{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UHX5XBVZIHNOT7YFT6S7NAK6JY","short_pith_number":"pith:UHX5XBVZ","schema_version":"1.0","canonical_sha256":"a1efdb86b941dae9ff059fa5f6815e4e309a690684acf3343c52c1b77a519aff","source":{"kind":"arxiv","id":"2411.04925","version":2},"attestation_state":"computed","paper":{"title":"StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CV","authors_text":"Jianqi Chen, Jin Jiang, Mingfei Han, Panwen Hu, Shengcai Liao, Xiaodan Liang, Xiaojun Chang","submitted_at":"2024-11-07T18:00:33Z","abstract_excerpt":"The advent of AI-Generated Content (AIGC) has spurred research into automated video generation to streamline conventional processes. However, automating storytelling video production, particularly for customized narratives, remains challenging due to the complexity of maintaining subject consistency across shots. While existing approaches like Mora and AesopAgent integrate multiple agents for Story-to-Video (S2V) generation, they fall short in preserving protagonist consistency and supporting Customized Storytelling Video Generation (CSVG). To address these limitations, we propose StoryAgent, "},"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":"2411.04925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:00:33Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ec4ff50b22fd6f1c228411021967bc4fe745ae101575e07ca7def25af420c7ff","abstract_canon_sha256":"21381ec2eab629468aa77a8730a77864ba912390c84f148c5318e5efa38859bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:40.806457Z","signature_b64":"YPi4OYv4pDgzw0GUavRHJ4aCVV9sQQ7sGpJcziQ0f3/L0rlT9/w1COuk6pFSeV+LyLMNeBvHu8VVBHfSpln0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1efdb86b941dae9ff059fa5f6815e4e309a690684acf3343c52c1b77a519aff","last_reissued_at":"2026-07-05T09:33:40.805882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:40.805882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CV","authors_text":"Jianqi Chen, Jin Jiang, Mingfei Han, Panwen Hu, Shengcai Liao, Xiaodan Liang, Xiaojun Chang","submitted_at":"2024-11-07T18:00:33Z","abstract_excerpt":"The advent of AI-Generated Content (AIGC) has spurred research into automated video generation to streamline conventional processes. However, automating storytelling video production, particularly for customized narratives, remains challenging due to the complexity of maintaining subject consistency across shots. While existing approaches like Mora and AesopAgent integrate multiple agents for Story-to-Video (S2V) generation, they fall short in preserving protagonist consistency and supporting Customized Storytelling Video Generation (CSVG). To address these limitations, we propose StoryAgent, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04925","kind":"arxiv","version":2},"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/2411.04925/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":"2411.04925","created_at":"2026-07-05T09:33:40.805939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04925v2","created_at":"2026-07-05T09:33:40.805939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04925","created_at":"2026-07-05T09:33:40.805939+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHX5XBVZIHNO","created_at":"2026-07-05T09:33:40.805939+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHX5XBVZIHNOT7YF","created_at":"2026-07-05T09:33:40.805939+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHX5XBVZ","created_at":"2026-07-05T09:33:40.805939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07534","citing_title":"Infinite Worlds with Versatile Interactions","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24107","citing_title":"DramaDirector: Geometry-Guided Short Drama Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20799","citing_title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01312","citing_title":"KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04797","citing_title":"Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07649","citing_title":"ViMax: Agentic Video Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23610","citing_title":"EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23508","citing_title":"DrawVideo: Generating Long Video from Storyboard Keyframe Sketches","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22144","citing_title":"One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05564","citing_title":"ProPhy: Progressive Physical Alignment for Dynamic World Simulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12496","citing_title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23579","citing_title":"CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10383","citing_title":"Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16958","citing_title":"Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY","json":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY.json","graph_json":"https://pith.science/api/pith-number/UHX5XBVZIHNOT7YFT6S7NAK6JY/graph.json","events_json":"https://pith.science/api/pith-number/UHX5XBVZIHNOT7YFT6S7NAK6JY/events.json","paper":"https://pith.science/paper/UHX5XBVZ"},"agent_actions":{"view_html":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY","download_json":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY.json","view_paper":"https://pith.science/paper/UHX5XBVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04925&json=true","fetch_graph":"https://pith.science/api/pith-number/UHX5XBVZIHNOT7YFT6S7NAK6JY/graph.json","fetch_events":"https://pith.science/api/pith-number/UHX5XBVZIHNOT7YFT6S7NAK6JY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY/action/storage_attestation","attest_author":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY/action/author_attestation","sign_citation":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY/action/citation_signature","submit_replication":"https://pith.science/pith/UHX5XBVZIHNOT7YFT6S7NAK6JY/action/replication_record"}},"created_at":"2026-07-05T09:33:40.805939+00:00","updated_at":"2026-07-05T09:33:40.805939+00:00"}