{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HOCDG4Y4SSIQU3LDMUUMBWJRKP","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":"ac4b84c317675954c8171a35bc3ae785ad1fa33ee12a246da8814cce67c13343","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T08:19:18Z","title_canon_sha256":"b758788ba948e51a9606ea4f75f0f71b43cc4a18ab97f2fb8abc3d49f8df5d9c"},"schema_version":"1.0","source":{"id":"2504.08344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08344","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08344v1","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08344","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"pith_short_12","alias_value":"HOCDG4Y4SSIQ","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"pith_short_16","alias_value":"HOCDG4Y4SSIQU3LD","created_at":"2026-07-05T10:47:47Z"},{"alias_kind":"pith_short_8","alias_value":"HOCDG4Y4","created_at":"2026-07-05T10:47:47Z"}],"graph_snapshots":[{"event_id":"sha256:e79debbbde1976d10da106941fb5be830b031a5cc7744b3a7891d38b3ab026f2","target":"graph","created_at":"2026-07-05T10:47:47Z","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/2504.08344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains challenging in gesture-to-video systems. In order to improve the generation effect, previous works adopted complex input and training strategies and required a large amount of data sets for pre-training, which brought inconvenience to practical applications. We propose a simple one-stage training method and a temporal inference method based on a diffusion mod","authors_text":"Jun Yu, Mei HanJing Xiao, Peng Chang, Qiang Ling, Renda Li, Xiaohua Qi, Ziyi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T08:19:18Z","title":"EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08344","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":"sha256:35088edb5a4a9b35804d8047ceb2fa3b1f1b7c89962f3cded69220ee1baa635d","target":"record","created_at":"2026-07-05T10:47:47Z","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":"ac4b84c317675954c8171a35bc3ae785ad1fa33ee12a246da8814cce67c13343","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T08:19:18Z","title_canon_sha256":"b758788ba948e51a9606ea4f75f0f71b43cc4a18ab97f2fb8abc3d49f8df5d9c"},"schema_version":"1.0","source":{"id":"2504.08344","kind":"arxiv","version":1}},"canonical_sha256":"3b8433731c94910a6d636528c0d93153e585d4f90fbd6061799f911c6d3d6cd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b8433731c94910a6d636528c0d93153e585d4f90fbd6061799f911c6d3d6cd4","first_computed_at":"2026-07-05T10:47:47.500574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:47.500574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AYLrCtd3Hiq6/i5qWKbABhM0h4nhLtycCWvWtDM7JKyoW71dG7m40mvUTnrApY77FmNvcfM4mfREBFc4EQ/zDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:47.501048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35088edb5a4a9b35804d8047ceb2fa3b1f1b7c89962f3cded69220ee1baa635d","sha256:e79debbbde1976d10da106941fb5be830b031a5cc7744b3a7891d38b3ab026f2"],"state_sha256":"c373c71e6bd128aadd06e8d9e2950ee1ea621a4c3a1037471b407469ddb5e6f3"}