{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LA2Q6IDSGP5ZTQHIACPBYKSNZK","short_pith_number":"pith:LA2Q6IDS","canonical_record":{"source":{"id":"2412.09262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:20:52Z","cross_cats_sorted":[],"title_canon_sha256":"106ae65c9059d01004a8307cd378512a10d9bc3c50188c73930de4ff4282919e","abstract_canon_sha256":"a1c1711f5dada2232e2a8b3a727fa5ee853b896c3435dbb2639c7c7a2b71fb68"},"schema_version":"1.0"},"canonical_sha256":"58350f207233fb99c0e8009e1c2a4dca9c2f4336bbce73d17ff91f813e6d1ee4","source":{"kind":"arxiv","id":"2412.09262","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LA2Q6IDSGP5ZTQHIACPBYKSNZK","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:20:52Z","cross_cats_sorted":[],"title_canon_sha256":"106ae65c9059d01004a8307cd378512a10d9bc3c50188c73930de4ff4282919e","abstract_canon_sha256":"a1c1711f5dada2232e2a8b3a727fa5ee853b896c3435dbb2639c7c7a2b71fb68"},"schema_version":"1.0"},"canonical_sha256":"58350f207233fb99c0e8009e1c2a4dca9c2f4336bbce73d17ff91f813e6d1ee4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:29.293422Z","signature_b64":"MLc5smuBePQy8x3DtxLnjqnNtvVpBYaCYo2KmqA1rpn0kdF8MfGPJ8kip80vsE2LgKOshiZsUGtauAWCjipWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58350f207233fb99c0e8009e1c2a4dca9c2f4336bbce73d17ff91f813e6d1ee4","last_reissued_at":"2026-07-05T10:30:29.292929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:29.292929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09262","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":"2026-07-05T10:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XhlGIIFLFTbgPrrZ/oP0kBBG2gkog90ZkhR5KcUu6M6ZHh1yDFCqWR85zBwot4XkAxPJhbUoWd4Xggb7TPcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:41:22.302172Z"},"content_sha256":"1be6b0beebb6af2beba9ce092ac2e641060e822e86441f2ab20130ea0b362360","schema_version":"1.0","event_id":"sha256:1be6b0beebb6af2beba9ce092ac2e641060e822e86441f2ab20130ea0b362360"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LA2Q6IDSGP5ZTQHIACPBYKSNZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyue Peng, Chao Zhang, Chunyu Li, Cunjian Chen, Jinghui Xie, Jingyu Lin, Weiguo Feng, Weikai Xu, Weiwei Xing","submitted_at":"2024-12-12T13:20:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09262","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/2412.09262/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":"2026-07-05T10:30:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TE7KuL2r5yO1vtIdW+uqzmcqjTODtNU9gfW6lJcu1uNN4UrnXuSqu4vLg0ven0WU9rRkCR4J3DeqDoylCwLSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:41:22.303126Z"},"content_sha256":"7165c1c5cfe11bd9b3c2d6a1cb20404096e6546389b23e832ed4dfebe9f279ff","schema_version":"1.0","event_id":"sha256:7165c1c5cfe11bd9b3c2d6a1cb20404096e6546389b23e832ed4dfebe9f279ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK/bundle.json","state_url":"https://pith.science/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK/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":"2026-08-04T05:41:22Z","links":{"resolver":"https://pith.science/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK","bundle":"https://pith.science/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK/bundle.json","state":"https://pith.science/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LA2Q6IDSGP5ZTQHIACPBYKSNZK/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j383vzCsFVZwjUf6LdpjX+LCUXF/4id1eirD8py6otUsfixBURm9kKDe+xDqiH3VWt7Mp+SPXcleARLjtfERCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:41:22.342705Z","bundle_sha256":"64769bd185e05d57a1bf2da6cf93fe58e33e759253f922bea715457e1f6f88d4"}}