{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MKKSBJRZB6UJKZXE7FQI3IGLIX","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":"ccd02e1a70993004a0b02f4da330a3ae85cbb70d517deee0497a0d99dd9d91cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:56:05Z","title_canon_sha256":"af3bbb419cefd766304d789fd2e1427f3ae1b610ab175dc570ad4d5a3cac5acd"},"schema_version":"1.0","source":{"id":"2412.04440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04440","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04440v1","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04440","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"MKKSBJRZB6UJ","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"MKKSBJRZB6UJKZXE","created_at":"2026-07-05T09:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"MKKSBJRZ","created_at":"2026-07-05T09:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:52fa755eee699cd178642c277150bd68ecabdbcc1584e680064be7a72b58ca6a","target":"graph","created_at":"2026-07-05T09:45:03Z","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/2412.04440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video generation models have shown significant progress in the recent years. However, they still struggle with generating complex dynamic scenes based on compositional text prompts, such as attribute binding for multiple objects, temporal dynamics associated with different objects, and interactions between objects. Our key motivation is that complex tasks can be decomposed into simpler ones, each handled by a role-specialized MLLM agent. Multiple agents can collaborate together to achieve collective intelligence for complex goals. We propose GenMAC, an iterative, multi-agent framework ","authors_text":"Kaiyi Huang, Xihui Liu, Xuefei Ning, Yukun Huang, Yu Wang, Zinan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:56:05Z","title":"GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04440","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":"sha256:40628d3cea54b973fbda8dba9151c49568f1f278d1a3fc48fff67a09ad44d7f9","target":"record","created_at":"2026-07-05T09:45:03Z","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":"ccd02e1a70993004a0b02f4da330a3ae85cbb70d517deee0497a0d99dd9d91cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:56:05Z","title_canon_sha256":"af3bbb419cefd766304d789fd2e1427f3ae1b610ab175dc570ad4d5a3cac5acd"},"schema_version":"1.0","source":{"id":"2412.04440","kind":"arxiv","version":1}},"canonical_sha256":"629520a6390fa89566e4f9608da0cb45c24231acc93fbfdd678b796b7a18f590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"629520a6390fa89566e4f9608da0cb45c24231acc93fbfdd678b796b7a18f590","first_computed_at":"2026-07-05T09:45:03.944040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:03.944040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/t6I8E+FTtBpg4WueIotEgm7NwqFv4LakMWQIeNXMli6nE+8LA1H6n2sK6EY3uR3JbY6z6QbzaHXyV0dRhN6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:03.944518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40628d3cea54b973fbda8dba9151c49568f1f278d1a3fc48fff67a09ad44d7f9","sha256:52fa755eee699cd178642c277150bd68ecabdbcc1584e680064be7a72b58ca6a"],"state_sha256":"9977f5d1956721d5887e761ddcac94d33a3e930e66ecae38d5d66738fc64ab0a"}