{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3SHYXTGIGKGEQEB343RHKFFSOE","short_pith_number":"pith:3SHYXTGI","schema_version":"1.0","canonical_sha256":"dc8f8bccc8328c48103be6e27514b2712cae16f083144b183b756de8b0f0b503","source":{"kind":"arxiv","id":"2502.06734","version":3},"attestation_state":"computed","paper":{"title":"Se\\~norita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liang, Bojia Zi, Kam-Fai Wong, Marco Chen, Penghui Ruan, Rong Xiao, Shaozhe Hao, Shihao Zhao, Xianbiao Qi, Youze Huang","submitted_at":"2025-02-10T17:58:22Z","abstract_excerpt":"Recent advancements in video generation have spurred the development of video editing techniques, which can be divided into inversion-based and end-to-end methods. However, current video editing methods still suffer from several challenges. Inversion-based methods, though training-free and flexible, are time-consuming during inference, struggle with fine-grained editing instructions, and produce artifacts and jitter. On the other hand, end-to-end methods, which rely on edited video pairs for training, offer faster inference speeds but often produce poor editing results due to a lack of high-qu"},"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":"2502.06734","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T17:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"7152773be1ab94de154ebc1f3f248fac6c663419eaf3d7e501b34f616fe90e88","abstract_canon_sha256":"dcd802cfbf587bfe1f4b256572baf1083bbc33e6257688569249218ddad81d12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:33.813897Z","signature_b64":"AuuZS2QaaTCv++MiXs0IVZmrgs4L0bOUYdG5FfFt9DX5Ps5IjS7XcT/kXQlK4gzEfBBp6XtYgMTBvG8xs4sfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc8f8bccc8328c48103be6e27514b2712cae16f083144b183b756de8b0f0b503","last_reissued_at":"2026-07-05T10:29:33.813221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:33.813221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Se\\~norita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liang, Bojia Zi, Kam-Fai Wong, Marco Chen, Penghui Ruan, Rong Xiao, Shaozhe Hao, Shihao Zhao, Xianbiao Qi, Youze Huang","submitted_at":"2025-02-10T17:58:22Z","abstract_excerpt":"Recent advancements in video generation have spurred the development of video editing techniques, which can be divided into inversion-based and end-to-end methods. However, current video editing methods still suffer from several challenges. Inversion-based methods, though training-free and flexible, are time-consuming during inference, struggle with fine-grained editing instructions, and produce artifacts and jitter. On the other hand, end-to-end methods, which rely on edited video pairs for training, offer faster inference speeds but often produce poor editing results due to a lack of high-qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06734","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/2502.06734/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":"2502.06734","created_at":"2026-07-05T10:29:33.813296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06734v3","created_at":"2026-07-05T10:29:33.813296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06734","created_at":"2026-07-05T10:29:33.813296+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SHYXTGIGKGE","created_at":"2026-07-05T10:29:33.813296+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SHYXTGIGKGEQEB3","created_at":"2026-07-05T10:29:33.813296+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SHYXTGI","created_at":"2026-07-05T10:29:33.813296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24674","citing_title":"Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25193","citing_title":"SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21466","citing_title":"StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18467","citing_title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18748","citing_title":"Aurora: Unified Video Editing with a Tool-Using Agent","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20360","citing_title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06535","citing_title":"Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":74,"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":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE","json":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE.json","graph_json":"https://pith.science/api/pith-number/3SHYXTGIGKGEQEB343RHKFFSOE/graph.json","events_json":"https://pith.science/api/pith-number/3SHYXTGIGKGEQEB343RHKFFSOE/events.json","paper":"https://pith.science/paper/3SHYXTGI"},"agent_actions":{"view_html":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE","download_json":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE.json","view_paper":"https://pith.science/paper/3SHYXTGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06734&json=true","fetch_graph":"https://pith.science/api/pith-number/3SHYXTGIGKGEQEB343RHKFFSOE/graph.json","fetch_events":"https://pith.science/api/pith-number/3SHYXTGIGKGEQEB343RHKFFSOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE/action/storage_attestation","attest_author":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE/action/author_attestation","sign_citation":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE/action/citation_signature","submit_replication":"https://pith.science/pith/3SHYXTGIGKGEQEB343RHKFFSOE/action/replication_record"}},"created_at":"2026-07-05T10:29:33.813296+00:00","updated_at":"2026-07-05T10:29:33.813296+00:00"}