{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7K22JRNHNBZWNFPNS3EZVGPPEV","short_pith_number":"pith:7K22JRNH","schema_version":"1.0","canonical_sha256":"fab5a4c5a768736695ed96c99a99ef254bdbab74d677f2ca4dc7434b46655964","source":{"kind":"arxiv","id":"2507.18634","version":1},"attestation_state":"computed","paper":{"title":"Captain Cinema: Towards Short Movie Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Ceyuan Yang, Gordon Wetzstein, Junfei Xiao, Lu Jiang, Lvmin Zhang, Maneesh Agrawala, Shengqu Cai, Yang Zhao, Yuwei Guo","submitted_at":"2025-07-24T17:59:56Z","abstract_excerpt":"We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up "},"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":"2507.18634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"e05add5767dfd1918b316161817c5969d540fd5a1fe88ab8c7faa95ba14c73db","abstract_canon_sha256":"022d8cc4331d662b19ea6984b9913bb1a7e27b052de1479edf5d1d9b4a885f19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:51.390395Z","signature_b64":"h8rOzeuFSlBKxa6/dZ2e4XwoZ62X+WaXYVwWQv8Fr6ChuZPoZuRQKDMflch3IN9/MkLdR0zGqtQUnwMp4/nvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fab5a4c5a768736695ed96c99a99ef254bdbab74d677f2ca4dc7434b46655964","last_reissued_at":"2026-07-05T11:42:51.389839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:51.389839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Captain Cinema: Towards Short Movie Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Ceyuan Yang, Gordon Wetzstein, Junfei Xiao, Lu Jiang, Lvmin Zhang, Maneesh Agrawala, Shengqu Cai, Yang Zhao, Yuwei Guo","submitted_at":"2025-07-24T17:59:56Z","abstract_excerpt":"We present Captain Cinema, a generation framework for short movie generation. Given a detailed textual description of a movie storyline, our approach firstly generates a sequence of keyframes that outline the entire narrative, which ensures long-range coherence in both the storyline and visual appearance (e.g., scenes and characters). We refer to this step as top-down keyframe planning. These keyframes then serve as conditioning signals for a video synthesis model, which supports long context learning, to produce the spatio-temporal dynamics between them. This step is referred to as bottom-up "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18634","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/2507.18634/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":"2507.18634","created_at":"2026-07-05T11:42:51.389912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18634v1","created_at":"2026-07-05T11:42:51.389912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18634","created_at":"2026-07-05T11:42:51.389912+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K22JRNHNBZW","created_at":"2026-07-05T11:42:51.389912+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K22JRNHNBZWNFPN","created_at":"2026-07-05T11:42:51.389912+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K22JRNH","created_at":"2026-07-05T11:42:51.389912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24107","citing_title":"DramaDirector: Geometry-Guided Short Drama Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22370","citing_title":"Towards Error-Free Long Video Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21661","citing_title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating","ref_index":47,"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":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25266","citing_title":"DeltaCam: Differential Intrinsic Camera Modeling for Video Generation","ref_index":38,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01843","citing_title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18233","citing_title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09195","citing_title":"Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17195","citing_title":"DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV","json":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV.json","graph_json":"https://pith.science/api/pith-number/7K22JRNHNBZWNFPNS3EZVGPPEV/graph.json","events_json":"https://pith.science/api/pith-number/7K22JRNHNBZWNFPNS3EZVGPPEV/events.json","paper":"https://pith.science/paper/7K22JRNH"},"agent_actions":{"view_html":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV","download_json":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV.json","view_paper":"https://pith.science/paper/7K22JRNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18634&json=true","fetch_graph":"https://pith.science/api/pith-number/7K22JRNHNBZWNFPNS3EZVGPPEV/graph.json","fetch_events":"https://pith.science/api/pith-number/7K22JRNHNBZWNFPNS3EZVGPPEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV/action/storage_attestation","attest_author":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV/action/author_attestation","sign_citation":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV/action/citation_signature","submit_replication":"https://pith.science/pith/7K22JRNHNBZWNFPNS3EZVGPPEV/action/replication_record"}},"created_at":"2026-07-05T11:42:51.389912+00:00","updated_at":"2026-07-05T11:42:51.389912+00:00"}