{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IJ6YYVJV75E2SMBPMXEL7VMHUE","short_pith_number":"pith:IJ6YYVJV","schema_version":"1.0","canonical_sha256":"427d8c5535ff49a9302f65c8bfd587a13108b7ad60e596017ffed19907539a22","source":{"kind":"arxiv","id":"2606.09639","version":1},"attestation_state":"computed","paper":{"title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jiangning Zhang, Lizhuang Ma, Qianyu Zhou, Qingdong He, Teng Hu, Xiangtai Li, Yuheng Chen, Yuji Wang, Zhucun Xue","submitted_at":"2026-06-08T15:35:51Z","abstract_excerpt":"The fidelity and structural diversity of training datasets fundamentally determine the capabilities of video generation models. While commercial systems showremarkableabilitytogeneratecinematicnarratives, the progress of open-source models remains limited by the scarcity of high-quality training data. To bridge this gap, we introduce CineDance-1M, a large-scale, open research Text-to-Audio-Video (T2AV) dataset designed specifically for multi-shot, long-form joint audio-video generation. Averaging 92.8 seconds and 24.2 continuous shots per video, it provides configurable, structured annotations"},"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":"2606.09639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T15:35:51Z","cross_cats_sorted":[],"title_canon_sha256":"0e675751219cb3a8f509354e46fd137ff5b2d725d8fd204551d26040f61fc67a","abstract_canon_sha256":"e61ae71e9393e2869765e8bd1d517b0448f898d305e0807754ad2914ccd74417"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:00.642733Z","signature_b64":"8mc6ToKn45zZktOZzpO2LPGaNR3gXE5UuGuDAkVp3mVpQE2yKsqYC/at2Sv1ai1iqUCTZ8YluUDqqk5HYXIRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"427d8c5535ff49a9302f65c8bfd587a13108b7ad60e596017ffed19907539a22","last_reissued_at":"2026-06-09T02:09:00.641853Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:00.641853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jiangning Zhang, Lizhuang Ma, Qianyu Zhou, Qingdong He, Teng Hu, Xiangtai Li, Yuheng Chen, Yuji Wang, Zhucun Xue","submitted_at":"2026-06-08T15:35:51Z","abstract_excerpt":"The fidelity and structural diversity of training datasets fundamentally determine the capabilities of video generation models. While commercial systems showremarkableabilitytogeneratecinematicnarratives, the progress of open-source models remains limited by the scarcity of high-quality training data. To bridge this gap, we introduce CineDance-1M, a large-scale, open research Text-to-Audio-Video (T2AV) dataset designed specifically for multi-shot, long-form joint audio-video generation. Averaging 92.8 seconds and 24.2 continuous shots per video, it provides configurable, structured annotations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09639","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/2606.09639/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":"2606.09639","created_at":"2026-06-09T02:09:00.642004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09639v1","created_at":"2026-06-09T02:09:00.642004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09639","created_at":"2026-06-09T02:09:00.642004+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJ6YYVJV75E2","created_at":"2026-06-09T02:09:00.642004+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJ6YYVJV75E2SMBP","created_at":"2026-06-09T02:09:00.642004+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJ6YYVJV","created_at":"2026-06-09T02:09:00.642004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE","json":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE.json","graph_json":"https://pith.science/api/pith-number/IJ6YYVJV75E2SMBPMXEL7VMHUE/graph.json","events_json":"https://pith.science/api/pith-number/IJ6YYVJV75E2SMBPMXEL7VMHUE/events.json","paper":"https://pith.science/paper/IJ6YYVJV"},"agent_actions":{"view_html":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE","download_json":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE.json","view_paper":"https://pith.science/paper/IJ6YYVJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09639&json=true","fetch_graph":"https://pith.science/api/pith-number/IJ6YYVJV75E2SMBPMXEL7VMHUE/graph.json","fetch_events":"https://pith.science/api/pith-number/IJ6YYVJV75E2SMBPMXEL7VMHUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE/action/storage_attestation","attest_author":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE/action/author_attestation","sign_citation":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE/action/citation_signature","submit_replication":"https://pith.science/pith/IJ6YYVJV75E2SMBPMXEL7VMHUE/action/replication_record"}},"created_at":"2026-06-09T02:09:00.642004+00:00","updated_at":"2026-06-09T02:09:00.642004+00:00"}