{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XANCHSWKEKT47MNPYUGQFK4SZN","short_pith_number":"pith:XANCHSWK","schema_version":"1.0","canonical_sha256":"b81a23caca22a7cfb1afc50d02ab92cb65e05322c63a6a218d39a8f79f902008","source":{"kind":"arxiv","id":"2502.17414","version":2},"attestation_state":"computed","paper":{"title":"X-Dancer: Expressive Music to Human Dance Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wang, Chenxu Zhang, Di Chang, Guoxian Song, Hongyi Xu, Linjie Luo, Xin Chen, You Xie, Zeyuan Chen","submitted_at":"2025-02-24T18:47:54Z","abstract_excerpt":"We present X-Dancer, a novel zero-shot music-driven image animation pipeline that creates diverse and long-range lifelike human dance videos from a single static image. As its core, we introduce a unified transformer-diffusion framework, featuring an autoregressive transformer model that synthesize extended and music-synchronized token sequences for 2D body, head and hands poses, which then guide a diffusion model to produce coherent and realistic dance video frames. Unlike traditional methods that primarily generate human motion in 3D, X-Dancer addresses data limitations and enhances scalabil"},"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":"2502.17414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"5f927a0b22589f591ec121ff3c4520420efaa330e7adfba705ac243b54ba567c","abstract_canon_sha256":"8211953a41861d8d07f770edbde10113d1f7181e3da89d5abd6ef6ad1a434701"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:32.607924Z","signature_b64":"/4F+qVnvhLooD+cI6QMyQULTjMhzuJTFqzi+7Kcsjn75l5pQoImkDfOzaOCLMJUGd17Bg2Z5xNsDmHGaZlHQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b81a23caca22a7cfb1afc50d02ab92cb65e05322c63a6a218d39a8f79f902008","last_reissued_at":"2026-07-05T11:35:32.606889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:32.606889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-Dancer: Expressive Music to Human Dance Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wang, Chenxu Zhang, Di Chang, Guoxian Song, Hongyi Xu, Linjie Luo, Xin Chen, You Xie, Zeyuan Chen","submitted_at":"2025-02-24T18:47:54Z","abstract_excerpt":"We present X-Dancer, a novel zero-shot music-driven image animation pipeline that creates diverse and long-range lifelike human dance videos from a single static image. As its core, we introduce a unified transformer-diffusion framework, featuring an autoregressive transformer model that synthesize extended and music-synchronized token sequences for 2D body, head and hands poses, which then guide a diffusion model to produce coherent and realistic dance video frames. Unlike traditional methods that primarily generate human motion in 3D, X-Dancer addresses data limitations and enhances scalabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17414","kind":"arxiv","version":2},"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/2502.17414/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":"2502.17414","created_at":"2026-07-05T11:35:32.607292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17414v2","created_at":"2026-07-05T11:35:32.607292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17414","created_at":"2026-07-05T11:35:32.607292+00:00"},{"alias_kind":"pith_short_12","alias_value":"XANCHSWKEKT4","created_at":"2026-07-05T11:35:32.607292+00:00"},{"alias_kind":"pith_short_16","alias_value":"XANCHSWKEKT47MNP","created_at":"2026-07-05T11:35:32.607292+00:00"},{"alias_kind":"pith_short_8","alias_value":"XANCHSWK","created_at":"2026-07-05T11:35:32.607292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30019","citing_title":"OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN","json":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN.json","graph_json":"https://pith.science/api/pith-number/XANCHSWKEKT47MNPYUGQFK4SZN/graph.json","events_json":"https://pith.science/api/pith-number/XANCHSWKEKT47MNPYUGQFK4SZN/events.json","paper":"https://pith.science/paper/XANCHSWK"},"agent_actions":{"view_html":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN","download_json":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN.json","view_paper":"https://pith.science/paper/XANCHSWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17414&json=true","fetch_graph":"https://pith.science/api/pith-number/XANCHSWKEKT47MNPYUGQFK4SZN/graph.json","fetch_events":"https://pith.science/api/pith-number/XANCHSWKEKT47MNPYUGQFK4SZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN/action/storage_attestation","attest_author":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN/action/author_attestation","sign_citation":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN/action/citation_signature","submit_replication":"https://pith.science/pith/XANCHSWKEKT47MNPYUGQFK4SZN/action/replication_record"}},"created_at":"2026-07-05T11:35:32.607292+00:00","updated_at":"2026-07-05T11:35:32.607292+00:00"}