{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BXEMMBOADXZZAS5ZILJPWDS4OK","short_pith_number":"pith:BXEMMBOA","schema_version":"1.0","canonical_sha256":"0dc8c605c01df3904bb942d2fb0e5c728ee1bfb9cf6101c4129a060d2caa7e4c","source":{"kind":"arxiv","id":"2310.05922","version":3},"attestation_state":"computed","paper":{"title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christian Simon, Jiawei Ren, Juan-Manuel Perez-Rua, Mengmeng Xu, Sen He, Shoufa Chen, Tao Xiang, Yanping Xie, Yuren Cong","submitted_at":"2023-10-09T17:59:53Z","abstract_excerpt":"Text-to-video editing aims to edit the visual appearance of a source video conditional on textual prompts. A major challenge in this task is to ensure that all frames in the edited video are visually consistent. Most recent works apply advanced text-to-image diffusion models to this task by inflating 2D spatial attention in the U-Net into spatio-temporal attention. Although temporal context can be added through spatio-temporal attention, it may introduce some irrelevant information for each patch and therefore cause inconsistency in the edited video. In this paper, for the first time, we intro"},"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":"2310.05922","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"bce8150ddfd70342883f2988bdc376ad65118eabc1234f4d16b6037256473522","abstract_canon_sha256":"56c510e718b89fb74df219d6106756f9783455e87cccbb09cf97d9d217414dfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:52.864194Z","signature_b64":"5QfeNzbGD6Sv1QZB2AUKhN/swFjZpvjbUh91spD8Uy5ny34BmrKIe+OzWxa49/JoLWGvpyJV8lwiWoMzauzqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc8c605c01df3904bb942d2fb0e5c728ee1bfb9cf6101c4129a060d2caa7e4c","last_reissued_at":"2026-07-05T07:50:52.863704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:52.863704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christian Simon, Jiawei Ren, Juan-Manuel Perez-Rua, Mengmeng Xu, Sen He, Shoufa Chen, Tao Xiang, Yanping Xie, Yuren Cong","submitted_at":"2023-10-09T17:59:53Z","abstract_excerpt":"Text-to-video editing aims to edit the visual appearance of a source video conditional on textual prompts. A major challenge in this task is to ensure that all frames in the edited video are visually consistent. Most recent works apply advanced text-to-image diffusion models to this task by inflating 2D spatial attention in the U-Net into spatio-temporal attention. Although temporal context can be added through spatio-temporal attention, it may introduce some irrelevant information for each patch and therefore cause inconsistency in the edited video. In this paper, for the first time, we intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05922","kind":"arxiv","version":3},"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/2310.05922/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":"2310.05922","created_at":"2026-07-05T07:50:52.863762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05922v3","created_at":"2026-07-05T07:50:52.863762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05922","created_at":"2026-07-05T07:50:52.863762+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXEMMBOADXZZ","created_at":"2026-07-05T07:50:52.863762+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXEMMBOADXZZAS5Z","created_at":"2026-07-05T07:50:52.863762+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXEMMBOA","created_at":"2026-07-05T07:50:52.863762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23254","citing_title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22042","citing_title":"IDAG-Edit: Multi-Object Video Editing via Instance-Decoupled Attention and Guidance","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19676","citing_title":"TeleMorpher: Toward Robust Simultaneous Motion-Location Editing","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02000","citing_title":"Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29020","citing_title":"Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01186","citing_title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09721","citing_title":"FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14136","citing_title":"TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion","ref_index":12,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07695","citing_title":"OphEdit: Training-Free Text-Guided Editing of Ophthalmic Surgical Videos","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13509","citing_title":"DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14556","citing_title":"Controllable Video Object Insertion via Multiview Priors","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK","json":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK.json","graph_json":"https://pith.science/api/pith-number/BXEMMBOADXZZAS5ZILJPWDS4OK/graph.json","events_json":"https://pith.science/api/pith-number/BXEMMBOADXZZAS5ZILJPWDS4OK/events.json","paper":"https://pith.science/paper/BXEMMBOA"},"agent_actions":{"view_html":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK","download_json":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK.json","view_paper":"https://pith.science/paper/BXEMMBOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05922&json=true","fetch_graph":"https://pith.science/api/pith-number/BXEMMBOADXZZAS5ZILJPWDS4OK/graph.json","fetch_events":"https://pith.science/api/pith-number/BXEMMBOADXZZAS5ZILJPWDS4OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK/action/storage_attestation","attest_author":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK/action/author_attestation","sign_citation":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK/action/citation_signature","submit_replication":"https://pith.science/pith/BXEMMBOADXZZAS5ZILJPWDS4OK/action/replication_record"}},"created_at":"2026-07-05T07:50:52.863762+00:00","updated_at":"2026-07-05T07:50:52.863762+00:00"}