{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4JEP5VYFIBMRBRVADCLIWIUGHV","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":"4f7557cfa7b005722dad030250b309b0ab5f271705fab79732a7f2796d4a5e73","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T15:03:58Z","title_canon_sha256":"1d57e387ac283524fefc6a785e5ab4f438a0444c9620bc56a878657cae967410"},"schema_version":"1.0","source":{"id":"2505.03603","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03603","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03603v5","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03603","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_12","alias_value":"4JEP5VYFIBMR","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_16","alias_value":"4JEP5VYFIBMRBRVA","created_at":"2026-07-05T11:20:11Z"},{"alias_kind":"pith_short_8","alias_value":"4JEP5VYF","created_at":"2026-07-05T11:20:11Z"}],"graph_snapshots":[{"event_id":"sha256:ed013945ed992af29f3b466228dfa7eeebb9ffdfabe91d201fac2f673cffc546","target":"graph","created_at":"2026-07-05T11:20:11Z","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/2505.03603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-driven human animation technology is widely used in human-computer interaction, and the emergence of diffusion models has further advanced its development. Currently, most methods rely on multi-stage generation and intermediate representations, resulting in long inference time and issues with generation quality in specific foreground regions and audio-motion consistency. These shortcomings are primarily due to the lack of localized fine-grained supervised guidance. To address above challenges, we propose Parts-aware Audio-driven Human Animation, PAHA, a unit enhancement and guidance fram","authors_text":"J.F. Wu, J.N. Zhang, S.Z. Zhou, T. Hu, Y.B. Wang","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T15:03:58Z","title":"A Unit Enhancement and Guidance Framework for Audio-Driven Avatar Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03603","kind":"arxiv","version":5},"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:aa5745bb03d931f8c7ea6b622a1271e28783c6cb72bd6a1eebde6efc95c47c91","target":"record","created_at":"2026-07-05T11:20:11Z","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":"4f7557cfa7b005722dad030250b309b0ab5f271705fab79732a7f2796d4a5e73","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T15:03:58Z","title_canon_sha256":"1d57e387ac283524fefc6a785e5ab4f438a0444c9620bc56a878657cae967410"},"schema_version":"1.0","source":{"id":"2505.03603","kind":"arxiv","version":5}},"canonical_sha256":"e248fed705405910c6a018968b22863d4c1fe17e74fad8d05a24755e42a8cdf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e248fed705405910c6a018968b22863d4c1fe17e74fad8d05a24755e42a8cdf6","first_computed_at":"2026-07-05T11:20:11.907839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:11.907839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2/mqivuAhoP7B/1lAbPqFEkTwA6FDVc1hpc+kH7V0fmsjWWsk/83bGnXH4zgmyTjnBNvzyiEVNQ8rlEQ/zg6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:11.908487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03603","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa5745bb03d931f8c7ea6b622a1271e28783c6cb72bd6a1eebde6efc95c47c91","sha256:ed013945ed992af29f3b466228dfa7eeebb9ffdfabe91d201fac2f673cffc546"],"state_sha256":"f5ff355a8fc7e70caa58c4f6a5409fcae861f25ee6ec2463031ed4bd0f34ea36"}