25.112622Z","title":"SeerAttention: Self-distilled attention gating for efficient long-context prefilling","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.112622Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:c1542b095040689858be814c593773e8ba55f3af29fe4bf73343ff307a689968","observation_id":"bcd9f100-c347-4724-8917-23ff22381c18","resolution":{"observed_at":"2026-07-31T23:18:25.112622Z","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":"2026-07-31T23:18:25.114669Z","title":"Native sparse attention: Hardware-aligned and natively trainable sparse attention","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.114669Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:b03077cb7e39879e8c9c57010a8a6e2e9a5ef381685ff1f7b55310374272f6f9","observation_id":"7b341715-e828-4377-8162-bb15b3787322","resolution":{"observed_at":"2026-07-31T23:18:25.114669Z","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":"2026-07-31T23:18:25.116948Z","title":"MoBA: Mixture of block attention for long-context LLMs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.116948Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:cb8855b21162304ddbe2a59c3cb6b4bd477b4d888a990dc97e7e8347a9fbb9c2","observation_id":"7b475d8f-4a69-4a1b-9d10-5a85a8e3626a","resolution":{"observed_at":"2026-07-31T23:18:25.116948Z","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":"2026-07-31T23:18:25.118913Z","title":"Sparse video-gen: Accelerating video diffusion transformers with spatial-temporal sparsity","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.118913Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:e7b735855a7138c2a3039b54d7a88b10f3623d98ffc3567e96a3ae97bcd129a8","observation_id":"bcb66a47-6d8e-40fd-b8ac-4e69ba8fef5f","resolution":{"observed_at":"2026-07-31T23:18:25.118913Z","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":"2026-07-31T23:18:25.121332Z","title":"Radial attention:𝒪(𝑛log𝑛)sparse attention with energy decay for long video generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.121332Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:f4ffeccfbfb3661cb97f2599a9f0cc29bf02e87e975b5ac44a476b93c2d32196","observation_id":"d42b402b-cbb8-405d-9b4d-a3c00cc5d0ae","resolution":{"observed_at":"2026-07-31T23:18:25.121332Z","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":"2026-07-31T23:18:25.123340Z","title":"Fast video generation with sliding tile attention","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.123340Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:06b944719cc3372fe6128e1fabda62a16fa32b8953c70997e3bbe2eafcae1286","observation_id":"d9470a0a-e4ec-49a1-a963-489726405f4d","resolution":{"observed_at":"2026-07-31T23:18:25.123340Z","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":"2026-07-31T23:18:25.125454Z","title":"Sparse-vDiT: Unleashing the power of sparse attention to accelerate video diffusion transformers","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.125454Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:b152e6adafef5a83d436823248d6af896a7268643aa471c17e86140ec50d4ef1","observation_id":"b516180d-5f5e-4fd3-a58c-c9c2fd40664f","resolution":{"observed_at":"2026-07-31T23:18:25.125454Z","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":"2026-07-31T23:18:25.127847Z","title":"Xing, and Hao Zhang","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.127847Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:08a5ade0448936440339d07ea7bb0edfdf14586dee242e86108380382c7286c1","observation_id":"d9020c76-95b3-44bf-a946-9b7ae024d817","resolution":{"observed_at":"2026-07-31T23:18:25.127847Z","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":"2026-07-31T23:18:25.130080Z","title":"DFSAttn: Dynamic fine-grained sparse attention for efficient video generation","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.130080Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:aa592e879e021b2c146e57ad92dc05b7b412647f6da80eba316d012cdc9f0418","observation_id":"8161ade0-ec56-4605-8d72-05134b2dc158","resolution":{"observed_at":"2026-07-31T23:18:25.130080Z","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":"2026-07-31T23:18:25.131959Z","title":"FPSAttention: Training-aware FP8 and sparsity co-design for fast video diffusion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.131959Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:5317370fd923f28b209f2468bc0781ae9a2c148019e96f355431222a6d150320","observation_id":"af357fef-8760-4890-8a37-aa28196bbf83","resolution":{"observed_at":"2026-07-31T23:18:25.131959Z","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":"2026-07-31T23:18:25.133988Z","title":"SpargeAttention2: Trainable sparse attention via hybrid top-𝑘+top-𝑝 masking and distillation fine-tuning.arXiv preprint arXiv:2602.13515, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.133988Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:11cced6c7e3d10823346cfd6d9a2c47f77810d11423bb909d5b92a3d193b51e8","observation_id":"7a0825ac-0098-42e4-ac79-0a74c00c5f2a","resolution":{"observed_at":"2026-07-31T23:18:25.133988Z","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":"2026-07-31T23:18:25.136021Z","title":"Twilight: Adaptive attention sparsity with hierarchical top-𝑝 pruning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.136021Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:b32c2bbf397416a19c2a43c9f3aa924719542924b0165bad94c64759cfd8b435","observation_id":"8b9325c0-87f4-4556-9b21-f4ab4820ab4d","resolution":{"observed_at":"2026-07-31T23:18:25.136021Z","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":"2026-07-31T23:18:25.137951Z","title":"VecAttention: Vector- wise sparse attention for accelerating long context inference","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.137951Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:ac037229053f9660fb3580967fc736d1ebb52e965bbdbf51d161fb8a9beaf293","observation_id":"8b35a45f-0f7c-48f5-878c-567b3cc2581f","resolution":{"observed_at":"2026-07-31T23:18:25.137951Z","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":"2026-07-31T23:18:25.140412Z","title":"QUEST: Query-aware sparsity for efficient long-context LLM inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.140412Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:b80e3de0c9ab4e42ffb54983e88c202fecde13e01a4e4994fb1b65b3379b679f","observation_id":"14a6b053-c9f2-4a87-a878-fd2d63dd0b97","resolution":{"observed_at":"2026-07-31T23:18:25.140412Z","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":"2026-07-31T23:18:25.142801Z","title":"A training-free sub-quadratic cost transformer model serving framework with hierarchically pruned attention","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.142801Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:f3ea89df4303e7ea21bf12efe59998bc3b57da950de1546a9c2cc5217362e60c","observation_id":"76f3cee2-d2bc-416b-a272-f743ca1f91df","resolution":{"observed_at":"2026-07-31T23:18:25.142801Z","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":"2026-07-31T23:18:25.144814Z","title":"FlexPrefill: A context-aware sparse attention mechanism for efficient long-sequence inference","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.144814Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:607db164b5803d5c9bccb2486b06959cb7fd16f888deb66a9189cc685e73e1f7","observation_id":"559a0cb8-5967-4956-958b-9cfa9b633298","resolution":{"observed_at":"2026-07-31T23:18:25.144814Z","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":"2026-07-31T23:18:25.146747Z","title":"Gonzalez, and Ion Stoica","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.146747Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:d8265575a68d0718890639e0cbfb19c8142f764bcb1bd5498c7739d2a56f40b9","observation_id":"2d8d46fd-fc07-48c8-8ada-297bd02b9f7d","resolution":{"observed_at":"2026-07-31T23:18:25.146747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.08982","last_updated":"2026-07-05T04:50:20Z","snapshot_observed_at":"2026-08-04T11:23:37.451573Z","submitted_at":"2026-03-09T22:15:31Z","title":"SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.08982","snapshot_observed_at":"2026-07-31T23:18:25.148667Z","title":"Gonzalez, Kurt Keutzer, Ion Stoica, and Alvin Cheung","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.148667Z"},"links":{"cited_paper":"/paper/2603.08982","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:ecfdb29854ebbd636d550dad28f1d6c36df3397f1a064f213abb1c6bade88de3","observation_id":"84761b5d-e111-49ee-818d-b2ec4c12a083","resolution":{"observed_at":"2026-07-31T23:18:25.148667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.19726","last_updated":"2026-05-19T12:01:13Z","snapshot_observed_at":"2026-08-01T08:38:35.585519Z","submitted_at":"2026-05-19T12:01:13Z","title":"Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.19726","snapshot_observed_at":"2026-07-31T23:18:25.150782Z","title":"Efficient long-context modeling in diffusion language models via block approximate sparse attention.arXiv preprint arXiv:2605.19726, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.150782Z"},"links":{"cited_paper":"/paper/2605.19726","citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:de22fd0caebd58f5a09177bc5f20631e8a76bfb68053fa14186c856c88124561","observation_id":"3caa674b-9cd1-41ee-a30d-f8a9d2f4623b","resolution":{"observed_at":"2026-07-31T23:18:25.150782Z","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":"2026-07-31T23:18:25.152788Z","title":"Gonzalez, Jianfei Chen, and Jun Zhu","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.152788Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:d18b52785ce95a84804ede40271a1d5fe768947933726394f9adb46eab5cc74e","observation_id":"e8f91928-27e3-48e5-8b75-baf199657299","resolution":{"observed_at":"2026-07-31T23:18:25.152788Z","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":"2026-07-31T23:18:25.154970Z","title":"Gonzalez","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-31T23:18:25.154970Z"},"links":{"citing_paper":"/paper/2607.24027"},"observation_digest":"sha256:78db07d0110c8c342a3af86d2520cc7abd83378b4c37fbcf0e251e0ae7b2c642","observation_id":"86fc9978-6cf5-435d-9268-b962eb144bb0","resolution":{"observed_at":"2026-07-31T23:18:25.154970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.24027","last_updated":"2026-07-27T05:53:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-31T23:18:23.831798Z","submitted_at":"2026-07-27T05:53:28Z","title":"Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":52},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2607.24027."}