{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EOT6FJF3JAPN65FBSN7H4WUFCI","short_pith_number":"pith:EOT6FJF3","schema_version":"1.0","canonical_sha256":"23a7e2a4bb481edf74a1937e7e5a85120571b156c479f89d79bf62a93e844cdc","source":{"kind":"arxiv","id":"2306.08707","version":4},"attestation_state":"computed","paper":{"title":"VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Jean-Emmanuel Haugeard, Nicolas Thome, Paul Couairon","submitted_at":"2023-06-14T19:15:49Z","abstract_excerpt":"Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, existing diffusion-based video editing approaches lack the ability to offer precise control over generated content that maintains temporal consistency in long-term videos. On the other hand, atlas-based methods provide strong temporal consistency but are costly to edit a video and lack spatial control. In this work, we introduce VidEdit, a novel method for zero-shot text-based video editing that guarantees robust temporal and spatial consistency. In particular, we combine an "},"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":"2306.08707","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-14T19:15:49Z","cross_cats_sorted":[],"title_canon_sha256":"acc329852a6353c50a6f1c41b8e8a55141d8504b72666d3245cca424321eab8b","abstract_canon_sha256":"c917e350607aca8df5a5d4151dafaada65b9be7cac3cab91ea4e1d24340dfbfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:25.929944Z","signature_b64":"b5qN2nEpDN9BETeNluW3C9g+zrr2c/NF+AVX/AVTim2i3tD04AXGcz4J6pWHDf+uwMkE6ogdc2jcr0iP/7xoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a7e2a4bb481edf74a1937e7e5a85120571b156c479f89d79bf62a93e844cdc","last_reissued_at":"2026-07-05T08:03:25.929479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:25.929479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cl\\'ement Rambour, Jean-Emmanuel Haugeard, Nicolas Thome, Paul Couairon","submitted_at":"2023-06-14T19:15:49Z","abstract_excerpt":"Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, existing diffusion-based video editing approaches lack the ability to offer precise control over generated content that maintains temporal consistency in long-term videos. On the other hand, atlas-based methods provide strong temporal consistency but are costly to edit a video and lack spatial control. In this work, we introduce VidEdit, a novel method for zero-shot text-based video editing that guarantees robust temporal and spatial consistency. In particular, we combine an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08707","kind":"arxiv","version":4},"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/2306.08707/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":"2306.08707","created_at":"2026-07-05T08:03:25.929531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08707v4","created_at":"2026-07-05T08:03:25.929531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08707","created_at":"2026-07-05T08:03:25.929531+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOT6FJF3JAPN","created_at":"2026-07-05T08:03:25.929531+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOT6FJF3JAPN65FB","created_at":"2026-07-05T08:03:25.929531+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOT6FJF3","created_at":"2026-07-05T08:03:25.929531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI","json":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI.json","graph_json":"https://pith.science/api/pith-number/EOT6FJF3JAPN65FBSN7H4WUFCI/graph.json","events_json":"https://pith.science/api/pith-number/EOT6FJF3JAPN65FBSN7H4WUFCI/events.json","paper":"https://pith.science/paper/EOT6FJF3"},"agent_actions":{"view_html":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI","download_json":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI.json","view_paper":"https://pith.science/paper/EOT6FJF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08707&json=true","fetch_graph":"https://pith.science/api/pith-number/EOT6FJF3JAPN65FBSN7H4WUFCI/graph.json","fetch_events":"https://pith.science/api/pith-number/EOT6FJF3JAPN65FBSN7H4WUFCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI/action/storage_attestation","attest_author":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI/action/author_attestation","sign_citation":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI/action/citation_signature","submit_replication":"https://pith.science/pith/EOT6FJF3JAPN65FBSN7H4WUFCI/action/replication_record"}},"created_at":"2026-07-05T08:03:25.929531+00:00","updated_at":"2026-07-05T08:03:25.929531+00:00"}