{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5PAHF7TLEYWWSYVPUV2ZLNVO24","short_pith_number":"pith:5PAHF7TL","schema_version":"1.0","canonical_sha256":"ebc072fe6b262d6962afa57595b6aed732be15f207cb133df498536b061d0300","source":{"kind":"arxiv","id":"2603.02175","version":4},"attestation_state":"computed","paper":{"title":"Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Kiwi-Edit achieves state-of-the-art results in controllable video editing by combining instructions with reference images through a new data pipeline and architecture.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guoqiang Liang, Mike Zheng Shou, Yanzhe Chen, Yiqi Lin, Zechen Bai, Ziyun Zeng","submitted_at":"2026-03-02T18:46:28Z","abstract_excerpt":"Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describing complex visual nuances. Although reference-guided editing offers a robust solution, its potential is currently bottlenecked by the scarcity of high-quality paired training data. To bridge this gap, we introduce a scalable data generation pipeline that transforms existing video editing pairs into high-fidelity training quadruplets, leveraging image generative models to create synthesized reference scaffolds. Using t"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.02175","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-02T18:46:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e82812b8063cd874a10adc3deb3298719b67b3b54e2993ac6ab820884bcb1180","abstract_canon_sha256":"1d4d9c9f52287d7737edd4900dfb6e570d716a7a4a526f3592fcdcb24500696d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:23.220217Z","signature_b64":"xz2r4KhtQNeBxFY4DuWN+shrryLYwgdVUQ8/ucs59h++d0G+brjbwTjlERllAYJ/aTjg4RoTpWDpFB/ZUbU0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc072fe6b262d6962afa57595b6aed732be15f207cb133df498536b061d0300","last_reissued_at":"2026-05-18T03:09:23.219439Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:23.219439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Kiwi-Edit achieves state-of-the-art results in controllable video editing by combining instructions with reference images through a new data pipeline and architecture.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guoqiang Liang, Mike Zheng Shou, Yanzhe Chen, Yiqi Lin, Zechen Bai, Ziyun Zeng","submitted_at":"2026-03-02T18:46:28Z","abstract_excerpt":"Instruction-based video editing has witnessed rapid progress, yet current methods often struggle with precise visual control, as natural language is inherently limited in describing complex visual nuances. Although reference-guided editing offers a robust solution, its potential is currently bottlenecked by the scarcity of high-quality paired training data. To bridge this gap, we introduce a scalable data generation pipeline that transforms existing video editing pairs into high-fidelity training quadruplets, leveraging image generative models to create synthesized reference scaffolds. Using t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our model achieves significant gains in instruction following and reference fidelity via a progressive multi-stage training curriculum. Extensive experiments demonstrate that our data and architecture establish a new state-of-the-art in controllable video editing.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The image generative models used in the data pipeline produce synthesized reference scaffolds that are high-fidelity and unbiased enough to train a model that generalizes to real user-provided references without introducing artifacts or distribution shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Kiwi-Edit introduces a scalable pipeline to generate RefVIE dataset and a unified model using learnable queries plus reference features to achieve new state-of-the-art in instruction-and-reference guided video editing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Kiwi-Edit achieves state-of-the-art results in controllable video editing by combining instructions with reference images through a new data pipeline and architecture.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e18ce611c993c105eeb645cb594d0d4ba9bc8bdc9675158d47d432bbde5b9b0d"},"source":{"id":"2603.02175","kind":"arxiv","version":4},"verdict":{"id":"21c21a12-9247-445a-99e0-513e83cb9b5a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T17:32:43.981091Z","strongest_claim":"Our model achieves significant gains in instruction following and reference fidelity via a progressive multi-stage training curriculum. Extensive experiments demonstrate that our data and architecture establish a new state-of-the-art in controllable video editing.","one_line_summary":"Kiwi-Edit introduces a scalable pipeline to generate RefVIE dataset and a unified model using learnable queries plus reference features to achieve new state-of-the-art in instruction-and-reference guided video editing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The image generative models used in the data pipeline produce synthesized reference scaffolds that are high-fidelity and unbiased enough to train a model that generalizes to real user-provided references without introducing artifacts or distribution shifts.","pith_extraction_headline":"Kiwi-Edit achieves state-of-the-art results in controllable video editing by combining instructions with reference images through a new data pipeline and architecture."},"references":{"count":32,"sample":[{"doi":"","year":null,"title":"- Object identity, attributes (color, shape, material, style), and edit type must be consistent","work_id":"d5d96ab4-c93f-4e63-ae26-2ad1f7cbb1a8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"- Coherent structure, plausible lighting and texture","work_id":"b6eb58bc-17f3-42e1-a954-5cb7b805697a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Object not swapped/added, or a completely unrelated object appears","work_id":"1e0d2148-6d9f-4a08-b6ec-661e90d27fa9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Object is changed, but looks nothing like the reference image (wrong color, shape, or class)","work_id":"3db0ad97-159f-4a41-870d-ed838e14bd14","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Object class is correct, but identity details (texture, specific markings, logos) differ significantly from the reference image","work_id":"0da8ff03-155b-4fe6-a9de-889d62aece5d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"4bb9d83768bf47e9c83c3bc6bd7f64d35cbd3aa612d627a0e0fb0bda30271b1e","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":"2603.02175","created_at":"2026-05-18T03:09:23.219574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.02175v4","created_at":"2026-05-18T03:09:23.219574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02175","created_at":"2026-05-18T03:09:23.219574+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PAHF7TLEYWW","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PAHF7TLEYWWSYVP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PAHF7TL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.20795","citing_title":"What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18748","citing_title":"Aurora: Unified Video Editing with a Tool-Using Agent","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17019","citing_title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15307","citing_title":"Sound Sparks Motion: Audio and Text Tuning for Video Editing","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06535","citing_title":"Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07958","citing_title":"ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks","ref_index":18,"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":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02641","citing_title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24","json":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24.json","graph_json":"https://pith.science/api/pith-number/5PAHF7TLEYWWSYVPUV2ZLNVO24/graph.json","events_json":"https://pith.science/api/pith-number/5PAHF7TLEYWWSYVPUV2ZLNVO24/events.json","paper":"https://pith.science/paper/5PAHF7TL"},"agent_actions":{"view_html":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24","download_json":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24.json","view_paper":"https://pith.science/paper/5PAHF7TL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.02175&json=true","fetch_graph":"https://pith.science/api/pith-number/5PAHF7TLEYWWSYVPUV2ZLNVO24/graph.json","fetch_events":"https://pith.science/api/pith-number/5PAHF7TLEYWWSYVPUV2ZLNVO24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24/action/storage_attestation","attest_author":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24/action/author_attestation","sign_citation":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24/action/citation_signature","submit_replication":"https://pith.science/pith/5PAHF7TLEYWWSYVPUV2ZLNVO24/action/replication_record"}},"created_at":"2026-05-18T03:09:23.219574+00:00","updated_at":"2026-05-18T03:09:23.219574+00:00"}