{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CCU3KPUK4YMEOMLRPHYC7TMGOE","short_pith_number":"pith:CCU3KPUK","canonical_record":{"source":{"id":"2304.00334","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T15:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"b3047bc718fa16ccdb755c683b051470597ad0536a2d5d92f0562bd9f083597d","abstract_canon_sha256":"eae2f0a5c4990ebf2d0191d7909c20dce7364bb58954159d21faf333d3a79451"},"schema_version":"1.0"},"canonical_sha256":"10a9b53e8ae61847317179f02fcd86710e8b15c5b57d5bc8535236962bba16aa","source":{"kind":"arxiv","id":"2304.00334","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00334","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00334v4","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00334","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"pith_short_12","alias_value":"CCU3KPUK4YME","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"pith_short_16","alias_value":"CCU3KPUK4YMEOMLR","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"pith_short_8","alias_value":"CCU3KPUK","created_at":"2026-07-05T08:54:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CCU3KPUK4YMEOMLRPHYC7TMGOE","target":"record","payload":{"canonical_record":{"source":{"id":"2304.00334","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T15:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"b3047bc718fa16ccdb755c683b051470597ad0536a2d5d92f0562bd9f083597d","abstract_canon_sha256":"eae2f0a5c4990ebf2d0191d7909c20dce7364bb58954159d21faf333d3a79451"},"schema_version":"1.0"},"canonical_sha256":"10a9b53e8ae61847317179f02fcd86710e8b15c5b57d5bc8535236962bba16aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:01.576431Z","signature_b64":"a/ovJFu5qjI4hcL6MSj8V54eoHniNuV81TnLciazBJAH0TogpysK6ivHmUMXKDq5BUBKDCXKMLEF8XHIM37JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10a9b53e8ae61847317179f02fcd86710e8b15c5b57d5bc8535236962bba16aa","last_reissued_at":"2026-07-05T08:54:01.575862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:01.575862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.00334","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:54:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8iiE7fLRkrSjdK+KzcWmyRCO4krRDiSkK0NmJ9wTL0rIV360E/5d+wPWMJdKdADi/ZpfvomSiwGmb3Ck2AfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:50:01.821137Z"},"content_sha256":"41d10187a4598bd792b7aa18f4fc3b5b7ffdba7ffbff8147b988ec0c0747cf17","schema_version":"1.0","event_id":"sha256:41d10187a4598bd792b7aa18f4fc3b5b7ffdba7ffbff8147b988ec0c0747cf17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CCU3KPUK4YMEOMLRPHYC7TMGOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Ma, Changjie Fan, Suzhen Wang, Tangjie Lv, Xin Yu, Yifeng Ma, Yu Ding, Zhidong Deng, Zhipeng Hu","submitted_at":"2023-04-01T15:10:02Z","abstract_excerpt":"Audio-driven talking head generation has drawn growing attention. To produce talking head videos with desired facial expressions, previous methods rely on extra reference videos to provide expression information, which may be difficult to find and hence limits their usage. In this work, we propose TalkCLIP, a framework that can generate talking heads where the expressions are specified by natural language, hence allowing for specifying expressions more conveniently. To model the mapping from text to expressions, we first construct a text-video paired talking head dataset where each video has d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00334","kind":"arxiv","version":4},"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/2304.00334/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":"2026-07-05T08:54:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qw0/v90AlC4elq305K0pNmRteJH7+csMKNYmIIgC3aVtmbvXNTEl/SGLdgtQLufEeAvvKSZDZkCWY+qojDO6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:50:01.821639Z"},"content_sha256":"2dd9a1b124278d3f44bdc9ab0a200b6888d91247b32c1d4bc24fd7ca8b7a7d8c","schema_version":"1.0","event_id":"sha256:2dd9a1b124278d3f44bdc9ab0a200b6888d91247b32c1d4bc24fd7ca8b7a7d8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE/bundle.json","state_url":"https://pith.science/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE/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":"2026-08-07T19:50:01Z","links":{"resolver":"https://pith.science/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE","bundle":"https://pith.science/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE/bundle.json","state":"https://pith.science/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCU3KPUK4YMEOMLRPHYC7TMGOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CCU3KPUK4YMEOMLRPHYC7TMGOE","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":"eae2f0a5c4990ebf2d0191d7909c20dce7364bb58954159d21faf333d3a79451","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T15:10:02Z","title_canon_sha256":"b3047bc718fa16ccdb755c683b051470597ad0536a2d5d92f0562bd9f083597d"},"schema_version":"1.0","source":{"id":"2304.00334","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00334","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00334v4","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00334","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"pith_short_12","alias_value":"CCU3KPUK4YME","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"pith_short_16","alias_value":"CCU3KPUK4YMEOMLR","created_at":"2026-07-05T08:54:01Z"},{"alias_kind":"pith_short_8","alias_value":"CCU3KPUK","created_at":"2026-07-05T08:54:01Z"}],"graph_snapshots":[{"event_id":"sha256:2dd9a1b124278d3f44bdc9ab0a200b6888d91247b32c1d4bc24fd7ca8b7a7d8c","target":"graph","created_at":"2026-07-05T08:54:01Z","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/2304.00334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-driven talking head generation has drawn growing attention. To produce talking head videos with desired facial expressions, previous methods rely on extra reference videos to provide expression information, which may be difficult to find and hence limits their usage. In this work, we propose TalkCLIP, a framework that can generate talking heads where the expressions are specified by natural language, hence allowing for specifying expressions more conveniently. To model the mapping from text to expressions, we first construct a text-video paired talking head dataset where each video has d","authors_text":"Bowen Ma, Changjie Fan, Suzhen Wang, Tangjie Lv, Xin Yu, Yifeng Ma, Yu Ding, Zhidong Deng, Zhipeng Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T15:10:02Z","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00334","kind":"arxiv","version":4},"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":"sha256:41d10187a4598bd792b7aa18f4fc3b5b7ffdba7ffbff8147b988ec0c0747cf17","target":"record","created_at":"2026-07-05T08:54:01Z","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":"eae2f0a5c4990ebf2d0191d7909c20dce7364bb58954159d21faf333d3a79451","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-01T15:10:02Z","title_canon_sha256":"b3047bc718fa16ccdb755c683b051470597ad0536a2d5d92f0562bd9f083597d"},"schema_version":"1.0","source":{"id":"2304.00334","kind":"arxiv","version":4}},"canonical_sha256":"10a9b53e8ae61847317179f02fcd86710e8b15c5b57d5bc8535236962bba16aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10a9b53e8ae61847317179f02fcd86710e8b15c5b57d5bc8535236962bba16aa","first_computed_at":"2026-07-05T08:54:01.575862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:01.575862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/ovJFu5qjI4hcL6MSj8V54eoHniNuV81TnLciazBJAH0TogpysK6ivHmUMXKDq5BUBKDCXKMLEF8XHIM37JDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:01.576431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00334","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d10187a4598bd792b7aa18f4fc3b5b7ffdba7ffbff8147b988ec0c0747cf17","sha256:2dd9a1b124278d3f44bdc9ab0a200b6888d91247b32c1d4bc24fd7ca8b7a7d8c"],"state_sha256":"238cdeddc8f1ac4272f5bbd0dde750e57e55dfc87528363d56f038b6b6240fb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QuQUNX3PLYvOryFRqCzUzzs6PBJ5GrKggOs88dCPgjjmb+ab6IP+mYOY/acwTzfFBRHgjswJic8v4Z7P5+FCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:50:01.825796Z","bundle_sha256":"59cbc2086b2338282613639e8ef1bd5526475edd61f9e2e74b3af6d834da7240"}}