{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S4AOVWTMK54JZFK67IMIPIMWPU","short_pith_number":"pith:S4AOVWTM","schema_version":"1.0","canonical_sha256":"9700eada6c57789c955efa1887a1967d2281a032b71d3e7f805e6fa6feca953a","source":{"kind":"arxiv","id":"2306.07954","version":2},"attestation_state":"computed","paper":{"title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Shuai Yang, Yifan Zhou, Ziwei Liu","submitted_at":"2023-06-13T17:52:23Z","abstract_excerpt":"Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes"},"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":"2306.07954","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T17:52:23Z","cross_cats_sorted":[],"title_canon_sha256":"f86e6fadf59ba66d8914d9d296cc9540c1777b071239bb2894546a041eff848b","abstract_canon_sha256":"1e74e1038277b400516a653a0a3687d458bd60f96da4f93e09daaba6fb92748b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:26.402444Z","signature_b64":"mQs0Ecms/dG7HgriL+V62i1GhrC8VBQmjZgpcWoE5+r8qEH4XoGLV8I/5xepBA/2PwdSk5Xp9toH9FBS5iGbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9700eada6c57789c955efa1887a1967d2281a032b71d3e7f805e6fa6feca953a","last_reissued_at":"2026-07-05T06:51:26.401941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:26.401941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Shuai Yang, Yifan Zhou, Ziwei Liu","submitted_at":"2023-06-13T17:52:23Z","abstract_excerpt":"Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07954","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/2306.07954/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":"2306.07954","created_at":"2026-07-05T06:51:26.402001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07954v2","created_at":"2026-07-05T06:51:26.402001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07954","created_at":"2026-07-05T06:51:26.402001+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4AOVWTMK54J","created_at":"2026-07-05T06:51:26.402001+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4AOVWTMK54JZFK6","created_at":"2026-07-05T06:51:26.402001+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4AOVWTM","created_at":"2026-07-05T06:51:26.402001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":219,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU","json":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU.json","graph_json":"https://pith.science/api/pith-number/S4AOVWTMK54JZFK67IMIPIMWPU/graph.json","events_json":"https://pith.science/api/pith-number/S4AOVWTMK54JZFK67IMIPIMWPU/events.json","paper":"https://pith.science/paper/S4AOVWTM"},"agent_actions":{"view_html":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU","download_json":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU.json","view_paper":"https://pith.science/paper/S4AOVWTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07954&json=true","fetch_graph":"https://pith.science/api/pith-number/S4AOVWTMK54JZFK67IMIPIMWPU/graph.json","fetch_events":"https://pith.science/api/pith-number/S4AOVWTMK54JZFK67IMIPIMWPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU/action/storage_attestation","attest_author":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU/action/author_attestation","sign_citation":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU/action/citation_signature","submit_replication":"https://pith.science/pith/S4AOVWTMK54JZFK67IMIPIMWPU/action/replication_record"}},"created_at":"2026-07-05T06:51:26.402001+00:00","updated_at":"2026-07-05T06:51:26.402001+00:00"}