{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KO2EJIUPYZZE4NWSG677O5JCP5","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":"91e06fdab4f579fec178bdf8cad6f6ddf00535baf459d5a7ab72777a771ce65a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:36:26Z","title_canon_sha256":"ed1f9c92447326189a7f2b05ea23dd5388504a2883864b1d71d9f8cbb5db9a14"},"schema_version":"1.0","source":{"id":"2309.15091","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15091","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15091v2","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15091","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"KO2EJIUPYZZE","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"KO2EJIUPYZZE4NWS","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"KO2EJIUP","created_at":"2026-07-05T08:43:23Z"}],"graph_snapshots":[{"event_id":"sha256:657e9d6e8bdc8ca0779a4ed96f1e495e391fdedabe7911d8e0f96d039343c059","target":"graph","created_at":"2026-07-05T08:43:23Z","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/2309.15091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-video (T2V) generation methods have seen significant advancements. However, the majority of these works focus on producing short video clips of a single event (i.e., single-scene videos). Meanwhile, recent large language models (LLMs) have demonstrated their capability in generating layouts and programs to control downstream visual modules. This prompts an important question: can we leverage the knowledge embedded in these LLMs for temporally consistent long video generation? In this paper, we propose VideoDirectorGPT, a novel framework for consistent multi-scene video generatio","authors_text":"Abhay Zala, Han Lin, Jaemin Cho, Mohit Bansal","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:36:26Z","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15091","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:de8c124a350b8e478592fdedfe1e8e73d1e82bfede97011b642182d3849bf014","target":"record","created_at":"2026-07-05T08:43:23Z","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":"91e06fdab4f579fec178bdf8cad6f6ddf00535baf459d5a7ab72777a771ce65a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-26T17:36:26Z","title_canon_sha256":"ed1f9c92447326189a7f2b05ea23dd5388504a2883864b1d71d9f8cbb5db9a14"},"schema_version":"1.0","source":{"id":"2309.15091","kind":"arxiv","version":2}},"canonical_sha256":"53b444a28fc6724e36d237bff775227f6e635093734157a805abd9886e94e3f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53b444a28fc6724e36d237bff775227f6e635093734157a805abd9886e94e3f0","first_computed_at":"2026-07-05T08:43:23.422840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:23.422840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JP3WNrpAOa33eNzZzr/AoAbjbHwv9J4SU2ZcWkP9HVE74XXKBw2P23DDaR+nq/jItjBkoMpUD2H50IP3ugR/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:23.423326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15091","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de8c124a350b8e478592fdedfe1e8e73d1e82bfede97011b642182d3849bf014","sha256:657e9d6e8bdc8ca0779a4ed96f1e495e391fdedabe7911d8e0f96d039343c059"],"state_sha256":"1db99f8c3100517501f8305d2c1199fa3361107c30b8717b9c9a506df9aad99e"}