{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5I63Q3PVCW2LT5XNJCIF4QAEZL","short_pith_number":"pith:5I63Q3PV","schema_version":"1.0","canonical_sha256":"ea3db86df515b4b9f6ed48905e4004cac7086da7a469be9c7338c066f0e4a0e7","source":{"kind":"arxiv","id":"2607.14681","version":1},"attestation_state":"computed","paper":{"title":"ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pengfei Wan, Ruibin Yuan, Shihao Li, Weihong Lin, Wenhan Luo, Xinlong Chen, Xinyu Liu, Yanghao Wang, Yang Shi, Yike Guo, Yiyang Cai, Yuanxing Zhang, Yujin Han","submitted_at":"2026-07-16T07:43:27Z","abstract_excerpt":"Recent diffusion-based video generation models have made significant progress in multi-reference image-conditioned video editing. However, existing methods still struggle to coordinate information from multiple visual sources accurately. We identify a critical deficiency in existing approaches. Existing editing instructions lack explicit reference relationships, and most multimodal large language models (MLLMs) cannot generate them reliably. To address this problem, we propose ReBind, a systematic framework that introduces semantic instructions with embedded reference tokens as the intermediat"},"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":"2607.14681","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T07:43:27Z","cross_cats_sorted":[],"title_canon_sha256":"2640ab40055e9777f5eb91ce12518513e8448f864f2d4841c4af1ea4d6aaa1da","abstract_canon_sha256":"88ad70bdacf8090f46d5b87d7518abba496991761b02319335e2490d947320a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:24.767967Z","signature_b64":"zDKJ9xMXlzgC1tWpel14ut0vFAa9YYnF1bMnNMKsAxbuJXzePZdBBkl4Md99ADpS9gFISHOGnziAAPhqMCqcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea3db86df515b4b9f6ed48905e4004cac7086da7a469be9c7338c066f0e4a0e7","last_reissued_at":"2026-07-17T01:21:24.767087Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:24.767087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pengfei Wan, Ruibin Yuan, Shihao Li, Weihong Lin, Wenhan Luo, Xinlong Chen, Xinyu Liu, Yanghao Wang, Yang Shi, Yike Guo, Yiyang Cai, Yuanxing Zhang, Yujin Han","submitted_at":"2026-07-16T07:43:27Z","abstract_excerpt":"Recent diffusion-based video generation models have made significant progress in multi-reference image-conditioned video editing. However, existing methods still struggle to coordinate information from multiple visual sources accurately. We identify a critical deficiency in existing approaches. Existing editing instructions lack explicit reference relationships, and most multimodal large language models (MLLMs) cannot generate them reliably. To address this problem, we propose ReBind, a systematic framework that introduces semantic instructions with embedded reference tokens as the intermediat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14681","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/2607.14681/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":"2607.14681","created_at":"2026-07-17T01:21:24.767546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14681v1","created_at":"2026-07-17T01:21:24.767546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14681","created_at":"2026-07-17T01:21:24.767546+00:00"},{"alias_kind":"pith_short_12","alias_value":"5I63Q3PVCW2L","created_at":"2026-07-17T01:21:24.767546+00:00"},{"alias_kind":"pith_short_16","alias_value":"5I63Q3PVCW2LT5XN","created_at":"2026-07-17T01:21:24.767546+00:00"},{"alias_kind":"pith_short_8","alias_value":"5I63Q3PV","created_at":"2026-07-17T01:21:24.767546+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/5I63Q3PVCW2LT5XNJCIF4QAEZL","json":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL.json","graph_json":"https://pith.science/api/pith-number/5I63Q3PVCW2LT5XNJCIF4QAEZL/graph.json","events_json":"https://pith.science/api/pith-number/5I63Q3PVCW2LT5XNJCIF4QAEZL/events.json","paper":"https://pith.science/paper/5I63Q3PV"},"agent_actions":{"view_html":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL","download_json":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL.json","view_paper":"https://pith.science/paper/5I63Q3PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14681&json=true","fetch_graph":"https://pith.science/api/pith-number/5I63Q3PVCW2LT5XNJCIF4QAEZL/graph.json","fetch_events":"https://pith.science/api/pith-number/5I63Q3PVCW2LT5XNJCIF4QAEZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL/action/storage_attestation","attest_author":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL/action/author_attestation","sign_citation":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL/action/citation_signature","submit_replication":"https://pith.science/pith/5I63Q3PVCW2LT5XNJCIF4QAEZL/action/replication_record"}},"created_at":"2026-07-17T01:21:24.767546+00:00","updated_at":"2026-07-17T01:21:24.767546+00:00"}