{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CTZSCLDUB7FGISP5RCMXF3FV5Q","short_pith_number":"pith:CTZSCLDU","schema_version":"1.0","canonical_sha256":"14f3212c740fca6449fd889972ecb5ec282b13745478950f510a51a60fe32c37","source":{"kind":"arxiv","id":"2512.07826","version":3},"attestation_state":"computed","paper":{"title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyang He, Jiangning Zhang, Jie Wang, Lei Xie, Qiangpeng Yang, Shilei Wen, Xingyuan Bu, Zhucun Xue","submitted_at":"2025-12-08T18:55:07Z","abstract_excerpt":"The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulous"},"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":"2512.07826","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-08T18:55:07Z","cross_cats_sorted":[],"title_canon_sha256":"0106528e708db583df188854a578681b42781e63d404843973eaa3da5329e5d0","abstract_canon_sha256":"9d7b7fde2f134a0c7592ef99142586561af45d585a1ce3f705f68671204df13e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:24:46.951655Z","signature_b64":"zXV8kBXYVvo7cpxEy+s3XuWxQHl7Blgh3Rs0AtgnmxxfeFULZV4fkxHH6854M+aukHsyht8Al0gqOwe90KM2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14f3212c740fca6449fd889972ecb5ec282b13745478950f510a51a60fe32c37","last_reissued_at":"2026-08-13T01:24:46.949324Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:24:46.949324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyang He, Jiangning Zhang, Jie Wang, Lei Xie, Qiangpeng Yang, Shilei Wen, Xingyuan Bu, Zhucun Xue","submitted_at":"2025-12-08T18:55:07Z","abstract_excerpt":"The quality and diversity of instruction-based image editing datasets are continuously increasing, yet large-scale, high-quality datasets for instruction-based video editing remain scarce. To address this gap, we introduce OpenVE-3M, an open-source, large-scale, and high-quality dataset for instruction-based video editing. It comprises two primary categories: spatially-aligned edits (Global Style, Background Change, Local Change, Local Remove, Local Add, and Subtitles Edit) and non-spatially-aligned edits (Camera Multi-Shot Edit and Creative Edit). All edit types are generated via a meticulous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.07826","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/2512.07826/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":"2512.07826","created_at":"2026-08-13T01:24:46.950455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.07826v3","created_at":"2026-08-13T01:24:46.950455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.07826","created_at":"2026-08-13T01:24:46.950455+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTZSCLDUB7FG","created_at":"2026-08-13T01:24:46.950455+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTZSCLDUB7FGISP5","created_at":"2026-08-13T01:24:46.950455+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTZSCLDU","created_at":"2026-08-13T01:24:46.950455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30599","citing_title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24674","citing_title":"Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25193","citing_title":"SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30599","citing_title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30045","citing_title":"DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30409","citing_title":"SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23192","citing_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","ref_index":113,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23891","citing_title":"Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18748","citing_title":"Aurora: Unified Video Editing with a Tool-Using Agent","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14664","citing_title":"MiVE: Multiscale Vision-language features for reference-guided video Editing","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06535","citing_title":"Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08646","citing_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07958","citing_title":"ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16272","citing_title":"VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17021","citing_title":"LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02641","citing_title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q","json":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q.json","graph_json":"https://pith.science/api/pith-number/CTZSCLDUB7FGISP5RCMXF3FV5Q/graph.json","events_json":"https://pith.science/api/pith-number/CTZSCLDUB7FGISP5RCMXF3FV5Q/events.json","paper":"https://pith.science/paper/CTZSCLDU"},"agent_actions":{"view_html":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q","download_json":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q.json","view_paper":"https://pith.science/paper/CTZSCLDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.07826&json=true","fetch_graph":"https://pith.science/api/pith-number/CTZSCLDUB7FGISP5RCMXF3FV5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/CTZSCLDUB7FGISP5RCMXF3FV5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q/action/storage_attestation","attest_author":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q/action/author_attestation","sign_citation":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q/action/citation_signature","submit_replication":"https://pith.science/pith/CTZSCLDUB7FGISP5RCMXF3FV5Q/action/replication_record"}},"created_at":"2026-08-13T01:24:46.950455+00:00","updated_at":"2026-08-13T01:24:46.950455+00:00"}