{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BBUXEDWSDMKJGVVHIWVK4UGP7Q","short_pith_number":"pith:BBUXEDWS","schema_version":"1.0","canonical_sha256":"0869720ed21b149356a745aaae50cffc10979d0814e43f70a9264278ef875a30","source":{"kind":"arxiv","id":"2308.09592","version":1},"attestation_state":"computed","paper":{"title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaoang Wang, Wenhao Chai, Xun Guo, Yan Lu","submitted_at":"2023-08-18T14:39:16Z","abstract_excerpt":"Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing in practical scenarios. In this paper, we tackle this problem by introducing temporal dependency to existing text-driven diffusion models, which allows them to generate consistent appearance for the edited objects. Specifically, we develop a novel inter-frame propagation mechanism for diffusion video editing, which leverages the concept of layered representa"},"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":"2308.09592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T14:39:16Z","cross_cats_sorted":[],"title_canon_sha256":"f21fc482076a0e59b2f097741c69d5302bb76b3ef4aacfa06fa3f76534c1aa54","abstract_canon_sha256":"7944ee14a55a9fee2865f1fb2ac52da345f8d2a424aba00b4b5a1a259374f5da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:35.186250Z","signature_b64":"J3ZSZN1nMUSEybM7C8mowjLNVQCiNuRTZsJ1h2jeytIFJkR6tm5Q3rrtWQc5xhQWJZFLNYgvfXS89XspHJSFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0869720ed21b149356a745aaae50cffc10979d0814e43f70a9264278ef875a30","last_reissued_at":"2026-07-05T06:42:35.185709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:35.185709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gaoang Wang, Wenhao Chai, Xun Guo, Yan Lu","submitted_at":"2023-08-18T14:39:16Z","abstract_excerpt":"Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing in practical scenarios. In this paper, we tackle this problem by introducing temporal dependency to existing text-driven diffusion models, which allows them to generate consistent appearance for the edited objects. Specifically, we develop a novel inter-frame propagation mechanism for diffusion video editing, which leverages the concept of layered representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09592","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/2308.09592/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":"2308.09592","created_at":"2026-07-05T06:42:35.185772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09592v1","created_at":"2026-07-05T06:42:35.185772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09592","created_at":"2026-07-05T06:42:35.185772+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBUXEDWSDMKJ","created_at":"2026-07-05T06:42:35.185772+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBUXEDWSDMKJGVVH","created_at":"2026-07-05T06:42:35.185772+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBUXEDWS","created_at":"2026-07-05T06:42:35.185772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.11988","citing_title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q","json":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q.json","graph_json":"https://pith.science/api/pith-number/BBUXEDWSDMKJGVVHIWVK4UGP7Q/graph.json","events_json":"https://pith.science/api/pith-number/BBUXEDWSDMKJGVVHIWVK4UGP7Q/events.json","paper":"https://pith.science/paper/BBUXEDWS"},"agent_actions":{"view_html":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q","download_json":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q.json","view_paper":"https://pith.science/paper/BBUXEDWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09592&json=true","fetch_graph":"https://pith.science/api/pith-number/BBUXEDWSDMKJGVVHIWVK4UGP7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/BBUXEDWSDMKJGVVHIWVK4UGP7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q/action/storage_attestation","attest_author":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q/action/author_attestation","sign_citation":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q/action/citation_signature","submit_replication":"https://pith.science/pith/BBUXEDWSDMKJGVVHIWVK4UGP7Q/action/replication_record"}},"created_at":"2026-07-05T06:42:35.185772+00:00","updated_at":"2026-07-05T06:42:35.185772+00:00"}