{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QQHEPIJ4KOR776BNYAT6RNP75Z","short_pith_number":"pith:QQHEPIJ4","canonical_record":{"source":{"id":"2305.02594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T07:01:36Z","cross_cats_sorted":[],"title_canon_sha256":"0d3d54678014ebbabffd7fe6e55b2f29e4739882308bef67a6dd3dcff6725826","abstract_canon_sha256":"a0180b3846e35dd07f10673bddb6830520ce9c8c98da846f81ce2786370712e1"},"schema_version":"1.0"},"canonical_sha256":"840e47a13c53a3fff82dc027e8b5ffee71277a52ded64212592f42b8d77aa465","source":{"kind":"arxiv","id":"2305.02594","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02594","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02594v2","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02594","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"QQHEPIJ4KOR7","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"QQHEPIJ4KOR776BN","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"QQHEPIJ4","created_at":"2026-07-05T06:08:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QQHEPIJ4KOR776BNYAT6RNP75Z","target":"record","payload":{"canonical_record":{"source":{"id":"2305.02594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T07:01:36Z","cross_cats_sorted":[],"title_canon_sha256":"0d3d54678014ebbabffd7fe6e55b2f29e4739882308bef67a6dd3dcff6725826","abstract_canon_sha256":"a0180b3846e35dd07f10673bddb6830520ce9c8c98da846f81ce2786370712e1"},"schema_version":"1.0"},"canonical_sha256":"840e47a13c53a3fff82dc027e8b5ffee71277a52ded64212592f42b8d77aa465","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:28.187675Z","signature_b64":"eLkkuodnBCu9PVCvCA/jmO8ftJ3lF6e2zAyVJUyb1JXapW1K5OGRyuDwlE4FUXmd7CyzugzNyVaUuh1TLiF/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"840e47a13c53a3fff82dc027e8b5ffee71277a52ded64212592f42b8d77aa465","last_reissued_at":"2026-07-05T06:08:28.187252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:28.187252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.02594","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"roAUsM6WRE+/oJ5mZQ03GBYkFZiGb8Jnq9qnYXzzplRpM94c/zQL1Zt8df0cBY/ONdMHZuPedIx39mhNIddfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:10:16.461827Z"},"content_sha256":"f1db6fbb169111373262e4b2726f62f85a276691c9f9f95938a6bd4d07382493","schema_version":"1.0","event_id":"sha256:f1db6fbb169111373262e4b2726f62f85a276691c9f9f95938a6bd4d07382493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QQHEPIJ4KOR776BNYAT6RNP75Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Xu, Jiangning Zhang, Junwei Zhu, Shaoting Zhu, Tianxin Huang, Ying Tai, Yong Liu","submitted_at":"2023-05-04T07:01:36Z","abstract_excerpt":"Multimodal-driven talking face generation refers to animating a portrait with the given pose, expression, and gaze transferred from the driving image and video, or estimated from the text and audio. However, existing methods ignore the potential of text modal, and their generators mainly follow the source-oriented feature rearrange paradigm coupled with unstable GAN frameworks. In this work, we first represent the emotion in the text prompt, which could inherit rich semantics from the CLIP, allowing flexible and generalized emotion control. We further reorganize these tasks as the target-orien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02594","kind":"arxiv","version":2},"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/2305.02594/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":"2026-07-05T06:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBYUL5U/gVBGRHvNfd/RkFEW0h3oE0XHgij8R3TXhj+PFCKTsf5MjE7VW5uAdMEphOxknZB8keZsxSIVmz9bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:10:16.462743Z"},"content_sha256":"a7552d05bc6f3bd6ba220fe7153c918073bbe6721f37009457759ec84eb00c9a","schema_version":"1.0","event_id":"sha256:a7552d05bc6f3bd6ba220fe7153c918073bbe6721f37009457759ec84eb00c9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQHEPIJ4KOR776BNYAT6RNP75Z/bundle.json","state_url":"https://pith.science/pith/QQHEPIJ4KOR776BNYAT6RNP75Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQHEPIJ4KOR776BNYAT6RNP75Z/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":"2026-08-05T07:10:16Z","links":{"resolver":"https://pith.science/pith/QQHEPIJ4KOR776BNYAT6RNP75Z","bundle":"https://pith.science/pith/QQHEPIJ4KOR776BNYAT6RNP75Z/bundle.json","state":"https://pith.science/pith/QQHEPIJ4KOR776BNYAT6RNP75Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQHEPIJ4KOR776BNYAT6RNP75Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QQHEPIJ4KOR776BNYAT6RNP75Z","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":"a0180b3846e35dd07f10673bddb6830520ce9c8c98da846f81ce2786370712e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T07:01:36Z","title_canon_sha256":"0d3d54678014ebbabffd7fe6e55b2f29e4739882308bef67a6dd3dcff6725826"},"schema_version":"1.0","source":{"id":"2305.02594","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02594","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02594v2","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02594","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"QQHEPIJ4KOR7","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"QQHEPIJ4KOR776BN","created_at":"2026-07-05T06:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"QQHEPIJ4","created_at":"2026-07-05T06:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:a7552d05bc6f3bd6ba220fe7153c918073bbe6721f37009457759ec84eb00c9a","target":"graph","created_at":"2026-07-05T06:08:28Z","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/2305.02594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal-driven talking face generation refers to animating a portrait with the given pose, expression, and gaze transferred from the driving image and video, or estimated from the text and audio. However, existing methods ignore the potential of text modal, and their generators mainly follow the source-oriented feature rearrange paradigm coupled with unstable GAN frameworks. In this work, we first represent the emotion in the text prompt, which could inherit rich semantics from the CLIP, allowing flexible and generalized emotion control. We further reorganize these tasks as the target-orien","authors_text":"Chao Xu, Jiangning Zhang, Junwei Zhu, Shaoting Zhu, Tianxin Huang, Ying Tai, Yong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T07:01:36Z","title":"Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02594","kind":"arxiv","version":2},"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:f1db6fbb169111373262e4b2726f62f85a276691c9f9f95938a6bd4d07382493","target":"record","created_at":"2026-07-05T06:08:28Z","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":"a0180b3846e35dd07f10673bddb6830520ce9c8c98da846f81ce2786370712e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T07:01:36Z","title_canon_sha256":"0d3d54678014ebbabffd7fe6e55b2f29e4739882308bef67a6dd3dcff6725826"},"schema_version":"1.0","source":{"id":"2305.02594","kind":"arxiv","version":2}},"canonical_sha256":"840e47a13c53a3fff82dc027e8b5ffee71277a52ded64212592f42b8d77aa465","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"840e47a13c53a3fff82dc027e8b5ffee71277a52ded64212592f42b8d77aa465","first_computed_at":"2026-07-05T06:08:28.187252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:28.187252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eLkkuodnBCu9PVCvCA/jmO8ftJ3lF6e2zAyVJUyb1JXapW1K5OGRyuDwlE4FUXmd7CyzugzNyVaUuh1TLiF/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:28.187675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02594","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1db6fbb169111373262e4b2726f62f85a276691c9f9f95938a6bd4d07382493","sha256:a7552d05bc6f3bd6ba220fe7153c918073bbe6721f37009457759ec84eb00c9a"],"state_sha256":"4393d9a55aa24571e5ac15219993eb5937c0477fcf53e7163e4b6bda5f0ce376"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JIi/qZmPxlIJ2XIqVJZl272g4SiKkBQV9oe3Ui2x2YJT3TMYSQfWQVTUl5uCA/knG0ZESfEtYCf+qbeZNZHvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:10:16.468645Z","bundle_sha256":"3c4fb1e1ede11147a262a9cd4b4c3a6adbbb8d060a8d8b6eb33bb936d25abcd4"}}