{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O26RZXDDQCG4RFDYPAM3SZLIR6","short_pith_number":"pith:O26RZXDD","schema_version":"1.0","canonical_sha256":"76bd1cdc63808dc894787819b965688f908e47627ee64223ab9e678ac18fd01b","source":{"kind":"arxiv","id":"2505.19151","version":1},"attestation_state":"computed","paper":{"title":"SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Bujiao Chen, Jiangsu Du, Lansong Diao, Lianghua Huang, Shenggan Cheng, Wei Lin, Wenyuan Yu, Yang You, Yong Liu, Yuanxin Wei, Yu Liu","submitted_at":"2025-05-25T13:58:52Z","abstract_excerpt":"Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video generation remains computationally intensive, especially for high-resolution, long-duration videos. Prior work accelerates its inference by skipping computation, usually at the cost of severe quality degradation. In this paper, we propose SRDiffusion, a novel framework that leverages collaboration between large and small models to reduce inference cost. The large mo"},"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":"2505.19151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2025-05-25T13:58:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c933981c5ce64ed60d30022a97a8397f71f3942c58ff57195d6d0f034c583a27","abstract_canon_sha256":"31b3ea611313841288501188914e78f511fe9ff4a0decddfe8582148d2bc1aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:25.700952Z","signature_b64":"nWnRItWZgeW/TxcPYfN3JdXSKTD069MtwKhO7/6zFS9JOzd7SZZjfIQvFvgZ1NBt9WFvCSWotgzxVRCxYHvoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76bd1cdc63808dc894787819b965688f908e47627ee64223ab9e678ac18fd01b","last_reissued_at":"2026-07-05T11:09:25.700454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:25.700454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Bujiao Chen, Jiangsu Du, Lansong Diao, Lianghua Huang, Shenggan Cheng, Wei Lin, Wenyuan Yu, Yang You, Yong Liu, Yuanxin Wei, Yu Liu","submitted_at":"2025-05-25T13:58:52Z","abstract_excerpt":"Leveraging the diffusion transformer (DiT) architecture, models like Sora, CogVideoX and Wan have achieved remarkable progress in text-to-video, image-to-video, and video editing tasks. Despite these advances, diffusion-based video generation remains computationally intensive, especially for high-resolution, long-duration videos. Prior work accelerates its inference by skipping computation, usually at the cost of severe quality degradation. In this paper, we propose SRDiffusion, a novel framework that leverages collaboration between large and small models to reduce inference cost. The large mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19151","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/2505.19151/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":"2505.19151","created_at":"2026-07-05T11:09:25.700508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19151v1","created_at":"2026-07-05T11:09:25.700508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19151","created_at":"2026-07-05T11:09:25.700508+00:00"},{"alias_kind":"pith_short_12","alias_value":"O26RZXDDQCG4","created_at":"2026-07-05T11:09:25.700508+00:00"},{"alias_kind":"pith_short_16","alias_value":"O26RZXDDQCG4RFDY","created_at":"2026-07-05T11:09:25.700508+00:00"},{"alias_kind":"pith_short_8","alias_value":"O26RZXDD","created_at":"2026-07-05T11:09:25.700508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30557","citing_title":"EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":243,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17397","citing_title":"Speculative Decoding for Autoregressive Video Generation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6","json":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6.json","graph_json":"https://pith.science/api/pith-number/O26RZXDDQCG4RFDYPAM3SZLIR6/graph.json","events_json":"https://pith.science/api/pith-number/O26RZXDDQCG4RFDYPAM3SZLIR6/events.json","paper":"https://pith.science/paper/O26RZXDD"},"agent_actions":{"view_html":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6","download_json":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6.json","view_paper":"https://pith.science/paper/O26RZXDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19151&json=true","fetch_graph":"https://pith.science/api/pith-number/O26RZXDDQCG4RFDYPAM3SZLIR6/graph.json","fetch_events":"https://pith.science/api/pith-number/O26RZXDDQCG4RFDYPAM3SZLIR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6/action/storage_attestation","attest_author":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6/action/author_attestation","sign_citation":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6/action/citation_signature","submit_replication":"https://pith.science/pith/O26RZXDDQCG4RFDYPAM3SZLIR6/action/replication_record"}},"created_at":"2026-07-05T11:09:25.700508+00:00","updated_at":"2026-07-05T11:09:25.700508+00:00"}