{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LA2Q6IDSGP5ZTQHIACPBYKSNZK","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":"a1c1711f5dada2232e2a8b3a727fa5ee853b896c3435dbb2639c7c7a2b71fb68","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:20:52Z","title_canon_sha256":"106ae65c9059d01004a8307cd378512a10d9bc3c50188c73930de4ff4282919e"},"schema_version":"1.0","source":{"id":"2412.09262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09262","created_at":"2026-07-05T10:30:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09262v2","created_at":"2026-07-05T10:30:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09262","created_at":"2026-07-05T10:30:29Z"},{"alias_kind":"pith_short_12","alias_value":"LA2Q6IDSGP5Z","created_at":"2026-07-05T10:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LA2Q6IDSGP5ZTQHI","created_at":"2026-07-05T10:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LA2Q6IDS","created_at":"2026-07-05T10:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:7165c1c5cfe11bd9b3c2d6a1cb20404096e6546389b23e832ed4dfebe9f279ff","target":"graph","created_at":"2026-07-05T10:30:29Z","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/2412.09262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike and high-resolution talking videos. However, direct application of audio-conditioned LDMs to lip-synchronization (lip-sync) tasks results in suboptimal lip-sync accuracy. Through an in-depth analysis, we identified the underlying cause as the \"shortcut learning problem\", wherein the model predominantly learns visual-visual shortcuts while neglecting the critical audio-visual correlations. To address this issue, we exp","authors_text":"Bingyue Peng, Chao Zhang, Chunyu Li, Cunjian Chen, Jinghui Xie, Jingyu Lin, Weiguo Feng, Weikai Xu, Weiwei Xing","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:20:52Z","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09262","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":"sha256:1be6b0beebb6af2beba9ce092ac2e641060e822e86441f2ab20130ea0b362360","target":"record","created_at":"2026-07-05T10:30:29Z","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":"a1c1711f5dada2232e2a8b3a727fa5ee853b896c3435dbb2639c7c7a2b71fb68","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:20:52Z","title_canon_sha256":"106ae65c9059d01004a8307cd378512a10d9bc3c50188c73930de4ff4282919e"},"schema_version":"1.0","source":{"id":"2412.09262","kind":"arxiv","version":2}},"canonical_sha256":"58350f207233fb99c0e8009e1c2a4dca9c2f4336bbce73d17ff91f813e6d1ee4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58350f207233fb99c0e8009e1c2a4dca9c2f4336bbce73d17ff91f813e6d1ee4","first_computed_at":"2026-07-05T10:30:29.292929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:29.292929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MLc5smuBePQy8x3DtxLnjqnNtvVpBYaCYo2KmqA1rpn0kdF8MfGPJ8kip80vsE2LgKOshiZsUGtauAWCjipWBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:29.293422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1be6b0beebb6af2beba9ce092ac2e641060e822e86441f2ab20130ea0b362360","sha256:7165c1c5cfe11bd9b3c2d6a1cb20404096e6546389b23e832ed4dfebe9f279ff"],"state_sha256":"e3f4a9486a056ee868c54cc98106d0eee3a67b223356ab9784c8082c6b6e865b"}