{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA","short_pith_number":"pith:6Q7HUTUZ","schema_version":"1.0","canonical_sha256":"f43e7a4e99e62970f4faf67b96e742b02cd56041b6555a7ab6cb82e0af261c24","source":{"kind":"arxiv","id":"2106.13871","version":3},"attestation_state":"computed","paper":{"title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andr\\'e Holzapfel, Guillermo Valle-P\\'erez, Gustav Eje Henter, Jonas Beskow, Pierre-Yves Oudeyer, Simon Alexanderson","submitted_at":"2021-06-25T20:14:28Z","abstract_excerpt":"Dance requires skillful composition of complex movements that follow rhythmic, tonal and timbral features of music. Formally, generating dance conditioned on a piece of music can be expressed as a problem of modelling a high-dimensional continuous motion signal, conditioned on an audio signal. In this work we make two contributions to tackle this problem. First, we present a novel probabilistic autoregressive architecture that models the distribution over future poses with a normalizing flow conditioned on previous poses as well as music context, using a multimodal transformer encoder. Second,"},"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":"2106.13871","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-25T20:14:28Z","cross_cats_sorted":["cs.GR","cs.LG","eess.AS"],"title_canon_sha256":"4a1ac2086dbbb4d83a56a8492e65db45fab95495f518c8ce1031b5903384bc41","abstract_canon_sha256":"f2c40443187de0de115e3a0b6831675526cd9785f16d88873516583a8dcd0f20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:51.506233Z","signature_b64":"1G0Jxl8Bu3J0F7UoIXXn3LK4Fzw46SGjirxEsw882O7mE9ZfsRC+piO7sMWLInR8BCK3V7c7fxR75o2GVAPqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f43e7a4e99e62970f4faf67b96e742b02cd56041b6555a7ab6cb82e0af261c24","last_reissued_at":"2026-07-05T04:30:51.505878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:51.505878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andr\\'e Holzapfel, Guillermo Valle-P\\'erez, Gustav Eje Henter, Jonas Beskow, Pierre-Yves Oudeyer, Simon Alexanderson","submitted_at":"2021-06-25T20:14:28Z","abstract_excerpt":"Dance requires skillful composition of complex movements that follow rhythmic, tonal and timbral features of music. Formally, generating dance conditioned on a piece of music can be expressed as a problem of modelling a high-dimensional continuous motion signal, conditioned on an audio signal. In this work we make two contributions to tackle this problem. First, we present a novel probabilistic autoregressive architecture that models the distribution over future poses with a normalizing flow conditioned on previous poses as well as music context, using a multimodal transformer encoder. Second,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13871","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/2106.13871/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":"2106.13871","created_at":"2026-07-05T04:30:51.505933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13871v3","created_at":"2026-07-05T04:30:51.505933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13871","created_at":"2026-07-05T04:30:51.505933+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Q7HUTUZ4YUX","created_at":"2026-07-05T04:30:51.505933+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Q7HUTUZ4YUXB5H2","created_at":"2026-07-05T04:30:51.505933+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Q7HUTUZ","created_at":"2026-07-05T04:30:51.505933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18052","citing_title":"DanceGraph: A Complementary Architecture for Synchronous Dancing Online","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA","json":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA.json","graph_json":"https://pith.science/api/pith-number/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/graph.json","events_json":"https://pith.science/api/pith-number/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/events.json","paper":"https://pith.science/paper/6Q7HUTUZ"},"agent_actions":{"view_html":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA","download_json":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA.json","view_paper":"https://pith.science/paper/6Q7HUTUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13871&json=true","fetch_graph":"https://pith.science/api/pith-number/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/graph.json","fetch_events":"https://pith.science/api/pith-number/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/action/storage_attestation","attest_author":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/action/author_attestation","sign_citation":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/action/citation_signature","submit_replication":"https://pith.science/pith/6Q7HUTUZ4YUXB5H26Z5ZNZ2CWA/action/replication_record"}},"created_at":"2026-07-05T04:30:51.505933+00:00","updated_at":"2026-07-05T04:30:51.505933+00:00"}