{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VDKR2PHU5BDG2QHZ4ITS7GO4K6","short_pith_number":"pith:VDKR2PHU","canonical_record":{"source":{"id":"2505.22024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T06:46:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"ae45235694ecc8a2eb1f03c380abfdd58983abb3b94549b5dd523322ec6d5329","abstract_canon_sha256":"387d711addd45f138b2caaf070d650e782de0d880f9685b1efec78137261d90a"},"schema_version":"1.0"},"canonical_sha256":"a8d51d3cf4e8466d40f9e2272f99dc5792fd1abb3b24fa6b050f1ed7423f482a","source":{"kind":"arxiv","id":"2505.22024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22024","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22024v1","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22024","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_12","alias_value":"VDKR2PHU5BDG","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_16","alias_value":"VDKR2PHU5BDG2QHZ","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_8","alias_value":"VDKR2PHU","created_at":"2026-07-05T11:11:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VDKR2PHU5BDG2QHZ4ITS7GO4K6","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T06:46:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"ae45235694ecc8a2eb1f03c380abfdd58983abb3b94549b5dd523322ec6d5329","abstract_canon_sha256":"387d711addd45f138b2caaf070d650e782de0d880f9685b1efec78137261d90a"},"schema_version":"1.0"},"canonical_sha256":"a8d51d3cf4e8466d40f9e2272f99dc5792fd1abb3b24fa6b050f1ed7423f482a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:08.271927Z","signature_b64":"9xJdBJ3Aih0uV/vjwpXpplMtq4vBTHz+XhFU2yLarCTKeyrCFfashnKsSn928+6751k3z0M/NesTm9lgPZMlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8d51d3cf4e8466d40f9e2272f99dc5792fd1abb3b24fa6b050f1ed7423f482a","last_reissued_at":"2026-07-05T11:11:08.271364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:08.271364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22024","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":"2026-07-05T11:11:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zah9o5wKwc8tXyj8PrTyXWWLGTybu4+Wr0wVvTDRG0zeaVwdTnD71mKi2cbxINhcwoWoe+PriOFywV/aOi6bDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:16:27.229709Z"},"content_sha256":"e2023e741da57dbc9ac9c6ac11291e35f8bb299cb028277c8d1eeae7ad7b8720","schema_version":"1.0","event_id":"sha256:e2023e741da57dbc9ac9c6ac11291e35f8bb299cb028277c8d1eeae7ad7b8720"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VDKR2PHU5BDG2QHZ4ITS7GO4K6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Long-Khanh Pham, Minh-Tan Pham, Thanh V. T. Tran, Van Nguyen","submitted_at":"2025-05-28T06:46:13Z","abstract_excerpt":"Lip-to-speech (L2S) synthesis, which reconstructs speech from visual cues, faces challenges in accuracy and naturalness due to limited supervision in capturing linguistic content, accents, and prosody. In this paper, we propose RESOUND, a novel L2S system that generates intelligible and expressive speech from silent talking face videos. Leveraging source-filter theory, our method involves two components: an acoustic path to predict prosody and a semantic path to extract linguistic features. This separation simplifies learning, allowing independent optimization of each representation. Additiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22024","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/2505.22024/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":"2026-07-05T11:11:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hj43B8jgKibkUNIkz28iVPM909FTXrX01ZMUt8+H9V/eRG1TeF0YdIFfdZcac+UVAZU2cbZfROajNe8TqzFGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:16:27.230239Z"},"content_sha256":"0721601e30f0d56baea9a7276d86b3d2ef267143efcb8a73e46bdf5edbde072b","schema_version":"1.0","event_id":"sha256:0721601e30f0d56baea9a7276d86b3d2ef267143efcb8a73e46bdf5edbde072b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6/bundle.json","state_url":"https://pith.science/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6/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":"2026-08-05T00:16:27Z","links":{"resolver":"https://pith.science/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6","bundle":"https://pith.science/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6/bundle.json","state":"https://pith.science/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDKR2PHU5BDG2QHZ4ITS7GO4K6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VDKR2PHU5BDG2QHZ4ITS7GO4K6","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":"387d711addd45f138b2caaf070d650e782de0d880f9685b1efec78137261d90a","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T06:46:13Z","title_canon_sha256":"ae45235694ecc8a2eb1f03c380abfdd58983abb3b94549b5dd523322ec6d5329"},"schema_version":"1.0","source":{"id":"2505.22024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22024","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22024v1","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22024","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_12","alias_value":"VDKR2PHU5BDG","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_16","alias_value":"VDKR2PHU5BDG2QHZ","created_at":"2026-07-05T11:11:08Z"},{"alias_kind":"pith_short_8","alias_value":"VDKR2PHU","created_at":"2026-07-05T11:11:08Z"}],"graph_snapshots":[{"event_id":"sha256:0721601e30f0d56baea9a7276d86b3d2ef267143efcb8a73e46bdf5edbde072b","target":"graph","created_at":"2026-07-05T11:11:08Z","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/2505.22024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lip-to-speech (L2S) synthesis, which reconstructs speech from visual cues, faces challenges in accuracy and naturalness due to limited supervision in capturing linguistic content, accents, and prosody. In this paper, we propose RESOUND, a novel L2S system that generates intelligible and expressive speech from silent talking face videos. Leveraging source-filter theory, our method involves two components: an acoustic path to predict prosody and a semantic path to extract linguistic features. This separation simplifies learning, allowing independent optimization of each representation. Additiona","authors_text":"Long-Khanh Pham, Minh-Tan Pham, Thanh V. T. Tran, Van Nguyen","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T06:46:13Z","title":"RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22024","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:e2023e741da57dbc9ac9c6ac11291e35f8bb299cb028277c8d1eeae7ad7b8720","target":"record","created_at":"2026-07-05T11:11:08Z","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":"387d711addd45f138b2caaf070d650e782de0d880f9685b1efec78137261d90a","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-28T06:46:13Z","title_canon_sha256":"ae45235694ecc8a2eb1f03c380abfdd58983abb3b94549b5dd523322ec6d5329"},"schema_version":"1.0","source":{"id":"2505.22024","kind":"arxiv","version":1}},"canonical_sha256":"a8d51d3cf4e8466d40f9e2272f99dc5792fd1abb3b24fa6b050f1ed7423f482a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8d51d3cf4e8466d40f9e2272f99dc5792fd1abb3b24fa6b050f1ed7423f482a","first_computed_at":"2026-07-05T11:11:08.271364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:08.271364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9xJdBJ3Aih0uV/vjwpXpplMtq4vBTHz+XhFU2yLarCTKeyrCFfashnKsSn928+6751k3z0M/NesTm9lgPZMlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:08.271927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2023e741da57dbc9ac9c6ac11291e35f8bb299cb028277c8d1eeae7ad7b8720","sha256:0721601e30f0d56baea9a7276d86b3d2ef267143efcb8a73e46bdf5edbde072b"],"state_sha256":"1a9be56d59d897c3f43d50acae321a4bfb112f4a85567353174ad87fb99064d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLAB+rjVbLo38E7jubnhkiSbtyF95yafM7AWoPrUx05OhM6+j6tW93r1Yrh3bHN4pYh1+5O/ylC0Lig65nAXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:16:27.234641Z","bundle_sha256":"4f88c3586e47e91ef6dc6a1e6a218da6020e9ccee6435a3971fc8d5bbe38456f"}}