{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XURA7PFBESKIITWEDG2UXBUED6","short_pith_number":"pith:XURA7PFB","schema_version":"1.0","canonical_sha256":"bd220fbca12494844ec419b54b86841fb576abde547fe014ac00fa1e7246bc05","source":{"kind":"arxiv","id":"2402.12208","version":4},"attestation_state":"computed","paper":{"title":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dingdong Wang, Hai Huang, Hanting Wang, Jialong Zuo, Minghui Fang, Shengpeng Ji, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-02-19T15:12:12Z","abstract_excerpt":"In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an intermediate representation replacing the mel-spectrogram. However, there exist several gaps between discrete codecs and downstream speech language models. Specifically, 1) Due to the reconstruction paradigm of the Codec model and the structure of residual vector quantization, the initial channel of the codebooks contains excessive information, making it challe"},"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":"2402.12208","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-19T15:12:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6ce34230629ccde9ea29fec03ad989bae9b30f003cb64b85ad4de6b65ed191f7","abstract_canon_sha256":"56aa823a2266f0f046be1113743f698849b9182082131a955220c543f50d0c97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:36.991312Z","signature_b64":"D053jX+eeQuEHccnPQEvR3sarqPFEeFN7Ylogv8c93vLy9GEN4zb3GYliTAtXkvomg2TusDTMBlLna4N5COIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd220fbca12494844ec419b54b86841fb576abde547fe014ac00fa1e7246bc05","last_reissued_at":"2026-07-05T11:15:36.990816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:36.990816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dingdong Wang, Hai Huang, Hanting Wang, Jialong Zuo, Minghui Fang, Shengpeng Ji, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-02-19T15:12:12Z","abstract_excerpt":"In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these models is the discrete acoustic codecs, which serve as an intermediate representation replacing the mel-spectrogram. However, there exist several gaps between discrete codecs and downstream speech language models. Specifically, 1) Due to the reconstruction paradigm of the Codec model and the structure of residual vector quantization, the initial channel of the codebooks contains excessive information, making it challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12208","kind":"arxiv","version":4},"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/2402.12208/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":"2402.12208","created_at":"2026-07-05T11:15:36.990874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12208v4","created_at":"2026-07-05T11:15:36.990874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12208","created_at":"2026-07-05T11:15:36.990874+00:00"},{"alias_kind":"pith_short_12","alias_value":"XURA7PFBESKI","created_at":"2026-07-05T11:15:36.990874+00:00"},{"alias_kind":"pith_short_16","alias_value":"XURA7PFBESKIITWE","created_at":"2026-07-05T11:15:36.990874+00:00"},{"alias_kind":"pith_short_8","alias_value":"XURA7PFB","created_at":"2026-07-05T11:15:36.990874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6","json":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6.json","graph_json":"https://pith.science/api/pith-number/XURA7PFBESKIITWEDG2UXBUED6/graph.json","events_json":"https://pith.science/api/pith-number/XURA7PFBESKIITWEDG2UXBUED6/events.json","paper":"https://pith.science/paper/XURA7PFB"},"agent_actions":{"view_html":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6","download_json":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6.json","view_paper":"https://pith.science/paper/XURA7PFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12208&json=true","fetch_graph":"https://pith.science/api/pith-number/XURA7PFBESKIITWEDG2UXBUED6/graph.json","fetch_events":"https://pith.science/api/pith-number/XURA7PFBESKIITWEDG2UXBUED6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6/action/storage_attestation","attest_author":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6/action/author_attestation","sign_citation":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6/action/citation_signature","submit_replication":"https://pith.science/pith/XURA7PFBESKIITWEDG2UXBUED6/action/replication_record"}},"created_at":"2026-07-05T11:15:36.990874+00:00","updated_at":"2026-07-05T11:15:36.990874+00:00"}