{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JQUPLKQMZ3F4VK67OSTO5GHRVW","short_pith_number":"pith:JQUPLKQM","schema_version":"1.0","canonical_sha256":"4c28f5aa0ccecbcaabdf74a6ee98f1ada4af7ca48ec3a3c9b80b78002426f0b8","source":{"kind":"arxiv","id":"2505.23465","version":1},"attestation_state":"computed","paper":{"title":"Semantics-Aware Human Motion Generation from Audio Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Chao Dong, Mingyuan Zhang, Shihao Zou, Shiyao Yu, Zi-An Wang","submitted_at":"2025-05-29T14:16:27Z","abstract_excerpt":"Recent advances in interactive technologies have highlighted the prominence of audio signals for semantic encoding. This paper explores a new task, where audio signals are used as conditioning inputs to generate motions that align with the semantics of the audio. Unlike text-based interactions, audio provides a more natural and intuitive communication method. However, existing methods typically focus on matching motions with music or speech rhythms, which often results in a weak connection between the semantics of the audio and generated motions. We propose an end-to-end framework using a mask"},"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":"2505.23465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T14:16:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"16f220077b55ef1fcd8ebe593bf551cd12dc59e3a9c670a467c4bb2ddfda7452","abstract_canon_sha256":"679a9b87033ed76572798fc5e6ee4128c9e1fe75f7760920af71cf44829bf863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:02.261434Z","signature_b64":"lvnic1Whe93G0xTbUIe/CJqGHnygcxAjV6nXpdW3VlScIIRdmXFwk5gV+ZFLTQWt/QF39pV7moTzZ8jf8NvNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c28f5aa0ccecbcaabdf74a6ee98f1ada4af7ca48ec3a3c9b80b78002426f0b8","last_reissued_at":"2026-07-05T11:12:02.260910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:02.260910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantics-Aware Human Motion Generation from Audio Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Chao Dong, Mingyuan Zhang, Shihao Zou, Shiyao Yu, Zi-An Wang","submitted_at":"2025-05-29T14:16:27Z","abstract_excerpt":"Recent advances in interactive technologies have highlighted the prominence of audio signals for semantic encoding. This paper explores a new task, where audio signals are used as conditioning inputs to generate motions that align with the semantics of the audio. Unlike text-based interactions, audio provides a more natural and intuitive communication method. However, existing methods typically focus on matching motions with music or speech rhythms, which often results in a weak connection between the semantics of the audio and generated motions. We propose an end-to-end framework using a mask"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23465","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/2505.23465/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":"2505.23465","created_at":"2026-07-05T11:12:02.260986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23465v1","created_at":"2026-07-05T11:12:02.260986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23465","created_at":"2026-07-05T11:12:02.260986+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQUPLKQMZ3F4","created_at":"2026-07-05T11:12:02.260986+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQUPLKQMZ3F4VK67","created_at":"2026-07-05T11:12:02.260986+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQUPLKQM","created_at":"2026-07-05T11:12:02.260986+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/JQUPLKQMZ3F4VK67OSTO5GHRVW","json":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW.json","graph_json":"https://pith.science/api/pith-number/JQUPLKQMZ3F4VK67OSTO5GHRVW/graph.json","events_json":"https://pith.science/api/pith-number/JQUPLKQMZ3F4VK67OSTO5GHRVW/events.json","paper":"https://pith.science/paper/JQUPLKQM"},"agent_actions":{"view_html":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW","download_json":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW.json","view_paper":"https://pith.science/paper/JQUPLKQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23465&json=true","fetch_graph":"https://pith.science/api/pith-number/JQUPLKQMZ3F4VK67OSTO5GHRVW/graph.json","fetch_events":"https://pith.science/api/pith-number/JQUPLKQMZ3F4VK67OSTO5GHRVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW/action/storage_attestation","attest_author":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW/action/author_attestation","sign_citation":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW/action/citation_signature","submit_replication":"https://pith.science/pith/JQUPLKQMZ3F4VK67OSTO5GHRVW/action/replication_record"}},"created_at":"2026-07-05T11:12:02.260986+00:00","updated_at":"2026-07-05T11:12:02.260986+00:00"}