{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J6VTFWMYR37ZTCC6PT6GK4RIBE","short_pith_number":"pith:J6VTFWMY","schema_version":"1.0","canonical_sha256":"4fab32d9988eff99885e7cfc65722809389ba71acc0a0ac3613af02dcb90cebd","source":{"kind":"arxiv","id":"2503.10634","version":2},"attestation_state":"computed","paper":{"title":"V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jipeng Lyu, Jun-Kun Chen, Yanming Zhang, Yu-Xiong Wang","submitted_at":"2025-03-13T17:59:55Z","abstract_excerpt":"This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach employs a progressive strategy that decomposes complex editing tasks into a sequence of simpler subtasks. Each subtask is controlled through three key synergistic mechanisms: the initial noise, noise added at each denoising step, and cross-attention maps between text prompts and video content. This ensures robust preservation of original video elements while ef"},"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":"2503.10634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"064a75ca473ff620d50b6f98ef38475f28c098258d1ef8a49541dc9cc8694718","abstract_canon_sha256":"de2581c98bce14087f6af56a3dbf0d3e5ab1eb48aba8f148271a73ce0bfdb1e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:57.252584Z","signature_b64":"zGqUi4aI3W2WRRjyDSY1XzkeBmQNN4odHB5ioP/+WfZ1oR9egtQo4w+Qeicw1HjvIAS8/2xKRxZy+mi/J9qaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fab32d9988eff99885e7cfc65722809389ba71acc0a0ac3613af02dcb90cebd","last_reissued_at":"2026-07-05T10:31:57.251665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:57.251665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jipeng Lyu, Jun-Kun Chen, Yanming Zhang, Yu-Xiong Wang","submitted_at":"2025-03-13T17:59:55Z","abstract_excerpt":"This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach employs a progressive strategy that decomposes complex editing tasks into a sequence of simpler subtasks. Each subtask is controlled through three key synergistic mechanisms: the initial noise, noise added at each denoising step, and cross-attention maps between text prompts and video content. This ensures robust preservation of original video elements while ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10634","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/2503.10634/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":"2503.10634","created_at":"2026-07-05T10:31:57.251779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10634v2","created_at":"2026-07-05T10:31:57.251779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10634","created_at":"2026-07-05T10:31:57.251779+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6VTFWMYR37Z","created_at":"2026-07-05T10:31:57.251779+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6VTFWMYR37ZTCC6","created_at":"2026-07-05T10:31:57.251779+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6VTFWMY","created_at":"2026-07-05T10:31:57.251779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06555","citing_title":"ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation","ref_index":149,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15533","citing_title":"Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE","json":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE.json","graph_json":"https://pith.science/api/pith-number/J6VTFWMYR37ZTCC6PT6GK4RIBE/graph.json","events_json":"https://pith.science/api/pith-number/J6VTFWMYR37ZTCC6PT6GK4RIBE/events.json","paper":"https://pith.science/paper/J6VTFWMY"},"agent_actions":{"view_html":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE","download_json":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE.json","view_paper":"https://pith.science/paper/J6VTFWMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10634&json=true","fetch_graph":"https://pith.science/api/pith-number/J6VTFWMYR37ZTCC6PT6GK4RIBE/graph.json","fetch_events":"https://pith.science/api/pith-number/J6VTFWMYR37ZTCC6PT6GK4RIBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE/action/storage_attestation","attest_author":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE/action/author_attestation","sign_citation":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE/action/citation_signature","submit_replication":"https://pith.science/pith/J6VTFWMYR37ZTCC6PT6GK4RIBE/action/replication_record"}},"created_at":"2026-07-05T10:31:57.251779+00:00","updated_at":"2026-07-05T10:31:57.251779+00:00"}