{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4ZVQJD6UAPPG6ELL3QINWN4WWF","short_pith_number":"pith:4ZVQJD6U","canonical_record":{"source":{"id":"2307.10373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T18:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"dbea7345e122a1e97e220cee9e14684f92d07d9632b7f26ed75e64ce59eb04e7","abstract_canon_sha256":"b96ec8c6351673bf7ed8019ebd9f1eb0f2ee97edac7e2bd78e5884173c3ed0cf"},"schema_version":"1.0"},"canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","source":{"kind":"arxiv","id":"2307.10373","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10373","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10373v3","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10373","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"4ZVQJD6UAPPG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"4ZVQJD6UAPPG6ELL","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"4ZVQJD6U","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4ZVQJD6UAPPG6ELL3QINWN4WWF","target":"record","payload":{"canonical_record":{"source":{"id":"2307.10373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T18:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"dbea7345e122a1e97e220cee9e14684f92d07d9632b7f26ed75e64ce59eb04e7","abstract_canon_sha256":"b96ec8c6351673bf7ed8019ebd9f1eb0f2ee97edac7e2bd78e5884173c3ed0cf"},"schema_version":"1.0"},"canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.200853Z","signature_b64":"PPVdOKv5ctFlpRIfBlz7IG3odD5gqnBF9/1N0TrB+ae7C7cnUPKcrQ1Wqwdg0V3+YNJ06jQu/UF0m5nWaq9JDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","last_reissued_at":"2026-05-17T23:38:13.200350Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.200350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.10373","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EbvDR9RYXzLIF23AH1OUHTm1lM2wyu2BuVZDJzCyQ5Vw3vUdnIaphDpsWrqH2mBsoKMu5+BM1n9KO+AAuvCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:27:42.316355Z"},"content_sha256":"49cdd14f9db47f58b18b647d3db0ed8bfabfd1f92f08379cb0c6542061b1dbd2","schema_version":"1.0","event_id":"sha256:49cdd14f9db47f58b18b647d3db0ed8bfabfd1f92f08379cb0c6542061b1dbd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4ZVQJD6UAPPG6ELL3QINWN4WWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel","submitted_at":"2023-07-19T18:00:03Z","abstract_excerpt":"The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key obse"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4ccb249b00a6a7e3e13d95681f3b8f30d3b6fafe43474d8898a78c5199fb930d"},"source":{"id":"2307.10373","kind":"arxiv","version":3},"verdict":{"id":"7f5d009a-ce61-46d1-9840-926ab35d5e64","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:12:21.562760Z","strongest_claim":"consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences","one_line_summary":"TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning.","pith_extraction_headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits."},"references":{"count":27,"sample":[{"doi":"","year":null,"title":"Multidiffusion: Fusing diffusion paths for controlled image generation","work_id":"1a06e9b7-e97f-4665-ba6e-55301822d3b6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Pix2video: Video editing using image diffusion","work_id":"9a64fd9d-fb53-46a1-8edb-808f1a5cd594","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models","work_id":"92bbf1bb-4319-45c4-845c-523bfc2cb97b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Diffusion models in vision: A survey.arXiv e-prints, abs/2209.04747","work_id":"46a3884e-d8d0-426d-873e-9096d96da38d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Structure and content-guided video synthesis with diffusion models","work_id":"9ec84ad8-517d-4d27-ba1a-447562d63988","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":27,"snapshot_sha256":"1458884d8ae3174bd27a627983cb5513060573d2271a44c8fca28fb9a36dc743","internal_anchors":7},"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"},"verdict_id":"7f5d009a-ce61-46d1-9840-926ab35d5e64"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4wlh+x3bxMKjB3V7YzQ+pNfgYJYXAo4YXjVIjqvFY8kSkZklxzbGFQav/3x5ahrSe8/M/EZwcFQXrPKp76kDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T21:27:42.316872Z"},"content_sha256":"691bee45452db63ff1371f8d2b6633d838ce9fd9e4d1bf50f3fa1d63c85656c0","schema_version":"1.0","event_id":"sha256:691bee45452db63ff1371f8d2b6633d838ce9fd9e4d1bf50f3fa1d63c85656c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/bundle.json","state_url":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T21:27:42Z","links":{"resolver":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF","bundle":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/bundle.json","state":"https://pith.science/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZVQJD6UAPPG6ELL3QINWN4WWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4ZVQJD6UAPPG6ELL3QINWN4WWF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b96ec8c6351673bf7ed8019ebd9f1eb0f2ee97edac7e2bd78e5884173c3ed0cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T18:00:03Z","title_canon_sha256":"dbea7345e122a1e97e220cee9e14684f92d07d9632b7f26ed75e64ce59eb04e7"},"schema_version":"1.0","source":{"id":"2307.10373","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10373","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10373v3","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10373","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"4ZVQJD6UAPPG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"4ZVQJD6UAPPG6ELL","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"4ZVQJD6U","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:691bee45452db63ff1371f8d2b6633d838ce9fd9e4d1bf50f3fa1d63c85656c0","target":"graph","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits."}],"snapshot_sha256":"4ccb249b00a6a7e3e13d95681f3b8f30d3b6fafe43474d8898a78c5199fb930d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key obse","authors_text":"Michal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel","cross_cats":[],"headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T18:00:03Z","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing"},"references":{"count":27,"internal_anchors":7,"resolved_work":27,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Multidiffusion: Fusing diffusion paths for controlled image generation","work_id":"1a06e9b7-e97f-4665-ba6e-55301822d3b6","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Pix2video: Video editing using image diffusion","work_id":"9a64fd9d-fb53-46a1-8edb-808f1a5cd594","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models","work_id":"92bbf1bb-4319-45c4-845c-523bfc2cb97b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Diffusion models in vision: A survey.arXiv e-prints, abs/2209.04747","work_id":"46a3884e-d8d0-426d-873e-9096d96da38d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Structure and content-guided video synthesis with diffusion models","work_id":"9ec84ad8-517d-4d27-ba1a-447562d63988","year":null}],"snapshot_sha256":"1458884d8ae3174bd27a627983cb5513060573d2271a44c8fca28fb9a36dc743"},"source":{"id":"2307.10373","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T20:12:21.562760Z","id":"7f5d009a-ce61-46d1-9840-926ab35d5e64","model_set":{"reader":"grok-4.3"},"one_line_summary":"TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.","strongest_claim":"consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences","weakest_assumption":"That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning."}},"verdict_id":"7f5d009a-ce61-46d1-9840-926ab35d5e64"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:49cdd14f9db47f58b18b647d3db0ed8bfabfd1f92f08379cb0c6542061b1dbd2","target":"record","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b96ec8c6351673bf7ed8019ebd9f1eb0f2ee97edac7e2bd78e5884173c3ed0cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T18:00:03Z","title_canon_sha256":"dbea7345e122a1e97e220cee9e14684f92d07d9632b7f26ed75e64ce59eb04e7"},"schema_version":"1.0","source":{"id":"2307.10373","kind":"arxiv","version":3}},"canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62","first_computed_at":"2026-05-17T23:38:13.200350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.200350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PPVdOKv5ctFlpRIfBlz7IG3odD5gqnBF9/1N0TrB+ae7C7cnUPKcrQ1Wqwdg0V3+YNJ06jQu/UF0m5nWaq9JDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.200853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.10373","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49cdd14f9db47f58b18b647d3db0ed8bfabfd1f92f08379cb0c6542061b1dbd2","sha256:691bee45452db63ff1371f8d2b6633d838ce9fd9e4d1bf50f3fa1d63c85656c0"],"state_sha256":"d97cc0482d2d01ceec85c94e361a2e14c6829969f864b17d4ed7df86eff0c217"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uTHrAToW57VAjlG1ZSb6yxEuZBy4HGVWqBqpfu++ZymP/RKpuNznICWm2YsIL6SEMKIdbVLD8OdwvGxE0NOCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T21:27:42.320215Z","bundle_sha256":"c47b6efe00b988af1fd6979d3b8f5f133ec02747978beacba5154ab8308325a7"}}