{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PIEIHLAX7CQ7FKMK5FLC5YC456","short_pith_number":"pith:PIEIHLAX","schema_version":"1.0","canonical_sha256":"7a0883ac17f8a1f2a98ae9562ee05cefacdf6a0f9d7b108f6b82fb8e149cca72","source":{"kind":"arxiv","id":"2607.09581","version":1},"attestation_state":"computed","paper":{"title":"Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Guangyuan Wang, Li Hu, Mingyang Huang, Peng Zhang","submitted_at":"2026-07-10T16:30:29Z","abstract_excerpt":"Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Existing approaches, whether they rely on intermediate 3D skeletons or on end-to-end video synthesis, suffer from temporal drift, identity inconsistency, and repetitive motion patterns when extended to longer horizons. To address these limitations, we propose a novel hierarchical framework for minute-scale coherent music-to-dance generation. Our me"},"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":"2607.09581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T16:30:29Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"493913b1629a139ae477b0c2c678ac821b0832152fa80d776960ffa9a7a694e6","abstract_canon_sha256":"f7d2c6623f6e2d26a7a032991b8cc7ebf2529e8ef0060f3b717ffe4682fa7c54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:21.682751Z","signature_b64":"VcGkWuBbCSZBQtqTN8MwuPfe2g8O5l8TD4SKp0sQugP8DeDQ3NqJFRlC85Ud2+BLL4oQzr1c0LaBInBDpk0hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a0883ac17f8a1f2a98ae9562ee05cefacdf6a0f9d7b108f6b82fb8e149cca72","last_reissued_at":"2026-07-13T01:20:21.681705Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:21.681705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Guangyuan Wang, Li Hu, Mingyang Huang, Peng Zhang","submitted_at":"2026-07-10T16:30:29Z","abstract_excerpt":"Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Existing approaches, whether they rely on intermediate 3D skeletons or on end-to-end video synthesis, suffer from temporal drift, identity inconsistency, and repetitive motion patterns when extended to longer horizons. To address these limitations, we propose a novel hierarchical framework for minute-scale coherent music-to-dance generation. Our me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09581","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/2607.09581/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":"2607.09581","created_at":"2026-07-13T01:20:21.682266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09581v1","created_at":"2026-07-13T01:20:21.682266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09581","created_at":"2026-07-13T01:20:21.682266+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIEIHLAX7CQ7","created_at":"2026-07-13T01:20:21.682266+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIEIHLAX7CQ7FKMK","created_at":"2026-07-13T01:20:21.682266+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIEIHLAX","created_at":"2026-07-13T01:20:21.682266+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/PIEIHLAX7CQ7FKMK5FLC5YC456","json":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456.json","graph_json":"https://pith.science/api/pith-number/PIEIHLAX7CQ7FKMK5FLC5YC456/graph.json","events_json":"https://pith.science/api/pith-number/PIEIHLAX7CQ7FKMK5FLC5YC456/events.json","paper":"https://pith.science/paper/PIEIHLAX"},"agent_actions":{"view_html":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456","download_json":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456.json","view_paper":"https://pith.science/paper/PIEIHLAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09581&json=true","fetch_graph":"https://pith.science/api/pith-number/PIEIHLAX7CQ7FKMK5FLC5YC456/graph.json","fetch_events":"https://pith.science/api/pith-number/PIEIHLAX7CQ7FKMK5FLC5YC456/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456/action/storage_attestation","attest_author":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456/action/author_attestation","sign_citation":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456/action/citation_signature","submit_replication":"https://pith.science/pith/PIEIHLAX7CQ7FKMK5FLC5YC456/action/replication_record"}},"created_at":"2026-07-13T01:20:21.682266+00:00","updated_at":"2026-07-13T01:20:21.682266+00:00"}