{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FGSFKX3VX5O2XJAD6Q3C22B6QV","short_pith_number":"pith:FGSFKX3V","canonical_record":{"source":{"id":"2501.01798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T13:14:52Z","cross_cats_sorted":[],"title_canon_sha256":"dfbe48c9085e36a33341b87beae0e1c99acd7b4fa2c2a6b4fbcd076ff3d0bccc","abstract_canon_sha256":"38ec06538e8deec930fe7e334c29e4a2e4fbf900755c9f13262aa6e2cfd292f8"},"schema_version":"1.0"},"canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","source":{"kind":"arxiv","id":"2501.01798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01798","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01798v1","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01798","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"FGSFKX3VX5O2","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"pith_short_16","alias_value":"FGSFKX3VX5O2XJAD","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"pith_short_8","alias_value":"FGSFKX3V","created_at":"2026-07-05T09:56:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FGSFKX3VX5O2XJAD6Q3C22B6QV","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T13:14:52Z","cross_cats_sorted":[],"title_canon_sha256":"dfbe48c9085e36a33341b87beae0e1c99acd7b4fa2c2a6b4fbcd076ff3d0bccc","abstract_canon_sha256":"38ec06538e8deec930fe7e334c29e4a2e4fbf900755c9f13262aa6e2cfd292f8"},"schema_version":"1.0"},"canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:41.136421Z","signature_b64":"T9EktBFJ89WUXKKy2StgwG/SRxcUn/LJwgpiS5Q26rZ156PKyhMPfsiGWCUJqyy9+NKxK96qj1wWw2nGfgRiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","last_reissued_at":"2026-07-05T09:56:41.135966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:41.135966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01798","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":"2026-07-05T09:56:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOG9K3BNloRdscati5LwDvXYY4o7pjyBd/3U7B5DutblHAbdYmuyrVwgMH0wtQQNiBwXtTR920Pa7+UMzaULBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:33:46.306763Z"},"content_sha256":"85a2fbedf136242426b90077fa46c0213dac70a4e48c70bc875cd845e478ea03","schema_version":"1.0","event_id":"sha256:85a2fbedf136242426b90077fa46c0213dac70a4e48c70bc875cd845e478ea03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FGSFKX3VX5O2XJAD6Q3C22B6QV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dajiang Wu, Jun Lv, Junshi Huang, Qili Wang, Zihang Xu","submitted_at":"2025-01-03T13:14:52Z","abstract_excerpt":"Significant progress has been made in talking-face video generation research; however, precise lip-audio synchronization and high visual quality remain challenging in editing lip shapes based on input audio. This paper introduces JoyGen, a novel two-stage framework for talking-face generation, comprising audio-driven lip motion generation and visual appearance synthesis. In the first stage, a 3D reconstruction model and an audio2motion model predict identity and expression coefficients respectively. Next, by integrating audio features with a facial depth map, we provide comprehensive supervisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01798","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/2501.01798/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":"2026-07-05T09:56:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mq+owwF55OXEjISxmny6hteh2J5eCXAy8jWgChd+BW95YGwMjJizsw+l+BIAj5oc0CUwiuSKJHNK6GZTY7jgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:33:46.307678Z"},"content_sha256":"6a8a8ac509ea0861ffbee7760db0c430e631fa230a5564b3287a642798247cf1","schema_version":"1.0","event_id":"sha256:6a8a8ac509ea0861ffbee7760db0c430e631fa230a5564b3287a642798247cf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/bundle.json","state_url":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/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":"2026-08-08T16:33:46Z","links":{"resolver":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV","bundle":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/bundle.json","state":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FGSFKX3VX5O2XJAD6Q3C22B6QV","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":"38ec06538e8deec930fe7e334c29e4a2e4fbf900755c9f13262aa6e2cfd292f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T13:14:52Z","title_canon_sha256":"dfbe48c9085e36a33341b87beae0e1c99acd7b4fa2c2a6b4fbcd076ff3d0bccc"},"schema_version":"1.0","source":{"id":"2501.01798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01798","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01798v1","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01798","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"FGSFKX3VX5O2","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"pith_short_16","alias_value":"FGSFKX3VX5O2XJAD","created_at":"2026-07-05T09:56:41Z"},{"alias_kind":"pith_short_8","alias_value":"FGSFKX3V","created_at":"2026-07-05T09:56:41Z"}],"graph_snapshots":[{"event_id":"sha256:6a8a8ac509ea0861ffbee7760db0c430e631fa230a5564b3287a642798247cf1","target":"graph","created_at":"2026-07-05T09:56:41Z","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/2501.01798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant progress has been made in talking-face video generation research; however, precise lip-audio synchronization and high visual quality remain challenging in editing lip shapes based on input audio. This paper introduces JoyGen, a novel two-stage framework for talking-face generation, comprising audio-driven lip motion generation and visual appearance synthesis. In the first stage, a 3D reconstruction model and an audio2motion model predict identity and expression coefficients respectively. Next, by integrating audio features with a facial depth map, we provide comprehensive supervisi","authors_text":"Dajiang Wu, Jun Lv, Junshi Huang, Qili Wang, Zihang Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T13:14:52Z","title":"JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01798","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":"sha256:85a2fbedf136242426b90077fa46c0213dac70a4e48c70bc875cd845e478ea03","target":"record","created_at":"2026-07-05T09:56:41Z","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":"38ec06538e8deec930fe7e334c29e4a2e4fbf900755c9f13262aa6e2cfd292f8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T13:14:52Z","title_canon_sha256":"dfbe48c9085e36a33341b87beae0e1c99acd7b4fa2c2a6b4fbcd076ff3d0bccc"},"schema_version":"1.0","source":{"id":"2501.01798","kind":"arxiv","version":1}},"canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","first_computed_at":"2026-07-05T09:56:41.135966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:41.135966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T9EktBFJ89WUXKKy2StgwG/SRxcUn/LJwgpiS5Q26rZ156PKyhMPfsiGWCUJqyy9+NKxK96qj1wWw2nGfgRiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:41.136421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85a2fbedf136242426b90077fa46c0213dac70a4e48c70bc875cd845e478ea03","sha256:6a8a8ac509ea0861ffbee7760db0c430e631fa230a5564b3287a642798247cf1"],"state_sha256":"2948e26cfbc8053d5480cd3423af421a372f24d0bebc884ceac3cd4b68a790f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wLMJ0l8ah3TnDryhuGAszSGFSUuxHeunEI6ng2csCIFCg3YwuHHHOy0GEvysOk+9p6B9dwFXz4at63eIZNcBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:33:46.312970Z","bundle_sha256":"ec3bebe38f7c3bb9d410cbe1f4e5b881830f6eea4184656ab2846a2e4db89ce4"}}