{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYM7J7IXBPNZRVGV4XFBQUNTHF","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":"c5e3f24cc61e9556817811554347d7f3b3d5aa6fc46631be2a7294fe9070778b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T13:02:12Z","title_canon_sha256":"93559d1fdf6d615ddcbffd4d6cade30be3dc478728e16dfa63e7acef2b4ab71d"},"schema_version":"1.0","source":{"id":"2507.06812","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06812","created_at":"2026-07-05T11:36:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06812v2","created_at":"2026-07-05T11:36:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06812","created_at":"2026-07-05T11:36:35Z"},{"alias_kind":"pith_short_12","alias_value":"XYM7J7IXBPNZ","created_at":"2026-07-05T11:36:35Z"},{"alias_kind":"pith_short_16","alias_value":"XYM7J7IXBPNZRVGV","created_at":"2026-07-05T11:36:35Z"},{"alias_kind":"pith_short_8","alias_value":"XYM7J7IX","created_at":"2026-07-05T11:36:35Z"}],"graph_snapshots":[{"event_id":"sha256:5ff950d9fdf15f0242dc55c0648f14a3425f2a54e121568fbadfdcbdaba13ac9","target":"graph","created_at":"2026-07-05T11:36:35Z","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/2507.06812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Co-speech gesture video generation aims to synthesize realistic, audio-aligned videos of speakers, complete with synchronized facial expressions and body gestures. This task presents challenges due to the significant one-to-many mapping between audio and visual content, further complicated by the scarcity of large-scale public datasets and high computational demands. We propose a lightweight framework that utilizes 2D full-body skeletons as an efficient auxiliary condition to bridge audio signals with visual outputs. Our approach introduces a diffusion model conditioned on fine-grained audio s","authors_text":"Changxing Ding, Shaoli Huang, Shenbo Xie, Xuelin Chen, Xu Yang, Yifei Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T13:02:12Z","title":"Democratizing High-Fidelity Co-Speech Gesture Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06812","kind":"arxiv","version":2},"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":"sha256:496519d183cc260cf8880877e23b1adfb1b5b1ae42f93f23ada4555d723445dd","target":"record","created_at":"2026-07-05T11:36:35Z","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":"c5e3f24cc61e9556817811554347d7f3b3d5aa6fc46631be2a7294fe9070778b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T13:02:12Z","title_canon_sha256":"93559d1fdf6d615ddcbffd4d6cade30be3dc478728e16dfa63e7acef2b4ab71d"},"schema_version":"1.0","source":{"id":"2507.06812","kind":"arxiv","version":2}},"canonical_sha256":"be19f4fd170bdb98d4d5e5ca1851b33950a59c41585deeabe3f8839e04dc36cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be19f4fd170bdb98d4d5e5ca1851b33950a59c41585deeabe3f8839e04dc36cf","first_computed_at":"2026-07-05T11:36:35.054368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:35.054368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kYWEZW0RKvskXO//ufiaOi8GfJ8+L3tbeNISbKodvFSwU9mXOSvsP2V7RisVAI4gjASklJXGUEHf6lqrQ2W2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:35.054786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06812","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:496519d183cc260cf8880877e23b1adfb1b5b1ae42f93f23ada4555d723445dd","sha256:5ff950d9fdf15f0242dc55c0648f14a3425f2a54e121568fbadfdcbdaba13ac9"],"state_sha256":"40ffdb75a68db4eeaa2e2f0aec497ea6ec7d104aad1d2f0cb6b6923d8a26448b"}