{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G3CUJPHO55TWAYSY24GU4SNJ6P","short_pith_number":"pith:G3CUJPHO","schema_version":"1.0","canonical_sha256":"36c544bceeef67606258d70d4e49a9f3dae264aef9e0e45faf26d1a377a4f564","source":{"kind":"arxiv","id":"2409.12121","version":3},"attestation_state":"computed","paper":{"title":"WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chu Yuan Zhang, Jiangyan Yi, Jianhua Tao, Junzuo Zhou, Tao Wang, Yong Ren","submitted_at":"2024-09-18T16:45:09Z","abstract_excerpt":"Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training processes for the watermark and codec, and insufficient cross-modal information integration, leading to reduced watermark imperceptibility, extraction accuracy, and capacity. To address these issues, we propose WMCodec, the first neural speech codec to jointly train compression-reconstruction and wate"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.12121","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T16:45:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3a36dae5ceef2393d2ea467e6e9462ea1b9e2e62608bfb5e8bcc2b291caffa05","abstract_canon_sha256":"27ac8dd0e5b5156101348ea8df56383da3cdc99616650f8fa3a2167d075a222b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:28.670232Z","signature_b64":"xIfYVOtk/bVa65A7bHoS5jQOO3Eu2WFUrxZoFYg1Q33kMVObi0DkpgErQALFKOrw+L6ec9mU79kqatMmnPHYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36c544bceeef67606258d70d4e49a9f3dae264aef9e0e45faf26d1a377a4f564","last_reissued_at":"2026-07-05T09:54:28.669803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:28.669803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chu Yuan Zhang, Jiangyan Yi, Jianhua Tao, Junzuo Zhou, Tao Wang, Yong Ren","submitted_at":"2024-09-18T16:45:09Z","abstract_excerpt":"Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training processes for the watermark and codec, and insufficient cross-modal information integration, leading to reduced watermark imperceptibility, extraction accuracy, and capacity. To address these issues, we propose WMCodec, the first neural speech codec to jointly train compression-reconstruction and wate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12121","kind":"arxiv","version":3},"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/2409.12121/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.12121","created_at":"2026-07-05T09:54:28.669860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12121v3","created_at":"2026-07-05T09:54:28.669860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12121","created_at":"2026-07-05T09:54:28.669860+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3CUJPHO55TW","created_at":"2026-07-05T09:54:28.669860+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3CUJPHO55TWAYSY","created_at":"2026-07-05T09:54:28.669860+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3CUJPHO","created_at":"2026-07-05T09:54:28.669860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08238","citing_title":"CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P","json":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P.json","graph_json":"https://pith.science/api/pith-number/G3CUJPHO55TWAYSY24GU4SNJ6P/graph.json","events_json":"https://pith.science/api/pith-number/G3CUJPHO55TWAYSY24GU4SNJ6P/events.json","paper":"https://pith.science/paper/G3CUJPHO"},"agent_actions":{"view_html":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P","download_json":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P.json","view_paper":"https://pith.science/paper/G3CUJPHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12121&json=true","fetch_graph":"https://pith.science/api/pith-number/G3CUJPHO55TWAYSY24GU4SNJ6P/graph.json","fetch_events":"https://pith.science/api/pith-number/G3CUJPHO55TWAYSY24GU4SNJ6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P/action/storage_attestation","attest_author":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P/action/author_attestation","sign_citation":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P/action/citation_signature","submit_replication":"https://pith.science/pith/G3CUJPHO55TWAYSY24GU4SNJ6P/action/replication_record"}},"created_at":"2026-07-05T09:54:28.669860+00:00","updated_at":"2026-07-05T09:54:28.669860+00:00"}