{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GUQTZZQOXR3QHFM6CCWXCQAE5B","short_pith_number":"pith:GUQTZZQO","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"},"canonical_sha256":"35213ce60ebc7703959e10ad714004e85a246e154d0247ecf9dba3f6451df648","source":{"kind":"arxiv","id":"2608.01113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01113","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01113v1","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01113","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"GUQTZZQOXR3Q","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"GUQTZZQOXR3QHFM6","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"GUQTZZQO","created_at":"2026-08-04T01:56:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GUQTZZQOXR3QHFM6CCWXCQAE5B","target":"record","payload":{"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"},"canonical_sha256":"35213ce60ebc7703959e10ad714004e85a246e154d0247ecf9dba3f6451df648","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"},"source_kind":"arxiv","source_id":"2608.01113","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Au47UYrcArWuuWFV4ha8c3EGYswFqOoSZEt/QOjvhQRUNTX0nT3SD7cDQRVkWWV/o2V7mkqTOob1resvQryWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:07:18.881438Z"},"content_sha256":"78b10d48f2a0b60c9e6ec11693100a02d9c5922be3c2665bd72a6b008bc7add8","schema_version":"1.0","event_id":"sha256:78b10d48f2a0b60c9e6ec11693100a02d9c5922be3c2665bd72a6b008bc7add8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GUQTZZQOXR3QHFM6CCWXCQAE5B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3VJ7KuQByJ2GyZmT+NR6Qp/JBcWYW7xPJD4B/zLFEKxYIVmxAiiyLdbGPR6OgT4jw3fM+mhfmSxy9rZDCQ9mCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:07:18.881957Z"},"content_sha256":"fc25ec2cea7dfee081f834d9ae6b5f3641b99358b5265ca64ca6a0e29be9ae90","schema_version":"1.0","event_id":"sha256:fc25ec2cea7dfee081f834d9ae6b5f3641b99358b5265ca64ca6a0e29be9ae90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/bundle.json","state_url":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T05:07:18Z","links":{"resolver":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B","bundle":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/bundle.json","state":"https://pith.science/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUQTZZQOXR3QHFM6CCWXCQAE5B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GUQTZZQOXR3QHFM6CCWXCQAE5B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"594833cca3ee82058bf4a4dfbae2dc1022da60306f1bb8c027bfd8fb6765f990","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T09:20:15Z","title_canon_sha256":"c4b3e41394a3f5848e4864653952fa8a19511ef42165147207f2dd101ab3d9e0"},"schema_version":"1.0","source":{"id":"2608.01113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01113","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01113v1","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01113","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"GUQTZZQOXR3Q","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"GUQTZZQOXR3QHFM6","created_at":"2026-08-04T01:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"GUQTZZQO","created_at":"2026-08-04T01:56:51Z"}],"graph_snapshots":[{"event_id":"sha256:fc25ec2cea7dfee081f834d9ae6b5f3641b99358b5265ca64ca6a0e29be9ae90","target":"graph","created_at":"2026-08-04T01:56:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.01113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fengbin Guan, Sen Liang, Xin Li, Youliang Zhang, Zhibo Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T09:20:15Z","title":"CoT-Edit: Let CoT Guide Instruction Video Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01113","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78b10d48f2a0b60c9e6ec11693100a02d9c5922be3c2665bd72a6b008bc7add8","target":"record","created_at":"2026-08-04T01:56:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"594833cca3ee82058bf4a4dfbae2dc1022da60306f1bb8c027bfd8fb6765f990","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T09:20:15Z","title_canon_sha256":"c4b3e41394a3f5848e4864653952fa8a19511ef42165147207f2dd101ab3d9e0"},"schema_version":"1.0","source":{"id":"2608.01113","kind":"arxiv","version":1}},"canonical_sha256":"35213ce60ebc7703959e10ad714004e85a246e154d0247ecf9dba3f6451df648","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35213ce60ebc7703959e10ad714004e85a246e154d0247ecf9dba3f6451df648","first_computed_at":"2026-08-04T01:56:51.912534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:56:51.912534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fE+68wCXj3ExGEVjbWyssqoH7tt2k/SMe2c4fCGPmlDq0PLScWoff4W+vZuhc9qE+pHc1al836llFGXfPrxODw==","signature_status":"signed_v1","signed_at":"2026-08-04T01:56:51.914035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78b10d48f2a0b60c9e6ec11693100a02d9c5922be3c2665bd72a6b008bc7add8","sha256:fc25ec2cea7dfee081f834d9ae6b5f3641b99358b5265ca64ca6a0e29be9ae90"],"state_sha256":"b8240d6bc1e872d69012d6a4c8e1354f1d00ec8ce241d1582cf4e4fc4f143bcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ZgJAtADwt3ZIhziH0NPzWAFvfRgMe/J06WfIS5UOmOpgS2Ao5ldCbDiJYWD490Gfr7MqsimsRJgB9FIUmgqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T05:07:18.887964Z","bundle_sha256":"0ae602eee41dbb089a5667b4abae0427ba0a87b267ac7eded48d6e92b5009873"}}