{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P546BPMRJG4AEIQUIYJFT6TG27","short_pith_number":"pith:P546BPMR","schema_version":"1.0","canonical_sha256":"7f79e0bd9149b8022214461259fa66d7f4ff070d2ffcd11f935a62f0a7af9dc3","source":{"kind":"arxiv","id":"2505.12994","version":3},"attestation_state":"computed","paper":{"title":"Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haibin Wu, Hung-yi Lee, I-Ming Lin, Jiawei Du, Jyh-Shing Roger Jang, Lin Zhang, Xuanjun Chen","submitted_at":"2025-05-19T11:31:32Z","abstract_excerpt":"Recent advances in neural audio codec-based speech generation (CoSG) models have produced remarkably realistic audio deepfakes. We refer to deepfake speech generated by CoSG systems as codec-based deepfake, or CodecFake. Although existing anti-spoofing research on CodecFake predominantly focuses on verifying the authenticity of audio samples, almost no attention was given to tracing the CoSG used in generating these deepfakes. In CodecFake generation, processes such as speech-to-unit encoding, discrete unit modeling, and unit-to-speech decoding are fundamentally based on neural audio codecs. M"},"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":"2505.12994","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T11:31:32Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"34697c0dcb8d7ef1ab251515d2f2ef344518171b2ad6e337fc2b0d55fb2a604a","abstract_canon_sha256":"32e129f074e7a7ba69b9e827aa3a5bfb8bae23bbb590ea423bbc060f57dde013"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:23.271058Z","signature_b64":"q7FoSa+4EtaJbKZP7lUSPt1uqpEXfrOq3U1bK9JuALBKcEr0+T+SlViWF1BqzGzL7+nWJ2KRd0tX0AHHMWdHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f79e0bd9149b8022214461259fa66d7f4ff070d2ffcd11f935a62f0a7af9dc3","last_reissued_at":"2026-07-05T11:47:23.270608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:23.270608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haibin Wu, Hung-yi Lee, I-Ming Lin, Jiawei Du, Jyh-Shing Roger Jang, Lin Zhang, Xuanjun Chen","submitted_at":"2025-05-19T11:31:32Z","abstract_excerpt":"Recent advances in neural audio codec-based speech generation (CoSG) models have produced remarkably realistic audio deepfakes. We refer to deepfake speech generated by CoSG systems as codec-based deepfake, or CodecFake. Although existing anti-spoofing research on CodecFake predominantly focuses on verifying the authenticity of audio samples, almost no attention was given to tracing the CoSG used in generating these deepfakes. In CodecFake generation, processes such as speech-to-unit encoding, discrete unit modeling, and unit-to-speech decoding are fundamentally based on neural audio codecs. M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12994","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/2505.12994/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":"2505.12994","created_at":"2026-07-05T11:47:23.270667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12994v3","created_at":"2026-07-05T11:47:23.270667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12994","created_at":"2026-07-05T11:47:23.270667+00:00"},{"alias_kind":"pith_short_12","alias_value":"P546BPMRJG4A","created_at":"2026-07-05T11:47:23.270667+00:00"},{"alias_kind":"pith_short_16","alias_value":"P546BPMRJG4AEIQU","created_at":"2026-07-05T11:47:23.270667+00:00"},{"alias_kind":"pith_short_8","alias_value":"P546BPMR","created_at":"2026-07-05T11:47:23.270667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07494","citing_title":"Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27","json":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27.json","graph_json":"https://pith.science/api/pith-number/P546BPMRJG4AEIQUIYJFT6TG27/graph.json","events_json":"https://pith.science/api/pith-number/P546BPMRJG4AEIQUIYJFT6TG27/events.json","paper":"https://pith.science/paper/P546BPMR"},"agent_actions":{"view_html":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27","download_json":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27.json","view_paper":"https://pith.science/paper/P546BPMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12994&json=true","fetch_graph":"https://pith.science/api/pith-number/P546BPMRJG4AEIQUIYJFT6TG27/graph.json","fetch_events":"https://pith.science/api/pith-number/P546BPMRJG4AEIQUIYJFT6TG27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27/action/storage_attestation","attest_author":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27/action/author_attestation","sign_citation":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27/action/citation_signature","submit_replication":"https://pith.science/pith/P546BPMRJG4AEIQUIYJFT6TG27/action/replication_record"}},"created_at":"2026-07-05T11:47:23.270667+00:00","updated_at":"2026-07-05T11:47:23.270667+00:00"}