{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EG663Y3J4TP7SIPFALSHJBXOYZ","short_pith_number":"pith:EG663Y3J","schema_version":"1.0","canonical_sha256":"21bdede369e4dff921e502e47486eec65a02db458d745d34a881bd2a1455f272","source":{"kind":"arxiv","id":"2506.04216","version":1},"attestation_state":"computed","paper":{"title":"UNIC: Unified In-Context Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Kun Gai, Pengfei Wan, Qifeng Chen, Qiulin Wang, Quande Liu, Wenhan Luo, Xintao Wang, Xuanhua He, Zixuan Ye","submitted_at":"2025-06-04T17:57:43Z","abstract_excerpt":"Recent advances in text-to-video generation have sparked interest in generative video editing tasks. Previous methods often rely on task-specific architectures (e.g., additional adapter modules) or dedicated customizations (e.g., DDIM inversion), which limit the integration of versatile editing conditions and the unification of various editing tasks. In this paper, we introduce UNified In-Context Video Editing (UNIC), a simple yet effective framework that unifies diverse video editing tasks within a single model in an in-context manner. To achieve this unification, we represent the inputs of v"},"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":"2506.04216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"c038aacae7d2a3c9ec19f757496f99fc4f19fb87301cb60b90b5d94a2530d138","abstract_canon_sha256":"ee22145e21e8437845f241f0937487ae0ab64f642d63d92bcc74db9b89285b22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:59.095906Z","signature_b64":"fZQulG4lPpKgid4WD9f4vWGl2p4iKyv8kabJ1GbDTdGhHNV42eaTxEowWNRLRXQxHoBP75u7q8ennPyELOEfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21bdede369e4dff921e502e47486eec65a02db458d745d34a881bd2a1455f272","last_reissued_at":"2026-07-05T11:15:59.095366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:59.095366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNIC: Unified In-Context Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Kun Gai, Pengfei Wan, Qifeng Chen, Qiulin Wang, Quande Liu, Wenhan Luo, Xintao Wang, Xuanhua He, Zixuan Ye","submitted_at":"2025-06-04T17:57:43Z","abstract_excerpt":"Recent advances in text-to-video generation have sparked interest in generative video editing tasks. Previous methods often rely on task-specific architectures (e.g., additional adapter modules) or dedicated customizations (e.g., DDIM inversion), which limit the integration of versatile editing conditions and the unification of various editing tasks. In this paper, we introduce UNified In-Context Video Editing (UNIC), a simple yet effective framework that unifies diverse video editing tasks within a single model in an in-context manner. To achieve this unification, we represent the inputs of v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04216","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/2506.04216/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":"2506.04216","created_at":"2026-07-05T11:15:59.095438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04216v1","created_at":"2026-07-05T11:15:59.095438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04216","created_at":"2026-07-05T11:15:59.095438+00:00"},{"alias_kind":"pith_short_12","alias_value":"EG663Y3J4TP7","created_at":"2026-07-05T11:15:59.095438+00:00"},{"alias_kind":"pith_short_16","alias_value":"EG663Y3J4TP7SIPF","created_at":"2026-07-05T11:15:59.095438+00:00"},{"alias_kind":"pith_short_8","alias_value":"EG663Y3J","created_at":"2026-07-05T11:15:59.095438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24225","citing_title":"Geometry-Instructed Video Editing","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26740","citing_title":"LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01677","citing_title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07326","citing_title":"AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01362","citing_title":"AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12271","citing_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23891","citing_title":"Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12271","citing_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":208,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06010","citing_title":"OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ","json":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ.json","graph_json":"https://pith.science/api/pith-number/EG663Y3J4TP7SIPFALSHJBXOYZ/graph.json","events_json":"https://pith.science/api/pith-number/EG663Y3J4TP7SIPFALSHJBXOYZ/events.json","paper":"https://pith.science/paper/EG663Y3J"},"agent_actions":{"view_html":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ","download_json":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ.json","view_paper":"https://pith.science/paper/EG663Y3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04216&json=true","fetch_graph":"https://pith.science/api/pith-number/EG663Y3J4TP7SIPFALSHJBXOYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EG663Y3J4TP7SIPFALSHJBXOYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ/action/storage_attestation","attest_author":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ/action/author_attestation","sign_citation":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ/action/citation_signature","submit_replication":"https://pith.science/pith/EG663Y3J4TP7SIPFALSHJBXOYZ/action/replication_record"}},"created_at":"2026-07-05T11:15:59.095438+00:00","updated_at":"2026-07-05T11:15:59.095438+00:00"}