{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JPLSPCTJWO2J6DXKKGX57OOYVJ","short_pith_number":"pith:JPLSPCTJ","schema_version":"1.0","canonical_sha256":"4bd7278a69b3b49f0eea51afdfb9d8aa7f66b4791a3c494686655bd698312d38","source":{"kind":"arxiv","id":"2408.11788","version":1},"attestation_state":"computed","paper":{"title":"DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.SE"],"primary_cat":"cs.AI","authors_text":"Daniel Tang, Dingwei Tan, Jacques Klein, Saad Ezzini, Tegawend F. Bissyand, Zhifei Xie","submitted_at":"2024-08-21T17:21:13Z","abstract_excerpt":"Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \\texttt{DreamFactory}, an LLM-based framework that tackles this challenge. \\texttt{DreamFactory} leverages multi-agent collaboration principles and a Key Frames Iteration Design Method to ensure consistency and style across long videos. It utilizes Chain of Thought (COT) to address uncertainties inherent in large language models. \\texttt{DreamFactory} generates long, stylistically coherent, and complex videos. Evaluating these long-form videos presents a challeng"},"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":"2408.11788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T17:21:13Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SE"],"title_canon_sha256":"bcb23575f46012907dc842570a546119218753cb315e2e056c21628857bfe76f","abstract_canon_sha256":"ae53006edc46e73c1bd6fad4f118b81aea517a29ac63b003f0205bb22cf7fad0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:49.105421Z","signature_b64":"eULwGzBPKgSxS6nfR6BEwf7n6Dj5LveXez3SpRnnvZSo6HMikky42ViomhHQDwAiYePfkTfm5yCgTINAIKR4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd7278a69b3b49f0eea51afdfb9d8aa7f66b4791a3c494686655bd698312d38","last_reissued_at":"2026-07-05T08:57:49.104960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:49.104960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.SE"],"primary_cat":"cs.AI","authors_text":"Daniel Tang, Dingwei Tan, Jacques Klein, Saad Ezzini, Tegawend F. Bissyand, Zhifei Xie","submitted_at":"2024-08-21T17:21:13Z","abstract_excerpt":"Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \\texttt{DreamFactory}, an LLM-based framework that tackles this challenge. \\texttt{DreamFactory} leverages multi-agent collaboration principles and a Key Frames Iteration Design Method to ensure consistency and style across long videos. It utilizes Chain of Thought (COT) to address uncertainties inherent in large language models. \\texttt{DreamFactory} generates long, stylistically coherent, and complex videos. Evaluating these long-form videos presents a challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11788","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/2408.11788/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":"2408.11788","created_at":"2026-07-05T08:57:49.105018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11788v1","created_at":"2026-07-05T08:57:49.105018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11788","created_at":"2026-07-05T08:57:49.105018+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPLSPCTJWO2J","created_at":"2026-07-05T08:57:49.105018+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPLSPCTJWO2J6DXK","created_at":"2026-07-05T08:57:49.105018+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPLSPCTJ","created_at":"2026-07-05T08:57:49.105018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20799","citing_title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18591","citing_title":"Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09639","citing_title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07636","citing_title":"Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10543","citing_title":"TIE: Time Interval Encoding for Video Generation over Events","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15199","citing_title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03315","citing_title":"StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12496","citing_title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10543","citing_title":"TIE: Time Interval Encoding for Video Generation over Events","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ","json":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ.json","graph_json":"https://pith.science/api/pith-number/JPLSPCTJWO2J6DXKKGX57OOYVJ/graph.json","events_json":"https://pith.science/api/pith-number/JPLSPCTJWO2J6DXKKGX57OOYVJ/events.json","paper":"https://pith.science/paper/JPLSPCTJ"},"agent_actions":{"view_html":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ","download_json":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ.json","view_paper":"https://pith.science/paper/JPLSPCTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11788&json=true","fetch_graph":"https://pith.science/api/pith-number/JPLSPCTJWO2J6DXKKGX57OOYVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JPLSPCTJWO2J6DXKKGX57OOYVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ/action/storage_attestation","attest_author":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ/action/author_attestation","sign_citation":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ/action/citation_signature","submit_replication":"https://pith.science/pith/JPLSPCTJWO2J6DXKKGX57OOYVJ/action/replication_record"}},"created_at":"2026-07-05T08:57:49.105018+00:00","updated_at":"2026-07-05T08:57:49.105018+00:00"}