{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DWQY4BIRPKYKW2R5EMFNMPW2VA","short_pith_number":"pith:DWQY4BIR","schema_version":"1.0","canonical_sha256":"1da18e05117ab0ab6a3d230ad63edaa827ee1aa6b57650bab3cf09bdca157294","source":{"kind":"arxiv","id":"2409.11228","version":2},"attestation_state":"computed","paper":{"title":"Learning Source Disentanglement in Neural Audio Codec","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ga\\\"el Richard, Xiaoyu Bie, Xubo Liu","submitted_at":"2024-09-17T14:21:02Z","abstract_excerpt":"Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative models trained on these tokens. However, existing neural codec models are typically trained on large, undifferentiated audio datasets, neglecting the essential discrepancies between sound domains like speech, music, and environmental sound effects. This oversight complicates data modeling and poses additional challenges to the controllability of sound gener"},"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":"2409.11228","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-17T14:21:02Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"b7fc5e22b8b494770e4e3d134009e0a03f612cbb235ac6623855cba5c3cd0021","abstract_canon_sha256":"2e83088a529c0a1ad2733ed30bba7a88942a26fd5b97240cbb658e70a5c3d6ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:19.936526Z","signature_b64":"jRofzm0iMfVYXCIrb8/Xw6ycOp56GTDMWxZ7Z4cdPpOVNWMuiIvhnu/i988qRxXf/jorjfuqLK05vCgGLu8KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1da18e05117ab0ab6a3d230ad63edaa827ee1aa6b57650bab3cf09bdca157294","last_reissued_at":"2026-07-05T10:12:19.936128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:19.936128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Source Disentanglement in Neural Audio Codec","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ga\\\"el Richard, Xiaoyu Bie, Xubo Liu","submitted_at":"2024-09-17T14:21:02Z","abstract_excerpt":"Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative models trained on these tokens. However, existing neural codec models are typically trained on large, undifferentiated audio datasets, neglecting the essential discrepancies between sound domains like speech, music, and environmental sound effects. This oversight complicates data modeling and poses additional challenges to the controllability of sound gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11228","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/2409.11228/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":"2409.11228","created_at":"2026-07-05T10:12:19.936185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11228v2","created_at":"2026-07-05T10:12:19.936185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11228","created_at":"2026-07-05T10:12:19.936185+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWQY4BIRPKYK","created_at":"2026-07-05T10:12:19.936185+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWQY4BIRPKYKW2R5","created_at":"2026-07-05T10:12:19.936185+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWQY4BIR","created_at":"2026-07-05T10:12:19.936185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA","json":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA.json","graph_json":"https://pith.science/api/pith-number/DWQY4BIRPKYKW2R5EMFNMPW2VA/graph.json","events_json":"https://pith.science/api/pith-number/DWQY4BIRPKYKW2R5EMFNMPW2VA/events.json","paper":"https://pith.science/paper/DWQY4BIR"},"agent_actions":{"view_html":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA","download_json":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA.json","view_paper":"https://pith.science/paper/DWQY4BIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11228&json=true","fetch_graph":"https://pith.science/api/pith-number/DWQY4BIRPKYKW2R5EMFNMPW2VA/graph.json","fetch_events":"https://pith.science/api/pith-number/DWQY4BIRPKYKW2R5EMFNMPW2VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA/action/storage_attestation","attest_author":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA/action/author_attestation","sign_citation":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA/action/citation_signature","submit_replication":"https://pith.science/pith/DWQY4BIRPKYKW2R5EMFNMPW2VA/action/replication_record"}},"created_at":"2026-07-05T10:12:19.936185+00:00","updated_at":"2026-07-05T10:12:19.936185+00:00"}