{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QA6PZHYOA2DWKEGJOGXRZSOBGH","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":"95d509ec61cc0916199e7581093142a76e29345c3db3155de840ef4778f6fa86","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-21T03:28:13Z","title_canon_sha256":"0e0199a506409d3f2f9f586aa92368cdf8b04403a7b3737494078dcbfd6c90b8"},"schema_version":"1.0","source":{"id":"2305.12328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12328","created_at":"2026-07-05T08:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12328v2","created_at":"2026-07-05T08:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12328","created_at":"2026-07-05T08:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"QA6PZHYOA2DW","created_at":"2026-07-05T08:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"QA6PZHYOA2DWKEGJ","created_at":"2026-07-05T08:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"QA6PZHYO","created_at":"2026-07-05T08:24:36Z"}],"graph_snapshots":[{"event_id":"sha256:36317f9e35adfc33796e31c926e419fdcab5a4119024e4f25843c34e39bd7b69","target":"graph","created_at":"2026-07-05T08:24:36Z","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/2305.12328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for per-example fine-tuning or inversion. The proposed InstructVid2Vid model modifies a pretrained image generation model, Stable Diffusion, to generate a time-dependent sequence of video frames. By harnessing the collective intelligence of disparate models, we engineer a training dataset rich in video-instruction triplets, which is a more cost-efficient alternative t","authors_text":"Bosheng Qin, Juncheng Li, Siliang Tang, Tat-Seng Chua, Yueting Zhuang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-21T03:28:13Z","title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12328","kind":"arxiv","version":2},"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:eaa645499e303279505e26fa407cb7b158b1d6910072c39470db068ecf93846c","target":"record","created_at":"2026-07-05T08:24:36Z","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":"95d509ec61cc0916199e7581093142a76e29345c3db3155de840ef4778f6fa86","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-21T03:28:13Z","title_canon_sha256":"0e0199a506409d3f2f9f586aa92368cdf8b04403a7b3737494078dcbfd6c90b8"},"schema_version":"1.0","source":{"id":"2305.12328","kind":"arxiv","version":2}},"canonical_sha256":"803cfc9f0e06876510c971af1cc9c131fac8eddd48eb6376b1abca294ea086d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"803cfc9f0e06876510c971af1cc9c131fac8eddd48eb6376b1abca294ea086d7","first_computed_at":"2026-07-05T08:24:36.426046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:36.426046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pFqsu3JinAoSMpbWiGU/41BYlDsMSGzGRyPScak89SvlQg1JI3iLJ1nSO2smLhW3VVjKCJh8RcwmjjFdKINBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:36.426543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaa645499e303279505e26fa407cb7b158b1d6910072c39470db068ecf93846c","sha256:36317f9e35adfc33796e31c926e419fdcab5a4119024e4f25843c34e39bd7b69"],"state_sha256":"c9f69b19b9ac7cbfed8675c9f9d493f17a58c521b1a59c8f183da9747ea60d5e"}