{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JQUPLKQMZ3F4VK67OSTO5GHRVW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"679a9b87033ed76572798fc5e6ee4128c9e1fe75f7760920af71cf44829bf863","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T14:16:27Z","title_canon_sha256":"16f220077b55ef1fcd8ebe593bf551cd12dc59e3a9c670a467c4bb2ddfda7452"},"schema_version":"1.0","source":{"id":"2505.23465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23465","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23465v1","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23465","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"JQUPLKQMZ3F4","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"JQUPLKQMZ3F4VK67","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"JQUPLKQM","created_at":"2026-07-05T11:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:6d2c0e93dee0ac594c6267e11f9b9a2a4d2d117fdca6f917ca0cfd8db4c4c0ce","target":"graph","created_at":"2026-07-05T11:12:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.23465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Dong, Mingyuan Zhang, Shihao Zou, Shiyao Yu, Zi-An Wang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T14:16:27Z","title":"Semantics-Aware Human Motion Generation from Audio Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23465","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2de9967439631e52d57ca9d1e3d15af4674f3be79b95f1166f72e8b1fbfb50e","target":"record","created_at":"2026-07-05T11:12:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"679a9b87033ed76572798fc5e6ee4128c9e1fe75f7760920af71cf44829bf863","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T14:16:27Z","title_canon_sha256":"16f220077b55ef1fcd8ebe593bf551cd12dc59e3a9c670a467c4bb2ddfda7452"},"schema_version":"1.0","source":{"id":"2505.23465","kind":"arxiv","version":1}},"canonical_sha256":"4c28f5aa0ccecbcaabdf74a6ee98f1ada4af7ca48ec3a3c9b80b78002426f0b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c28f5aa0ccecbcaabdf74a6ee98f1ada4af7ca48ec3a3c9b80b78002426f0b8","first_computed_at":"2026-07-05T11:12:02.260910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:02.260910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvnic1Whe93G0xTbUIe/CJqGHnygcxAjV6nXpdW3VlScIIRdmXFwk5gV+ZFLTQWt/QF39pV7moTzZ8jf8NvNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:02.261434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2de9967439631e52d57ca9d1e3d15af4674f3be79b95f1166f72e8b1fbfb50e","sha256:6d2c0e93dee0ac594c6267e11f9b9a2a4d2d117fdca6f917ca0cfd8db4c4c0ce"],"state_sha256":"2d57f487f31c7308847402b7a70fae77116181d3822e3ce735077fb679e22d29"}