{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUQTZZQOXR3QHFM6CCWXCQAE5B","short_pith_number":"pith:GUQTZZQO","schema_version":"1.0","canonical_sha256":"35213ce60ebc7703959e10ad714004e85a246e154d0247ecf9dba3f6451df648","source":{"kind":"arxiv","id":"2608.01113","version":1},"attestation_state":"computed","paper":{"title":"CoT-Edit: Let CoT Guide Instruction Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengbin Guan, Sen Liang, Xin Li, Youliang Zhang, Zhibo Chen","submitted_at":"2026-08-02T09:20:15Z","abstract_excerpt":"Text-driven instruction-based video editing in complex scenes remains challenging: purely textual prompts often fail to capture precise spatial relationships and physical constraints, resulting in target ambiguity and physically implausible outcomes. To address this, we propose a plan--guide--edit framework that explicitly bridges semantic intent and spatial execution. In our framework, a Chain-of-Thought (CoT)-enhanced multimodal large language model (MLLM) serves as a planner, performing structured reasoning over the video and instructions to derive a precise sequence of bounding boxes and a"},"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":"2608.01113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T09:20:15Z","cross_cats_sorted":[],"title_canon_sha256":"c4b3e41394a3f5848e4864653952fa8a19511ef42165147207f2dd101ab3d9e0","abstract_canon_sha256":"594833cca3ee82058bf4a4dfbae2dc1022da60306f1bb8c027bfd8fb6765f990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:51.914035Z","signature_b64":"fE+68wCXj3ExGEVjbWyssqoH7tt2k/SMe2c4fCGPmlDq0PLScWoff4W+vZuhc9qE+pHc1al836llFGXfPrxODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35213ce60ebc7703959e10ad714004e85a246e154d0247ecf9dba3f6451df648","last_reissued_at":"2026-08-04T01:56:51.912534Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:51.912534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoT-Edit: Let CoT Guide Instruction Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengbin Guan, Sen Liang, Xin Li, Youliang Zhang, Zhibo Chen","submitted_at":"2026-08-02T09:20:15Z","abstract_excerpt":"Text-driven instruction-based video editing in complex scenes remains challenging: purely textual prompts often fail to capture precise spatial relationships and physical constraints, resulting in target ambiguity and physically implausible outcomes. To address this, we propose a plan--guide--edit framework that explicitly bridges semantic intent and spatial execution. In our framework, a Chain-of-Thought (CoT)-enhanced multimodal large language model (MLLM) serves as a planner, performing structured reasoning over the video and instructions to derive a precise sequence of bounding boxes and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01113","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/2608.01113/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":"2608.01113","created_at":"2026-08-04T01:56:51.913831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01113v1","created_at":"2026-08-04T01:56:51.913831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01113","created_at":"2026-08-04T01:56:51.913831+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUQTZZQOXR3Q","created_at":"2026-08-04T01:56:51.913831+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUQTZZQOXR3QHFM6","created_at":"2026-08-04T01:56:51.913831+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUQTZZQO","created_at":"2026-08-04T01:56:51.913831+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/GUQTZZQOXR3QHFM6CCWXCQAE5B","json":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B.json","graph_json":"https://pith.science/api/pith-number/GUQTZZQOXR3QHFM6CCWXCQAE5B/graph.json","events_json":"https://pith.science/api/pith-number/GUQTZZQOXR3QHFM6CCWXCQAE5B/events.json","paper":"https://pith.science/paper/GUQTZZQO"},"agent_actions":{"view_html":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B","download_json":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B.json","view_paper":"https://pith.science/paper/GUQTZZQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01113&json=true","fetch_graph":"https://pith.science/api/pith-number/GUQTZZQOXR3QHFM6CCWXCQAE5B/graph.json","fetch_events":"https://pith.science/api/pith-number/GUQTZZQOXR3QHFM6CCWXCQAE5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/action/storage_attestation","attest_author":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/action/author_attestation","sign_citation":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/action/citation_signature","submit_replication":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/action/replication_record"}},"created_at":"2026-08-04T01:56:51.913831+00:00","updated_at":"2026-08-04T01:56:51.913831+00:00"}