{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NE2CVBYWCW5S5EJAKJIQBEQS55","short_pith_number":"pith:NE2CVBYW","canonical_record":{"source":{"id":"2404.01862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T11:40:34Z","cross_cats_sorted":["cs.HC","cs.MM"],"title_canon_sha256":"ce0c0a1ae77a0a08c8b9b7aec318a3caaad140f5fe2fbd4ca5876a13816f3188","abstract_canon_sha256":"66a6f94b27e60e06d3c6ebdb2176c75e339b275a15dcfaa8640ec31677e2a8cd"},"schema_version":"1.0"},"canonical_sha256":"69342a871615bb2e91205251009212ef49162de7a5c256751ded27b7dbb0c87a","source":{"kind":"arxiv","id":"2404.01862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01862","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01862v1","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01862","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"NE2CVBYWCW5S","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"NE2CVBYWCW5S5EJA","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"NE2CVBYW","created_at":"2026-07-05T08:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NE2CVBYWCW5S5EJAKJIQBEQS55","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T11:40:34Z","cross_cats_sorted":["cs.HC","cs.MM"],"title_canon_sha256":"ce0c0a1ae77a0a08c8b9b7aec318a3caaad140f5fe2fbd4ca5876a13816f3188","abstract_canon_sha256":"66a6f94b27e60e06d3c6ebdb2176c75e339b275a15dcfaa8640ec31677e2a8cd"},"schema_version":"1.0"},"canonical_sha256":"69342a871615bb2e91205251009212ef49162de7a5c256751ded27b7dbb0c87a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:32.753198Z","signature_b64":"np3MFT9BVM4nDWEge9iLcRQjqEdxE9Dh4PSnZeFzJOphanptnhuqOnUy19NoIyQ1ONvjSQOio85jUKnEqttYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69342a871615bb2e91205251009212ef49162de7a5c256751ded27b7dbb0c87a","last_reissued_at":"2026-07-05T08:03:32.752692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:32.752692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01862","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1jDuUQ0JgdeKWPicM3/4+a86YhHCjn9hPkHVgBIO5C7ukWfVDOAQq/6b+/w9628cD1xOQLavoAeUuvxBCxcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T10:08:38.843008Z"},"content_sha256":"1faae8ebf01f31ce5def9c49de5018477c20400e183b77da2e542c7c01999764","schema_version":"1.0","event_id":"sha256:1faae8ebf01f31ce5def9c49de5018477c20400e183b77da2e542c7c01999764"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NE2CVBYWCW5S5EJAKJIQBEQS55","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.MM"],"primary_cat":"cs.CV","authors_text":"Minglei Li, Qiaochu Huang, Sicheng Yang, Songcen Xu, Xiaofei Wu, Xu He, Zhensong Zhang, Zhiwei Lin, Zhiyi Chen, Zhiyong Wu","submitted_at":"2024-04-02T11:40:34Z","abstract_excerpt":"Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01862","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.01862/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s4YAJyOUa1e5Q+vvg2+T7amGFh66/vF7h6kSReYtfZchPRNAt1paX0WrtnQ10FdPyu327GlbdruZXJApvpPtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T10:08:38.843523Z"},"content_sha256":"8449d438d9097ee6f899d00e97fcec2cf95c67dace6794b6c43135bad2dacc97","schema_version":"1.0","event_id":"sha256:8449d438d9097ee6f899d00e97fcec2cf95c67dace6794b6c43135bad2dacc97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NE2CVBYWCW5S5EJAKJIQBEQS55/bundle.json","state_url":"https://pith.science/pith/NE2CVBYWCW5S5EJAKJIQBEQS55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NE2CVBYWCW5S5EJAKJIQBEQS55/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T10:08:38Z","links":{"resolver":"https://pith.science/pith/NE2CVBYWCW5S5EJAKJIQBEQS55","bundle":"https://pith.science/pith/NE2CVBYWCW5S5EJAKJIQBEQS55/bundle.json","state":"https://pith.science/pith/NE2CVBYWCW5S5EJAKJIQBEQS55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NE2CVBYWCW5S5EJAKJIQBEQS55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NE2CVBYWCW5S5EJAKJIQBEQS55","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":"66a6f94b27e60e06d3c6ebdb2176c75e339b275a15dcfaa8640ec31677e2a8cd","cross_cats_sorted":["cs.HC","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T11:40:34Z","title_canon_sha256":"ce0c0a1ae77a0a08c8b9b7aec318a3caaad140f5fe2fbd4ca5876a13816f3188"},"schema_version":"1.0","source":{"id":"2404.01862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01862","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01862v1","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01862","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"NE2CVBYWCW5S","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"NE2CVBYWCW5S5EJA","created_at":"2026-07-05T08:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"NE2CVBYW","created_at":"2026-07-05T08:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:8449d438d9097ee6f899d00e97fcec2cf95c67dace6794b6c43135bad2dacc97","target":"graph","created_at":"2026-07-05T08:03:32Z","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/2404.01862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Co-speech gestures, if presented in the lively form of videos, can achieve superior visual effects in human-machine interaction. While previous works mostly generate structural human skeletons, resulting in the omission of appearance information, we focus on the direct generation of audio-driven co-speech gesture videos in this work. There are two main challenges: 1) A suitable motion feature is needed to describe complex human movements with crucial appearance information. 2) Gestures and speech exhibit inherent dependencies and should be temporally aligned even of arbitrary length. To solve ","authors_text":"Minglei Li, Qiaochu Huang, Sicheng Yang, Songcen Xu, Xiaofei Wu, Xu He, Zhensong Zhang, Zhiwei Lin, Zhiyi Chen, Zhiyong Wu","cross_cats":["cs.HC","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T11:40:34Z","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01862","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":"sha256:1faae8ebf01f31ce5def9c49de5018477c20400e183b77da2e542c7c01999764","target":"record","created_at":"2026-07-05T08:03:32Z","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":"66a6f94b27e60e06d3c6ebdb2176c75e339b275a15dcfaa8640ec31677e2a8cd","cross_cats_sorted":["cs.HC","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T11:40:34Z","title_canon_sha256":"ce0c0a1ae77a0a08c8b9b7aec318a3caaad140f5fe2fbd4ca5876a13816f3188"},"schema_version":"1.0","source":{"id":"2404.01862","kind":"arxiv","version":1}},"canonical_sha256":"69342a871615bb2e91205251009212ef49162de7a5c256751ded27b7dbb0c87a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69342a871615bb2e91205251009212ef49162de7a5c256751ded27b7dbb0c87a","first_computed_at":"2026-07-05T08:03:32.752692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:32.752692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"np3MFT9BVM4nDWEge9iLcRQjqEdxE9Dh4PSnZeFzJOphanptnhuqOnUy19NoIyQ1ONvjSQOio85jUKnEqttYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:32.753198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1faae8ebf01f31ce5def9c49de5018477c20400e183b77da2e542c7c01999764","sha256:8449d438d9097ee6f899d00e97fcec2cf95c67dace6794b6c43135bad2dacc97"],"state_sha256":"b30b38cacb0cc575e2d7201301fb4c76fec3e5603ab19aa78c8264b94d036568"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Koj3SfOuKtrUrI2EmsBuvasqPMzQyd+UJ8MwV3SIxGvYcG0Qc0j8Lys7yFVYMjGC1y0ihXCbuFu2+QHKHm4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T10:08:38.847018Z","bundle_sha256":"2a7403ef26250c50e1ca8bb5cefc218da8f8ff4862994b0ae317f9c92f83f85b"}}