{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WAE23BSP5USYRRORFNQNWPRVC2","short_pith_number":"pith:WAE23BSP","schema_version":"1.0","canonical_sha256":"b009ad864fed2588c5d12b60db3e35168a0702efc56c07632274c4c69af4d088","source":{"kind":"arxiv","id":"2607.21553","version":1},"attestation_state":"computed","paper":{"title":"SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Enze Xie, Haozhe Liu, Jincheng Yu, Jingyu Xin, Junsong Chen, Ping Luo, Shuchen Xue, Song Han, Tian Ye, Yitong Li, Yuyang Zhao, Zhangjie Wu, Zian Wang","submitted_at":"2026-07-23T17:36:05Z","abstract_excerpt":"We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified architecture. Designed to generate high-quality video up to 720p on a single GPU, SANA-Video 2.0 matches full-softmax video DiTs in quality while retaining the favorable long-sequence scaling of linear attention. To avoid quadratic attention throughout, Hybrid Linear-Softmax Attention combines gated linear attention for O(N)-dominated mixing with periodic gated-softmax anchors at a 3:1 ratio, restoring the full-rank token interactions that pure linear attention lacks. To propagat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.21553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T17:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"c1391f89664cb59434c3aba21db7d8ef3e016ac7afbddba0687824b7a672d0a1","abstract_canon_sha256":"dca61fafb76d479c7b628952e920f3479092607fa47a0306ae19d09963245106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:39.294039Z","signature_b64":"xqYe44fx3RfJa/4uFs65xkfHmgKyE8Bv6EwdlZQyfTW1o5F5uOqvzRhTKN774kChDP5VO7zOOMC0erICnTMSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b009ad864fed2588c5d12b60db3e35168a0702efc56c07632274c4c69af4d088","last_reissued_at":"2026-07-24T01:24:39.293207Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:39.293207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Enze Xie, Haozhe Liu, Jincheng Yu, Jingyu Xin, Junsong Chen, Ping Luo, Shuchen Xue, Song Han, Tian Ye, Yitong Li, Yuyang Zhao, Zhangjie Wu, Zian Wang","submitted_at":"2026-07-23T17:36:05Z","abstract_excerpt":"We introduce SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified architecture. Designed to generate high-quality video up to 720p on a single GPU, SANA-Video 2.0 matches full-softmax video DiTs in quality while retaining the favorable long-sequence scaling of linear attention. To avoid quadratic attention throughout, Hybrid Linear-Softmax Attention combines gated linear attention for O(N)-dominated mixing with periodic gated-softmax anchors at a 3:1 ratio, restoring the full-rank token interactions that pure linear attention lacks. To propagat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21553","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.21553/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.21553","created_at":"2026-07-24T01:24:39.293636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21553v1","created_at":"2026-07-24T01:24:39.293636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21553","created_at":"2026-07-24T01:24:39.293636+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAE23BSP5USY","created_at":"2026-07-24T01:24:39.293636+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAE23BSP5USYRROR","created_at":"2026-07-24T01:24:39.293636+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAE23BSP","created_at":"2026-07-24T01:24:39.293636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2","json":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2.json","graph_json":"https://pith.science/api/pith-number/WAE23BSP5USYRRORFNQNWPRVC2/graph.json","events_json":"https://pith.science/api/pith-number/WAE23BSP5USYRRORFNQNWPRVC2/events.json","paper":"https://pith.science/paper/WAE23BSP"},"agent_actions":{"view_html":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2","download_json":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2.json","view_paper":"https://pith.science/paper/WAE23BSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21553&json=true","fetch_graph":"https://pith.science/api/pith-number/WAE23BSP5USYRRORFNQNWPRVC2/graph.json","fetch_events":"https://pith.science/api/pith-number/WAE23BSP5USYRRORFNQNWPRVC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2/action/storage_attestation","attest_author":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2/action/author_attestation","sign_citation":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2/action/citation_signature","submit_replication":"https://pith.science/pith/WAE23BSP5USYRRORFNQNWPRVC2/action/replication_record"}},"created_at":"2026-07-24T01:24:39.293636+00:00","updated_at":"2026-07-24T01:24:39.293636+00:00"}