{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HNM5QHJQEOHYP3LT5LZAVW6EPB","short_pith_number":"pith:HNM5QHJQ","canonical_record":{"source":{"id":"2212.04248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2022-12-07T17:55:41Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"69fbdcd5865ef81d0d0185a13154968013fbd087aec874a2ded691d8ba504683","abstract_canon_sha256":"5d9568de73ed30374a0efaf4504c08969f7823003f2c02fb40298dd4a343a088"},"schema_version":"1.0"},"canonical_sha256":"3b59d81d30238f87ed73eaf20adbc47874e15067dbca88e070abdb3fcd61f67b","source":{"kind":"arxiv","id":"2212.04248","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04248","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04248v1","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04248","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"HNM5QHJQEOHY","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"HNM5QHJQEOHYP3LT","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"HNM5QHJQ","created_at":"2026-07-05T05:23:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HNM5QHJQEOHYP3LT5LZAVW6EPB","target":"record","payload":{"canonical_record":{"source":{"id":"2212.04248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2022-12-07T17:55:41Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"69fbdcd5865ef81d0d0185a13154968013fbd087aec874a2ded691d8ba504683","abstract_canon_sha256":"5d9568de73ed30374a0efaf4504c08969f7823003f2c02fb40298dd4a343a088"},"schema_version":"1.0"},"canonical_sha256":"3b59d81d30238f87ed73eaf20adbc47874e15067dbca88e070abdb3fcd61f67b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:38.231075Z","signature_b64":"KjNdeiClsMr++nClEbTHn0V04acdL1Z6wBkW3oNQaZ15Z6Sm5Bt+lZyca0iyZRhAxdZYXliqu8t4Ab753lBYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b59d81d30238f87ed73eaf20adbc47874e15067dbca88e070abdb3fcd61f67b","last_reissued_at":"2026-07-05T05:23:38.230731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:38.230731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.04248","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":"2026-07-05T05:23:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YtVrZuSV3EYq4NE29UQYSPr+VwgBbsYH2po+8oMZSz+5heyU+i1HmfIkbKIwce50as1XoWLqWSMJ7IOmJ97/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:38:44.852681Z"},"content_sha256":"49bbd46b2aa0314ce939a4c5b508dd86c2c5bb74095622ab265b854fd26364ab","schema_version":"1.0","event_id":"sha256:49bbd46b2aa0314ce939a4c5b508dd86c2c5bb74095622ab265b854fd26364ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HNM5QHJQEOHYP3LT5LZAVW6EPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.GR","authors_text":"Baoyuan Wang, Deyu Zhou, Duomin Wang, Finn Wong, Zhentao Yu, Zixin Yin","submitted_at":"2022-12-07T17:55:41Z","abstract_excerpt":"In this paper, we introduce a simple and novel framework for one-shot audio-driven talking head generation. Unlike prior works that require additional driving sources for controlled synthesis in a deterministic manner, we instead probabilistically sample all the holistic lip-irrelevant facial motions (i.e. pose, expression, blink, gaze, etc.) to semantically match the input audio while still maintaining both the photo-realism of audio-lip synchronization and the overall naturalness. This is achieved by our newly proposed audio-to-visual diffusion prior trained on top of the mapping between aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04248","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/2212.04248/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":"2026-07-05T05:23:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BoPLW2zYbvVAE/GL93jowZCoE3vx9e3VV06X2UjE8ZINXJAmBQOutYyXFyde7cLd9Q6w9kEP9Am2gekuEaQlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:38:44.853249Z"},"content_sha256":"04e49339159d138f77b901cd7dab521471f3ac460ff061e44b369868c34294cc","schema_version":"1.0","event_id":"sha256:04e49339159d138f77b901cd7dab521471f3ac460ff061e44b369868c34294cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB/bundle.json","state_url":"https://pith.science/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB/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":"2026-08-09T02:38:44Z","links":{"resolver":"https://pith.science/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB","bundle":"https://pith.science/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB/bundle.json","state":"https://pith.science/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HNM5QHJQEOHYP3LT5LZAVW6EPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HNM5QHJQEOHYP3LT5LZAVW6EPB","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":"5d9568de73ed30374a0efaf4504c08969f7823003f2c02fb40298dd4a343a088","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2022-12-07T17:55:41Z","title_canon_sha256":"69fbdcd5865ef81d0d0185a13154968013fbd087aec874a2ded691d8ba504683"},"schema_version":"1.0","source":{"id":"2212.04248","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.04248","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.04248v1","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04248","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"HNM5QHJQEOHY","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"HNM5QHJQEOHYP3LT","created_at":"2026-07-05T05:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"HNM5QHJQ","created_at":"2026-07-05T05:23:38Z"}],"graph_snapshots":[{"event_id":"sha256:04e49339159d138f77b901cd7dab521471f3ac460ff061e44b369868c34294cc","target":"graph","created_at":"2026-07-05T05:23:38Z","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/2212.04248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a simple and novel framework for one-shot audio-driven talking head generation. Unlike prior works that require additional driving sources for controlled synthesis in a deterministic manner, we instead probabilistically sample all the holistic lip-irrelevant facial motions (i.e. pose, expression, blink, gaze, etc.) to semantically match the input audio while still maintaining both the photo-realism of audio-lip synchronization and the overall naturalness. This is achieved by our newly proposed audio-to-visual diffusion prior trained on top of the mapping between aud","authors_text":"Baoyuan Wang, Deyu Zhou, Duomin Wang, Finn Wong, Zhentao Yu, Zixin Yin","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2022-12-07T17:55:41Z","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04248","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":"sha256:49bbd46b2aa0314ce939a4c5b508dd86c2c5bb74095622ab265b854fd26364ab","target":"record","created_at":"2026-07-05T05:23:38Z","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":"5d9568de73ed30374a0efaf4504c08969f7823003f2c02fb40298dd4a343a088","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2022-12-07T17:55:41Z","title_canon_sha256":"69fbdcd5865ef81d0d0185a13154968013fbd087aec874a2ded691d8ba504683"},"schema_version":"1.0","source":{"id":"2212.04248","kind":"arxiv","version":1}},"canonical_sha256":"3b59d81d30238f87ed73eaf20adbc47874e15067dbca88e070abdb3fcd61f67b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b59d81d30238f87ed73eaf20adbc47874e15067dbca88e070abdb3fcd61f67b","first_computed_at":"2026-07-05T05:23:38.230731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:38.230731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjNdeiClsMr++nClEbTHn0V04acdL1Z6wBkW3oNQaZ15Z6Sm5Bt+lZyca0iyZRhAxdZYXliqu8t4Ab753lBYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:38.231075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.04248","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49bbd46b2aa0314ce939a4c5b508dd86c2c5bb74095622ab265b854fd26364ab","sha256:04e49339159d138f77b901cd7dab521471f3ac460ff061e44b369868c34294cc"],"state_sha256":"41ce6baaea0992d81500dae425377ad2ae979817cc904791261ce86fe20905c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rqhyMh9vClmNB7f0tjffL518nXXGRMj2BblkOAxBF87ke1Bb76flb4ljX+vaxZTO0GqlMSopzVUd6O8ihJb6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:38:44.857601Z","bundle_sha256":"7ad0e0035f555654a926d2150f7e4624d8bd5f5b42327fe849264bd989c8f42a"}}