{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KNO4PN43A4PFB7RLURBPIUCYBS","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":"74779ca0084dae692fce10239cdbc6a934df6f2c028d7d27dfd9f36ed84c1443","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-05T16:30:46Z","title_canon_sha256":"90491d9cecb6bf199a2f829a5d77ee7cf95a073ba466370f71649a89c18ef96f"},"schema_version":"1.0","source":{"id":"2410.04221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04221","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04221v1","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04221","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"KNO4PN43A4PF","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"KNO4PN43A4PFB7RL","created_at":"2026-07-05T09:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"KNO4PN43","created_at":"2026-07-05T09:16:31Z"}],"graph_snapshots":[{"event_id":"sha256:bf66c1643a81311cd9c2e076815ec85ee09d9beae2d7018039d3354190babbe1","target":"graph","created_at":"2026-07-05T09:16:31Z","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/2410.04221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present TANGO, a framework for generating co-speech body-gesture videos. Given a few-minute, single-speaker reference video and target speech audio, TANGO produces high-fidelity videos with synchronized body gestures. TANGO builds on Gesture Video Reenactment (GVR), which splits and retrieves video clips using a directed graph structure - representing video frames as nodes and valid transitions as edges. We address two key limitations of GVR: audio-motion misalignment and visual artifacts in GAN-generated transition frames. In particular, (i) we propose retrieving gestures using latent feat","authors_text":"Haiyang Liu, Qiaoge Li, Shigeru Kuriyama, Takafumi Taketomi, Tomoya Akiyama, Xingchao Yang, Yuantian Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-05T16:30:46Z","title":"TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04221","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":"sha256:4cd17cd50d472cd6b41db45f4eace5cd0acac9aaf3e32b8949b99a3d31bd5296","target":"record","created_at":"2026-07-05T09:16:31Z","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":"74779ca0084dae692fce10239cdbc6a934df6f2c028d7d27dfd9f36ed84c1443","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-05T16:30:46Z","title_canon_sha256":"90491d9cecb6bf199a2f829a5d77ee7cf95a073ba466370f71649a89c18ef96f"},"schema_version":"1.0","source":{"id":"2410.04221","kind":"arxiv","version":1}},"canonical_sha256":"535dc7b79b071e50fe2ba442f450580cae9bf19f635995bfcf9db1361efcae81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"535dc7b79b071e50fe2ba442f450580cae9bf19f635995bfcf9db1361efcae81","first_computed_at":"2026-07-05T09:16:31.024278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:31.024278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1pZ/CXd4E/3TYcz17n7wYa0kaNQxDN/e9iRbbv/tjPvzY86JrvYgVluN3/Ou02WPsoNTDBjTdDmg7mg92XvAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:31.024772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cd17cd50d472cd6b41db45f4eace5cd0acac9aaf3e32b8949b99a3d31bd5296","sha256:bf66c1643a81311cd9c2e076815ec85ee09d9beae2d7018039d3354190babbe1"],"state_sha256":"65d6ca8eec4c5d5352348826b5ceac2494eef1457fc9bcb51309cea19816b10b"}