{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U42ARJZ6FJTTDQ4MDAJ3TO56CB","short_pith_number":"pith:U42ARJZ6","schema_version":"1.0","canonical_sha256":"a73408a73e2a6731c38c1813b9bbbe104c25be3bf9d074afc157cdcfe5827fea","source":{"kind":"arxiv","id":"2410.14411","version":1},"attestation_state":"computed","paper":{"title":"SNAC: Multi-Scale Neural Audio Codec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Gr\\\"otschla, Hubert Siuzdak, Luca A. Lanzend\\\"orfer","submitted_at":"2024-10-18T12:24:05Z","abstract_excerpt":"Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use language modeling approaches for audio generation and understanding. Residual Vector Quantization (RVQ) has become the standard technique for neural audio compression using a cascade of VQ codebooks. This paper proposes the Multi-Scale Neural Audio Codec, a simple extension of RVQ where the quantizers can operate at different temporal resolutions. By applying a hierarchy of quantizers at variable frame rates, the codec adapts to the aud"},"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":"2410.14411","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-18T12:24:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d6d70118680b8e8b2e8f87f6e71c93636a8cb7463dcab9ce9e78b51a25412a07","abstract_canon_sha256":"6d376841dd04c1c0a9208d48e0d5ae1e1262d28b47e6be89fce697acb004e86a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:31.964245Z","signature_b64":"gEEHeq1ybMYhL31ZBMIq78Og/ziz4HNVJq+mI4zI2teYxGoYSlP04E2lMtm+n+3ZGqyYekFDwnAy6eo7/W40BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a73408a73e2a6731c38c1813b9bbbe104c25be3bf9d074afc157cdcfe5827fea","last_reissued_at":"2026-07-05T09:22:31.963809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:31.963809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SNAC: Multi-Scale Neural Audio Codec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Gr\\\"otschla, Hubert Siuzdak, Luca A. Lanzend\\\"orfer","submitted_at":"2024-10-18T12:24:05Z","abstract_excerpt":"Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use language modeling approaches for audio generation and understanding. Residual Vector Quantization (RVQ) has become the standard technique for neural audio compression using a cascade of VQ codebooks. This paper proposes the Multi-Scale Neural Audio Codec, a simple extension of RVQ where the quantizers can operate at different temporal resolutions. By applying a hierarchy of quantizers at variable frame rates, the codec adapts to the aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14411","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/2410.14411/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":"2410.14411","created_at":"2026-07-05T09:22:31.963865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14411v1","created_at":"2026-07-05T09:22:31.963865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14411","created_at":"2026-07-05T09:22:31.963865+00:00"},{"alias_kind":"pith_short_12","alias_value":"U42ARJZ6FJTT","created_at":"2026-07-05T09:22:31.963865+00:00"},{"alias_kind":"pith_short_16","alias_value":"U42ARJZ6FJTTDQ4M","created_at":"2026-07-05T09:22:31.963865+00:00"},{"alias_kind":"pith_short_8","alias_value":"U42ARJZ6","created_at":"2026-07-05T09:22:31.963865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21727","citing_title":"Towards Detecting Neural Audio Codec Synthesized Heart Sounds","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12940","citing_title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12688","citing_title":"M*: A Modular, Extensible, Serving System for Multimodal Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":246,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29480","citing_title":"DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2504.08528","citing_title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26296","citing_title":"SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB","json":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB.json","graph_json":"https://pith.science/api/pith-number/U42ARJZ6FJTTDQ4MDAJ3TO56CB/graph.json","events_json":"https://pith.science/api/pith-number/U42ARJZ6FJTTDQ4MDAJ3TO56CB/events.json","paper":"https://pith.science/paper/U42ARJZ6"},"agent_actions":{"view_html":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB","download_json":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB.json","view_paper":"https://pith.science/paper/U42ARJZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14411&json=true","fetch_graph":"https://pith.science/api/pith-number/U42ARJZ6FJTTDQ4MDAJ3TO56CB/graph.json","fetch_events":"https://pith.science/api/pith-number/U42ARJZ6FJTTDQ4MDAJ3TO56CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB/action/storage_attestation","attest_author":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB/action/author_attestation","sign_citation":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB/action/citation_signature","submit_replication":"https://pith.science/pith/U42ARJZ6FJTTDQ4MDAJ3TO56CB/action/replication_record"}},"created_at":"2026-07-05T09:22:31.963865+00:00","updated_at":"2026-07-05T09:22:31.963865+00:00"}