{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MWYG777MNFHNAXBTTYGLXZDVFY","short_pith_number":"pith:MWYG777M","schema_version":"1.0","canonical_sha256":"65b06fffec694ed05c339e0cbbe4752e32cc9ae913e0a0ec209a71b4708f5f91","source":{"kind":"arxiv","id":"2506.01801","version":1},"attestation_state":"computed","paper":{"title":"OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongmei Wang, Qinglin Lu, Qin Lin, Sen Liang, Teng Hu, Xin Li, Yi Chen, Yuan Zhou, Zhengguang Zhou, Zhentao Yu, Zhibo Chen","submitted_at":"2025-06-02T15:42:06Z","abstract_excerpt":"The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generation is widely applied in various fields, most existing models are limited to single scenarios and cannot perform diverse video generation and editing through dynamic content manipulation. We propose OmniV2V, a video model capable of generating and editing videos across different scenarios based on various operations, including: object movement, object addition, mask-guided video edit, try-on, inpainting, outpainting,"},"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":"2506.01801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T15:42:06Z","cross_cats_sorted":[],"title_canon_sha256":"5eb0e7e04ac2a5e19af7db1a8b8884d89824a251654d77bb4afdf85ce81ace5f","abstract_canon_sha256":"be942d28f3ebb41d7946074533b0de31641e7c78279e3c238ad639419f57dcc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:19.650522Z","signature_b64":"fWf37GtHyH3OtQK1UZF8Sowbaj1QLjUsjtf1w8x1KqVFHLH2Z8fCEiCABMxQcivhCHfipBudf5OiPeOyLpmkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65b06fffec694ed05c339e0cbbe4752e32cc9ae913e0a0ec209a71b4708f5f91","last_reissued_at":"2026-07-05T11:14:19.650079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:19.650079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongmei Wang, Qinglin Lu, Qin Lin, Sen Liang, Teng Hu, Xin Li, Yi Chen, Yuan Zhou, Zhengguang Zhou, Zhentao Yu, Zhibo Chen","submitted_at":"2025-06-02T15:42:06Z","abstract_excerpt":"The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generation is widely applied in various fields, most existing models are limited to single scenarios and cannot perform diverse video generation and editing through dynamic content manipulation. We propose OmniV2V, a video model capable of generating and editing videos across different scenarios based on various operations, including: object movement, object addition, mask-guided video edit, try-on, inpainting, outpainting,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01801","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/2506.01801/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":"2506.01801","created_at":"2026-07-05T11:14:19.650130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01801v1","created_at":"2026-07-05T11:14:19.650130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01801","created_at":"2026-07-05T11:14:19.650130+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWYG777MNFHN","created_at":"2026-07-05T11:14:19.650130+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWYG777MNFHNAXBT","created_at":"2026-07-05T11:14:19.650130+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWYG777M","created_at":"2026-07-05T11:14:19.650130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30599","citing_title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25193","citing_title":"SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30599","citing_title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08646","citing_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":275,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY","json":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY.json","graph_json":"https://pith.science/api/pith-number/MWYG777MNFHNAXBTTYGLXZDVFY/graph.json","events_json":"https://pith.science/api/pith-number/MWYG777MNFHNAXBTTYGLXZDVFY/events.json","paper":"https://pith.science/paper/MWYG777M"},"agent_actions":{"view_html":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY","download_json":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY.json","view_paper":"https://pith.science/paper/MWYG777M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01801&json=true","fetch_graph":"https://pith.science/api/pith-number/MWYG777MNFHNAXBTTYGLXZDVFY/graph.json","fetch_events":"https://pith.science/api/pith-number/MWYG777MNFHNAXBTTYGLXZDVFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY/action/storage_attestation","attest_author":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY/action/author_attestation","sign_citation":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY/action/citation_signature","submit_replication":"https://pith.science/pith/MWYG777MNFHNAXBTTYGLXZDVFY/action/replication_record"}},"created_at":"2026-07-05T11:14:19.650130+00:00","updated_at":"2026-07-05T11:14:19.650130+00:00"}