{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WQ5V7BDSOHS7KSL2T6IK5Q2OZU","short_pith_number":"pith:WQ5V7BDS","schema_version":"1.0","canonical_sha256":"b43b5f847271e5f5497a9f90aec34ecd2736213b906e4c6ecd60afa944fe0d91","source":{"kind":"arxiv","id":"2307.06940","version":1},"attestation_state":"computed","paper":{"title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Weng, Haoxin Chen, Jinbo Xing, Menghan Xia, Qifeng Chen, Xiaodong Cun, Xintao Wang, Yingqing He, Ying Shan, Yong Zhang, Yuan Gong","submitted_at":"2023-07-13T17:57:13Z","abstract_excerpt":"Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of existing video clips and synthesize a coherent storytelling video by customizing their appearances. We achieve this by developing a framework comprised of two functional modules: (i) Motion Structure Retrieval, which provides video candidates with desired scene or motion context described by query texts, and (ii) Structure-Guided Text-to-Video Synthesis, which ge"},"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":"2307.06940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:57:13Z","cross_cats_sorted":[],"title_canon_sha256":"0c639b9be88cac65ce9aae69e43930bee9ea61cf0abcfb01d749a8da2b54daee","abstract_canon_sha256":"6d4f92e3d3f03636bcf77b089d236030db0efa0a92f8a6cdf238ece749191457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:39.731126Z","signature_b64":"GokWzfaxebtYacsUq8xP9/aSCc1vAEKLCGqWEyuxhZAzHD3w8hVglsCGXVGX8+CehuvhLM+FBKLv9GYylYOMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43b5f847271e5f5497a9f90aec34ecd2736213b906e4c6ecd60afa944fe0d91","last_reissued_at":"2026-07-05T06:30:39.730688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:39.730688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Weng, Haoxin Chen, Jinbo Xing, Menghan Xia, Qifeng Chen, Xiaodong Cun, Xintao Wang, Yingqing He, Ying Shan, Yong Zhang, Yuan Gong","submitted_at":"2023-07-13T17:57:13Z","abstract_excerpt":"Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of existing video clips and synthesize a coherent storytelling video by customizing their appearances. We achieve this by developing a framework comprised of two functional modules: (i) Motion Structure Retrieval, which provides video candidates with desired scene or motion context described by query texts, and (ii) Structure-Guided Text-to-Video Synthesis, which ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06940","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/2307.06940/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":"2307.06940","created_at":"2026-07-05T06:30:39.730745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06940v1","created_at":"2026-07-05T06:30:39.730745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06940","created_at":"2026-07-05T06:30:39.730745+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ5V7BDSOHS7","created_at":"2026-07-05T06:30:39.730745+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ5V7BDSOHS7KSL2","created_at":"2026-07-05T06:30:39.730745+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ5V7BDS","created_at":"2026-07-05T06:30:39.730745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.06310","citing_title":"Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16819","citing_title":"Character-Centered Dialogue Generation from Scene-Level Prompts","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20206","citing_title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2501.04001","citing_title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15127","citing_title":"MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU","json":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU.json","graph_json":"https://pith.science/api/pith-number/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/graph.json","events_json":"https://pith.science/api/pith-number/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/events.json","paper":"https://pith.science/paper/WQ5V7BDS"},"agent_actions":{"view_html":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU","download_json":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU.json","view_paper":"https://pith.science/paper/WQ5V7BDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06940&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/action/storage_attestation","attest_author":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/action/author_attestation","sign_citation":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/action/citation_signature","submit_replication":"https://pith.science/pith/WQ5V7BDSOHS7KSL2T6IK5Q2OZU/action/replication_record"}},"created_at":"2026-07-05T06:30:39.730745+00:00","updated_at":"2026-07-05T06:30:39.730745+00:00"}