{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AYDQYSLE3GHV5HRY446UTHLF6B","short_pith_number":"pith:AYDQYSLE","schema_version":"1.0","canonical_sha256":"06070c4964d98f5e9e38e73d499d65f065a4658a8a89ea972c96efa164d6a9b1","source":{"kind":"arxiv","id":"2412.10494","version":2},"attestation_state":"computed","paper":{"title":"SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.CV","authors_text":"Aleksei Lebedev, Anil Kag, Dimitris Metaxas, Huseyin Coskun, Jian Ren, Ju Hu, Ke Ma, Sergey Tulyakov, Yang Sui, Yanwu Xu, Yanyu Li, Yanzhi Wang, Yushu Wu, Zhixing Zhang","submitted_at":"2024-12-13T18:59:56Z","abstract_excerpt":"We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate cinematic and high-resolution videos with smooth motions from arbitrary input prompts. However, as a supertask of image generation, video generation models require more computation and are thus hosted mostly on cloud servers, limiting broader adoption among content creators. In this work, we propose a comprehensive acceleration framework to bring the power of the large-scale video diffusion model to the hands of edge "},"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":"2412.10494","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:59:56Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"title_canon_sha256":"8b37523c753fcc113d52e44a8d40ca9e6977397aa0975539c3d4a26c575d52b7","abstract_canon_sha256":"110feeff73f30689a2ef20f75f20811dcd1fb2468037e18228d88c2c36b6228f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:40.853206Z","signature_b64":"awgKWZbErPAQkbEXrbnkVdAf++l9VQzPsh1jP2wRNrY0qgsJncyfEYoqfQTULoygiancwRLdxrH+FdM709guBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06070c4964d98f5e9e38e73d499d65f065a4658a8a89ea972c96efa164d6a9b1","last_reissued_at":"2026-07-05T11:18:40.852713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:40.852713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.CV","authors_text":"Aleksei Lebedev, Anil Kag, Dimitris Metaxas, Huseyin Coskun, Jian Ren, Ju Hu, Ke Ma, Sergey Tulyakov, Yang Sui, Yanwu Xu, Yanyu Li, Yanzhi Wang, Yushu Wu, Zhixing Zhang","submitted_at":"2024-12-13T18:59:56Z","abstract_excerpt":"We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate cinematic and high-resolution videos with smooth motions from arbitrary input prompts. However, as a supertask of image generation, video generation models require more computation and are thus hosted mostly on cloud servers, limiting broader adoption among content creators. In this work, we propose a comprehensive acceleration framework to bring the power of the large-scale video diffusion model to the hands of edge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10494","kind":"arxiv","version":2},"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/2412.10494/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":"2412.10494","created_at":"2026-07-05T11:18:40.852769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10494v2","created_at":"2026-07-05T11:18:40.852769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10494","created_at":"2026-07-05T11:18:40.852769+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYDQYSLE3GHV","created_at":"2026-07-05T11:18:40.852769+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYDQYSLE3GHV5HRY","created_at":"2026-07-05T11:18:40.852769+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYDQYSLE","created_at":"2026-07-05T11:18:40.852769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04363","citing_title":"On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B","json":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B.json","graph_json":"https://pith.science/api/pith-number/AYDQYSLE3GHV5HRY446UTHLF6B/graph.json","events_json":"https://pith.science/api/pith-number/AYDQYSLE3GHV5HRY446UTHLF6B/events.json","paper":"https://pith.science/paper/AYDQYSLE"},"agent_actions":{"view_html":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B","download_json":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B.json","view_paper":"https://pith.science/paper/AYDQYSLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10494&json=true","fetch_graph":"https://pith.science/api/pith-number/AYDQYSLE3GHV5HRY446UTHLF6B/graph.json","fetch_events":"https://pith.science/api/pith-number/AYDQYSLE3GHV5HRY446UTHLF6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B/action/storage_attestation","attest_author":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B/action/author_attestation","sign_citation":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B/action/citation_signature","submit_replication":"https://pith.science/pith/AYDQYSLE3GHV5HRY446UTHLF6B/action/replication_record"}},"created_at":"2026-07-05T11:18:40.852769+00:00","updated_at":"2026-07-05T11:18:40.852769+00:00"}