{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WSWSV5UKIA23F2PKWFPFYANYNR","short_pith_number":"pith:WSWSV5UK","canonical_record":{"source":{"id":"2503.14517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T02:52:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"458f0752db2d4e46bad2eb64e55bb24f05ef884de08d717b37455c44d2fe5cc7","abstract_canon_sha256":"df87b1e3308d003d074ef6ae3839a4deaa2a639088d9dd193b1b5d0e957d5c87"},"schema_version":"1.0"},"canonical_sha256":"b4ad2af68a4035b2e9eab15e5c01b86c5982ca9aabaf181c08643e0b672eaab6","source":{"kind":"arxiv","id":"2503.14517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14517","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14517v1","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14517","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"WSWSV5UKIA23","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"WSWSV5UKIA23F2PK","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"WSWSV5UK","created_at":"2026-07-05T10:34:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WSWSV5UKIA23F2PKWFPFYANYNR","target":"record","payload":{"canonical_record":{"source":{"id":"2503.14517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T02:52:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"458f0752db2d4e46bad2eb64e55bb24f05ef884de08d717b37455c44d2fe5cc7","abstract_canon_sha256":"df87b1e3308d003d074ef6ae3839a4deaa2a639088d9dd193b1b5d0e957d5c87"},"schema_version":"1.0"},"canonical_sha256":"b4ad2af68a4035b2e9eab15e5c01b86c5982ca9aabaf181c08643e0b672eaab6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:19.171698Z","signature_b64":"TjanCIEgYlvM8frK5kDzSwqwqzUssjrM40+EBil1bl53JXyfFPyChMSD2vX7Vlf8gimqg7RgFRapSZuSOIuTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4ad2af68a4035b2e9eab15e5c01b86c5982ca9aabaf181c08643e0b672eaab6","last_reissued_at":"2026-07-05T10:34:19.170733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:19.170733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.14517","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":"2026-07-05T10:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wg/4vAmmt4rb3aouXsHrzEEqmTQGq0ozGPwQRKVVHHLfL4CzPMwuhYi4Q04TUvjPYD37HMR0nmFAVEQ+03SgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:00:23.158929Z"},"content_sha256":"0b6488e2679ca8c77cb2b59d832ceb1d9e40f96eccb34b1e8257cd09a43741be","schema_version":"1.0","event_id":"sha256:0b6488e2679ca8c77cb2b59d832ceb1d9e40f96eccb34b1e8257cd09a43741be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WSWSV5UKIA23F2PKWFPFYANYNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Haoxian Zhang, Hejia Chen, Pengfei Wan, Shoulong Zhang, Shuai Li, Sisi Zhuang, Xiaoqiang Liu, Yuan Zhang","submitted_at":"2025-03-14T02:52:41Z","abstract_excerpt":"Speech-driven 3D talking face method should offer both accurate lip synchronization and controllable expressions. Previous methods solely adopt discrete emotion labels to globally control expressions throughout sequences while limiting flexible fine-grained facial control within the spatiotemporal domain. We propose a diffusion-transformer-based 3D talking face generation model, Cafe-Talk, which simultaneously incorporates coarse- and fine-grained multimodal control conditions. Nevertheless, the entanglement of multiple conditions challenges achieving satisfying performance. To disentangle spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14517","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/2503.14517/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":"2026-07-05T10:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdmT6ot4NeGybbV16nFOdz24EVeYH22Rsb2E6TtJYeLNehCdo5Klwxw/BJeiwYCU9zP1IdruO7APv2g2GkRVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:00:23.159429Z"},"content_sha256":"ee716a2b9eefff714d22c9553e59d02c1829e143356ca76b5f20ed387eafbfc5","schema_version":"1.0","event_id":"sha256:ee716a2b9eefff714d22c9553e59d02c1829e143356ca76b5f20ed387eafbfc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSWSV5UKIA23F2PKWFPFYANYNR/bundle.json","state_url":"https://pith.science/pith/WSWSV5UKIA23F2PKWFPFYANYNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSWSV5UKIA23F2PKWFPFYANYNR/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":"2026-08-18T21:00:23Z","links":{"resolver":"https://pith.science/pith/WSWSV5UKIA23F2PKWFPFYANYNR","bundle":"https://pith.science/pith/WSWSV5UKIA23F2PKWFPFYANYNR/bundle.json","state":"https://pith.science/pith/WSWSV5UKIA23F2PKWFPFYANYNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSWSV5UKIA23F2PKWFPFYANYNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSWSV5UKIA23F2PKWFPFYANYNR","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":"df87b1e3308d003d074ef6ae3839a4deaa2a639088d9dd193b1b5d0e957d5c87","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T02:52:41Z","title_canon_sha256":"458f0752db2d4e46bad2eb64e55bb24f05ef884de08d717b37455c44d2fe5cc7"},"schema_version":"1.0","source":{"id":"2503.14517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14517","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14517v1","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14517","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"WSWSV5UKIA23","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"WSWSV5UKIA23F2PK","created_at":"2026-07-05T10:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"WSWSV5UK","created_at":"2026-07-05T10:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:ee716a2b9eefff714d22c9553e59d02c1829e143356ca76b5f20ed387eafbfc5","target":"graph","created_at":"2026-07-05T10:34:19Z","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/2503.14517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-driven 3D talking face method should offer both accurate lip synchronization and controllable expressions. Previous methods solely adopt discrete emotion labels to globally control expressions throughout sequences while limiting flexible fine-grained facial control within the spatiotemporal domain. We propose a diffusion-transformer-based 3D talking face generation model, Cafe-Talk, which simultaneously incorporates coarse- and fine-grained multimodal control conditions. Nevertheless, the entanglement of multiple conditions challenges achieving satisfying performance. To disentangle spe","authors_text":"Di Zhang, Haoxian Zhang, Hejia Chen, Pengfei Wan, Shoulong Zhang, Shuai Li, Sisi Zhuang, Xiaoqiang Liu, Yuan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T02:52:41Z","title":"Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14517","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":"sha256:0b6488e2679ca8c77cb2b59d832ceb1d9e40f96eccb34b1e8257cd09a43741be","target":"record","created_at":"2026-07-05T10:34:19Z","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":"df87b1e3308d003d074ef6ae3839a4deaa2a639088d9dd193b1b5d0e957d5c87","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T02:52:41Z","title_canon_sha256":"458f0752db2d4e46bad2eb64e55bb24f05ef884de08d717b37455c44d2fe5cc7"},"schema_version":"1.0","source":{"id":"2503.14517","kind":"arxiv","version":1}},"canonical_sha256":"b4ad2af68a4035b2e9eab15e5c01b86c5982ca9aabaf181c08643e0b672eaab6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4ad2af68a4035b2e9eab15e5c01b86c5982ca9aabaf181c08643e0b672eaab6","first_computed_at":"2026-07-05T10:34:19.170733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:19.170733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TjanCIEgYlvM8frK5kDzSwqwqzUssjrM40+EBil1bl53JXyfFPyChMSD2vX7Vlf8gimqg7RgFRapSZuSOIuTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:19.171698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b6488e2679ca8c77cb2b59d832ceb1d9e40f96eccb34b1e8257cd09a43741be","sha256:ee716a2b9eefff714d22c9553e59d02c1829e143356ca76b5f20ed387eafbfc5"],"state_sha256":"d16a3d3d9aafdeabb241525a764471fb5aa7460f635ee29df08266ad7a60f850"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCC3/hY6QZ4EziBn8onTrZrGBcuvdPoN5bSFXDClCN/rnPUucggqHvDnoJn8rpOhGP42hpFa9S2OmgFks+giDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:00:23.165822Z","bundle_sha256":"8b5284abd4dbf253ec3d6a038bbb9d6a5944acba28e3f32f5f9967aa030e1a46"}}