{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AAXCKVCRJZ7KONYNAZ5BDMRNFF","short_pith_number":"pith:AAXCKVCR","schema_version":"1.0","canonical_sha256":"002e2554514e7ea7370d067a11b22d29634495827e39ccf215586da8f7b2156b","source":{"kind":"arxiv","id":"2606.23254","version":1},"attestation_state":"computed","paper":{"title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Zeng, Ming Lu, Moran Li, Qi She, Ruichuan An, Wentao Zhang, Yiheng Lin, Yingchen Yu, Zhengwei Wang","submitted_at":"2026-06-22T12:37:15Z","abstract_excerpt":"Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain, video text editing remains largely unexplored: it is a localized task demanding stroke-level precision within small text regions, which compounds the challenges of cross-frame accuracy, temporal coherence, and stylistic fidelity. We introduce SteerVTE, a unified framework that \\underline{\\textbf{steer}}s a frozen video diffusion model to perform precise \\underline{\\textbf{V}}ideo \\underline{\\textbf{T}}ext \\underline{"},"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":"2606.23254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T12:37:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc5ce81faf33f3cfc5de1b7819e797b1860cdad82e77276b14f0d40860cad042","abstract_canon_sha256":"44e57e2f427d2ba1fa67f37a4f039fed79b116ec246e73546d740bff7fa2aac1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:14.966762Z","signature_b64":"ZuCHrm+NPJVRcccmHtBassXUjf+LWjxxw39zCwXg6Bgv1Dd9tYHjXVOu5V9IEpoYxDH5as3B3GnHJtQUlbz7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"002e2554514e7ea7370d067a11b22d29634495827e39ccf215586da8f7b2156b","last_reissued_at":"2026-06-23T03:14:14.966348Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:14.966348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kai Zeng, Ming Lu, Moran Li, Qi She, Ruichuan An, Wentao Zhang, Yiheng Lin, Yingchen Yu, Zhengwei Wang","submitted_at":"2026-06-22T12:37:15Z","abstract_excerpt":"Visual text editing aims to precisely modify text in images and videos while preserving stylistic consistency and visual realism. Despite significant advances in the image domain, video text editing remains largely unexplored: it is a localized task demanding stroke-level precision within small text regions, which compounds the challenges of cross-frame accuracy, temporal coherence, and stylistic fidelity. We introduce SteerVTE, a unified framework that \\underline{\\textbf{steer}}s a frozen video diffusion model to perform precise \\underline{\\textbf{V}}ideo \\underline{\\textbf{T}}ext \\underline{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23254","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/2606.23254/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":"2606.23254","created_at":"2026-06-23T03:14:14.966414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23254v1","created_at":"2026-06-23T03:14:14.966414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23254","created_at":"2026-06-23T03:14:14.966414+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAXCKVCRJZ7K","created_at":"2026-06-23T03:14:14.966414+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAXCKVCRJZ7KONYN","created_at":"2026-06-23T03:14:14.966414+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAXCKVCR","created_at":"2026-06-23T03:14:14.966414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF","json":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF.json","graph_json":"https://pith.science/api/pith-number/AAXCKVCRJZ7KONYNAZ5BDMRNFF/graph.json","events_json":"https://pith.science/api/pith-number/AAXCKVCRJZ7KONYNAZ5BDMRNFF/events.json","paper":"https://pith.science/paper/AAXCKVCR"},"agent_actions":{"view_html":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF","download_json":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF.json","view_paper":"https://pith.science/paper/AAXCKVCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23254&json=true","fetch_graph":"https://pith.science/api/pith-number/AAXCKVCRJZ7KONYNAZ5BDMRNFF/graph.json","fetch_events":"https://pith.science/api/pith-number/AAXCKVCRJZ7KONYNAZ5BDMRNFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF/action/storage_attestation","attest_author":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF/action/author_attestation","sign_citation":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF/action/citation_signature","submit_replication":"https://pith.science/pith/AAXCKVCRJZ7KONYNAZ5BDMRNFF/action/replication_record"}},"created_at":"2026-06-23T03:14:14.966414+00:00","updated_at":"2026-06-23T03:14:14.966414+00:00"}