{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BALCNMVHHNQV75XZ2JWZ4PXIKH","short_pith_number":"pith:BALCNMVH","schema_version":"1.0","canonical_sha256":"081626b2a73b615ff6f9d26d9e3ee851e61e58bce4fb08a641943b221d3d8abc","source":{"kind":"arxiv","id":"2503.05242","version":1},"attestation_state":"computed","paper":{"title":"MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenliang Li, Jiahao Mei, Ji Zhang, Mengyue Wu, Ming Yan, Shaopeng Lai, Xuenan Xu, Yuning Wu","submitted_at":"2025-03-07T08:53:10Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) and artificial intelligence-generated content (AIGC) has accelerated AI-native applications, such as AI-based storybooks that automate engaging story production for children. However, challenges remain in improving story attractiveness, enriching storytelling expressiveness, and developing open-source evaluation benchmarks and frameworks. Therefore, we propose and opensource MM-StoryAgent, which creates immersive narrated video storybooks with refined plots, role-consistent images, and multi-channel audio. MM-StoryAgent designs a multi-agen"},"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":"2503.05242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T08:53:10Z","cross_cats_sorted":[],"title_canon_sha256":"c73b336a8ed08c8f16b5e4375b625e71102bd891e232a5a838968fbc75c06851","abstract_canon_sha256":"75b5dd1c17378ec01d73676d1864f77c582fcaf78e175f3385e236a8a2abbf21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:24.831558Z","signature_b64":"cp+5t/N3TVh/LKIluqoSefoiMZc8JElyXZwpYLagONujfMYUQtE7v2zV0iqbtDcUs5q6qQkV7IrpYmVueuqRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081626b2a73b615ff6f9d26d9e3ee851e61e58bce4fb08a641943b221d3d8abc","last_reissued_at":"2026-07-05T10:26:24.830993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:24.830993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenliang Li, Jiahao Mei, Ji Zhang, Mengyue Wu, Ming Yan, Shaopeng Lai, Xuenan Xu, Yuning Wu","submitted_at":"2025-03-07T08:53:10Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) and artificial intelligence-generated content (AIGC) has accelerated AI-native applications, such as AI-based storybooks that automate engaging story production for children. However, challenges remain in improving story attractiveness, enriching storytelling expressiveness, and developing open-source evaluation benchmarks and frameworks. Therefore, we propose and opensource MM-StoryAgent, which creates immersive narrated video storybooks with refined plots, role-consistent images, and multi-channel audio. MM-StoryAgent designs a multi-agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05242","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/2503.05242/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":"2503.05242","created_at":"2026-07-05T10:26:24.831059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05242v1","created_at":"2026-07-05T10:26:24.831059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05242","created_at":"2026-07-05T10:26:24.831059+00:00"},{"alias_kind":"pith_short_12","alias_value":"BALCNMVHHNQV","created_at":"2026-07-05T10:26:24.831059+00:00"},{"alias_kind":"pith_short_16","alias_value":"BALCNMVHHNQV75XZ","created_at":"2026-07-05T10:26:24.831059+00:00"},{"alias_kind":"pith_short_8","alias_value":"BALCNMVH","created_at":"2026-07-05T10:26:24.831059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24107","citing_title":"DramaDirector: Geometry-Guided Short Drama Generation","ref_index":31,"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":53,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01312","citing_title":"KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07636","citing_title":"Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16958","citing_title":"Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH","json":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH.json","graph_json":"https://pith.science/api/pith-number/BALCNMVHHNQV75XZ2JWZ4PXIKH/graph.json","events_json":"https://pith.science/api/pith-number/BALCNMVHHNQV75XZ2JWZ4PXIKH/events.json","paper":"https://pith.science/paper/BALCNMVH"},"agent_actions":{"view_html":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH","download_json":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH.json","view_paper":"https://pith.science/paper/BALCNMVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05242&json=true","fetch_graph":"https://pith.science/api/pith-number/BALCNMVHHNQV75XZ2JWZ4PXIKH/graph.json","fetch_events":"https://pith.science/api/pith-number/BALCNMVHHNQV75XZ2JWZ4PXIKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH/action/storage_attestation","attest_author":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH/action/author_attestation","sign_citation":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH/action/citation_signature","submit_replication":"https://pith.science/pith/BALCNMVHHNQV75XZ2JWZ4PXIKH/action/replication_record"}},"created_at":"2026-07-05T10:26:24.831059+00:00","updated_at":"2026-07-05T10:26:24.831059+00:00"}