{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JUJYDZ3RO445KYSCZPAIP4JIAO","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":"388be6235a86fd444b5b2e29214dd5ce67f5d793ab4a500874bbc9ea4edd7aca","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-17T16:40:23Z","title_canon_sha256":"9b0726081f9c5c425617bf96f9330261aa308440edf0f4aa9e786c55112ea4c3"},"schema_version":"1.0","source":{"id":"2502.12002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12002","created_at":"2026-07-05T10:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12002v1","created_at":"2026-07-05T10:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12002","created_at":"2026-07-05T10:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"JUJYDZ3RO445","created_at":"2026-07-05T10:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"JUJYDZ3RO445KYSC","created_at":"2026-07-05T10:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"JUJYDZ3R","created_at":"2026-07-05T10:15:37Z"}],"graph_snapshots":[{"event_id":"sha256:16ca416852e2651516cd97cca2f34e5e8b3531790d4d0e75c18b23d086a95c93","target":"graph","created_at":"2026-07-05T10:15:37Z","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/2502.12002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in visual speech recognition (VSR) have promoted progress in lip-to-speech synthesis, where pre-trained VSR models enhance the intelligibility of synthesized speech by providing valuable semantic information. The success achieved by cascade frameworks, which combine pseudo-VSR with pseudo-text-to-speech (TTS) or implicitly utilize the transcribed text, highlights the benefits of leveraging VSR models. However, these methods typically rely on mel-spectrograms as an intermediate representation, which may introduce a key bottleneck: the domain gap between synthetic mel-spectro","authors_text":"Andong Li, Chengshi Zheng, Fangkun Liu, Xiaodong Li, Yifan Liang","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-17T16:40:23Z","title":"NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12002","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:e55b3a6525160ad90ed91ad30222d043f1c8e0fe72c486c77a68d5e51fd1b524","target":"record","created_at":"2026-07-05T10:15:37Z","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":"388be6235a86fd444b5b2e29214dd5ce67f5d793ab4a500874bbc9ea4edd7aca","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-17T16:40:23Z","title_canon_sha256":"9b0726081f9c5c425617bf96f9330261aa308440edf0f4aa9e786c55112ea4c3"},"schema_version":"1.0","source":{"id":"2502.12002","kind":"arxiv","version":1}},"canonical_sha256":"4d1381e7717739d56242cbc087f128039452f80e1afffc14a5b0ca08fa44a9dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1381e7717739d56242cbc087f128039452f80e1afffc14a5b0ca08fa44a9dd","first_computed_at":"2026-07-05T10:15:37.236788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:37.236788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DLlULpxNKsIfqFuhwjqiV4mEdfqUiXwwJSHSwS1Xy5ESElfE31on6iHSX7OJi0X6/amdd2hRPCxJmFPN4HxPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:37.237387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e55b3a6525160ad90ed91ad30222d043f1c8e0fe72c486c77a68d5e51fd1b524","sha256:16ca416852e2651516cd97cca2f34e5e8b3531790d4d0e75c18b23d086a95c93"],"state_sha256":"d8b528c661c1dfeee7b2640f15ce6d87a6077e5121e170be0e7b7dd743035884"}