{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EHFLZOGKC3NTS42WEGPFV6AX7V","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":"fc00994b507db4a2281d80e1942be27f5d7689cadc056b9d2eff2d732f2b9ae1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T16:58:53Z","title_canon_sha256":"9f1d460578b2e390ab5d75d900bb80ae7f97a007651ba04dc4d7d5a263b226dd"},"schema_version":"1.0","source":{"id":"2503.13371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13371","created_at":"2026-07-05T10:32:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13371v1","created_at":"2026-07-05T10:32:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13371","created_at":"2026-07-05T10:32:59Z"},{"alias_kind":"pith_short_12","alias_value":"EHFLZOGKC3NT","created_at":"2026-07-05T10:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"EHFLZOGKC3NTS42W","created_at":"2026-07-05T10:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"EHFLZOGK","created_at":"2026-07-05T10:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:eceb50e5414762d6dd97ee546156a2ae9593e2e274daf612168c3463efc9d3bf","target":"graph","created_at":"2026-07-05T10:32:59Z","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/2503.13371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Talking head synthesis, also known as speech-to-lip synthesis, reconstructs the facial motions that align with the given audio tracks. The synthesized videos are evaluated on mainly two aspects, lip-speech synchronization and image fidelity. Recent studies demonstrate that GAN-based and diffusion-based models achieve state-of-the-art (SOTA) performance on this task, with diffusion-based models achieving superior image fidelity but experiencing lower synchronization compared to their GAN-based counterparts. To this end, we propose SyncDiff, a simple yet effective approach to improve diffusion-b","authors_text":"Heting Gao, Mark Hasegawa-Johnson, Mei Han, Peng Chang, Xulin Fan, Ziyi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T16:58:53Z","title":"SyncDiff: Diffusion-based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13371","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":"sha256:77e01edc5ed5d35765d8e6307821afca1abd4e6ee0d13b179b4ec6a8d637398c","target":"record","created_at":"2026-07-05T10:32:59Z","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":"fc00994b507db4a2281d80e1942be27f5d7689cadc056b9d2eff2d732f2b9ae1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-17T16:58:53Z","title_canon_sha256":"9f1d460578b2e390ab5d75d900bb80ae7f97a007651ba04dc4d7d5a263b226dd"},"schema_version":"1.0","source":{"id":"2503.13371","kind":"arxiv","version":1}},"canonical_sha256":"21cabcb8ca16db397356219e5af817fd5e9a3a71cff8d0f55e2c38e6a2fba19d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21cabcb8ca16db397356219e5af817fd5e9a3a71cff8d0f55e2c38e6a2fba19d","first_computed_at":"2026-07-05T10:32:59.242501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:59.242501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aCkuvBqyR//B6F/X4wN5Ka0gKeoC1Odvy4qrjTQ0tLrnZpeZfNBpYwBmYAnfroF5kCEAIa6rWVxtWQcMop9wDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:59.242987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77e01edc5ed5d35765d8e6307821afca1abd4e6ee0d13b179b4ec6a8d637398c","sha256:eceb50e5414762d6dd97ee546156a2ae9593e2e274daf612168c3463efc9d3bf"],"state_sha256":"38827cd4d90ed3a22acaee7e89369c92cf59011a1a98c17c0a7212983bd5763d"}