{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L44EXAZRI3ZPA3HEJ5PVCHQVJS","short_pith_number":"pith:L44EXAZR","schema_version":"1.0","canonical_sha256":"5f384b833146f2f06ce44f5f511e154ca05622b97b2f8e569c55b18b68750565","source":{"kind":"arxiv","id":"2601.17737","version":3},"attestation_state":"computed","paper":{"title":"The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Cheng Deng, Chenyu Mu, Erkun Yang, Fanghua Ye, Huang Liu, Jiadi Yao, Linus, Qu Yang, Ruotian Ma, Wanshun Chen, Xiaolong Li, Xingyu Chen, Xin He, Zhaopeng Tu, Zihao Yi","submitted_at":"2026-01-25T08:10:28Z","abstract_excerpt":"Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, these models struggle to generate long-form, coherent narratives from high-level concepts like dialogue, revealing a ``semantic gap'' between a creative idea and its cinematic execution. To bridge this gap, we introduce a novel, end-to-end agentic framework for dialogue-to-cinematic-video generation. Central to our framework is ScripterAgent, a model trained to translate coarse dialogue into a fine-grained, executable cinematic script. To enable this, we c"},"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":"2601.17737","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-25T08:10:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"910aa12d30ebf55a0d579d540e5b5c344aefa12154598cd56f2872ce40900422","abstract_canon_sha256":"d2a6de4692f5be8c46ac3fcf8af20c90ca0ef4606ed25be11e0be7e6340cbd29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:35.613403Z","signature_b64":"KpyFHLjNKmLFEPtP8ZZ+4thGhYWPGWbquOIhtJcQjMw8fl5h40Fev1p+yP+COAHMxlkif9VzQxVxFedMn80FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f384b833146f2f06ce44f5f511e154ca05622b97b2f8e569c55b18b68750565","last_reissued_at":"2026-05-28T01:04:35.612915Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:35.612915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhao, Cheng Deng, Chenyu Mu, Erkun Yang, Fanghua Ye, Huang Liu, Jiadi Yao, Linus, Qu Yang, Ruotian Ma, Wanshun Chen, Xiaolong Li, Xingyu Chen, Xin He, Zhaopeng Tu, Zihao Yi","submitted_at":"2026-01-25T08:10:28Z","abstract_excerpt":"Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, these models struggle to generate long-form, coherent narratives from high-level concepts like dialogue, revealing a ``semantic gap'' between a creative idea and its cinematic execution. To bridge this gap, we introduce a novel, end-to-end agentic framework for dialogue-to-cinematic-video generation. Central to our framework is ScripterAgent, a model trained to translate coarse dialogue into a fine-grained, executable cinematic script. To enable this, we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17737","kind":"arxiv","version":3},"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/2601.17737/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":"2601.17737","created_at":"2026-05-28T01:04:35.612971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.17737v3","created_at":"2026-05-28T01:04:35.612971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17737","created_at":"2026-05-28T01:04:35.612971+00:00"},{"alias_kind":"pith_short_12","alias_value":"L44EXAZRI3ZP","created_at":"2026-05-28T01:04:35.612971+00:00"},{"alias_kind":"pith_short_16","alias_value":"L44EXAZRI3ZPA3HE","created_at":"2026-05-28T01:04:35.612971+00:00"},{"alias_kind":"pith_short_8","alias_value":"L44EXAZR","created_at":"2026-05-28T01:04:35.612971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.22144","citing_title":"One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15127","citing_title":"MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS","json":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS.json","graph_json":"https://pith.science/api/pith-number/L44EXAZRI3ZPA3HEJ5PVCHQVJS/graph.json","events_json":"https://pith.science/api/pith-number/L44EXAZRI3ZPA3HEJ5PVCHQVJS/events.json","paper":"https://pith.science/paper/L44EXAZR"},"agent_actions":{"view_html":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS","download_json":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS.json","view_paper":"https://pith.science/paper/L44EXAZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.17737&json=true","fetch_graph":"https://pith.science/api/pith-number/L44EXAZRI3ZPA3HEJ5PVCHQVJS/graph.json","fetch_events":"https://pith.science/api/pith-number/L44EXAZRI3ZPA3HEJ5PVCHQVJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS/action/storage_attestation","attest_author":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS/action/author_attestation","sign_citation":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS/action/citation_signature","submit_replication":"https://pith.science/pith/L44EXAZRI3ZPA3HEJ5PVCHQVJS/action/replication_record"}},"created_at":"2026-05-28T01:04:35.612971+00:00","updated_at":"2026-05-28T01:04:35.612971+00:00"}