{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TPUJOZFJD2AI2GLYMYT4HGEBXA","short_pith_number":"pith:TPUJOZFJ","schema_version":"1.0","canonical_sha256":"9be89764a91e808d19786627c39881b80665ea6ae17b43cc73a2d13414a0a6c3","source":{"kind":"arxiv","id":"2606.06743","version":1},"attestation_state":"computed","paper":{"title":"HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SD","authors_text":"Arjun Gangwar, S Umesh","submitted_at":"2026-06-04T21:57:18Z","abstract_excerpt":"The popularity of neural audio codecs as speech tokenizers has surged with the advent of Multimodal Large Language Models. New codec architectures with semantic and acoustic disentanglement have emerged. There are two main approaches to introduce semantic information into codec models: one distills semantic information from SSL representations into the first RVQ layer, while the other maintains separate streams for semantic and acoustic features. We propose HybridCodec, a unified architecture that combines both paradigms. It employs separate semantic and acoustic branches while distilling SSL "},"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":"2606.06743","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T21:57:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b5df85303bac408331cbeff2c3d31c62ce5d7bca547dfaaa89dce36a4be6aa33","abstract_canon_sha256":"af3effd693568e5beb354ad37e38b17d081adab60ba7d2188517c7d0e3d3cbe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:25.706994Z","signature_b64":"gl7/vQisAvRmVtlDiAJ5iJyL+qgdYDigmiu5lTsy+AdpCFrq8QBy0cc09r+q6S7JzrgpWmFIpUvvbOwt7AClAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9be89764a91e808d19786627c39881b80665ea6ae17b43cc73a2d13414a0a6c3","last_reissued_at":"2026-06-08T01:04:25.706167Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:25.706167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HybridCodec: Fast Dual-Stream, Semantically Enhanced Neural Audio Codec","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SD","authors_text":"Arjun Gangwar, S Umesh","submitted_at":"2026-06-04T21:57:18Z","abstract_excerpt":"The popularity of neural audio codecs as speech tokenizers has surged with the advent of Multimodal Large Language Models. New codec architectures with semantic and acoustic disentanglement have emerged. There are two main approaches to introduce semantic information into codec models: one distills semantic information from SSL representations into the first RVQ layer, while the other maintains separate streams for semantic and acoustic features. We propose HybridCodec, a unified architecture that combines both paradigms. It employs separate semantic and acoustic branches while distilling SSL "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06743","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/2606.06743/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":"2606.06743","created_at":"2026-06-08T01:04:25.706303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06743v1","created_at":"2026-06-08T01:04:25.706303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06743","created_at":"2026-06-08T01:04:25.706303+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPUJOZFJD2AI","created_at":"2026-06-08T01:04:25.706303+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPUJOZFJD2AI2GLY","created_at":"2026-06-08T01:04:25.706303+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPUJOZFJ","created_at":"2026-06-08T01:04:25.706303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA","json":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA.json","graph_json":"https://pith.science/api/pith-number/TPUJOZFJD2AI2GLYMYT4HGEBXA/graph.json","events_json":"https://pith.science/api/pith-number/TPUJOZFJD2AI2GLYMYT4HGEBXA/events.json","paper":"https://pith.science/paper/TPUJOZFJ"},"agent_actions":{"view_html":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA","download_json":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA.json","view_paper":"https://pith.science/paper/TPUJOZFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06743&json=true","fetch_graph":"https://pith.science/api/pith-number/TPUJOZFJD2AI2GLYMYT4HGEBXA/graph.json","fetch_events":"https://pith.science/api/pith-number/TPUJOZFJD2AI2GLYMYT4HGEBXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA/action/storage_attestation","attest_author":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA/action/author_attestation","sign_citation":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA/action/citation_signature","submit_replication":"https://pith.science/pith/TPUJOZFJD2AI2GLYMYT4HGEBXA/action/replication_record"}},"created_at":"2026-06-08T01:04:25.706303+00:00","updated_at":"2026-06-08T01:04:25.706303+00:00"}