{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FXTFWQJWDWAICFDYPIVSEIIYR3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"951e656dbce75348adc1ac8d6e7ac520df85f16714d0263621622f50d0955757","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-18T13:36:34Z","title_canon_sha256":"95d6c4998f25d6442b045f2c6fc55c042accc876a57427c3665e732ed0fa625a"},"schema_version":"1.0","source":{"id":"2506.15456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15456","created_at":"2026-07-05T11:23:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15456v1","created_at":"2026-07-05T11:23:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15456","created_at":"2026-07-05T11:23:44Z"},{"alias_kind":"pith_short_12","alias_value":"FXTFWQJWDWAI","created_at":"2026-07-05T11:23:44Z"},{"alias_kind":"pith_short_16","alias_value":"FXTFWQJWDWAICFDY","created_at":"2026-07-05T11:23:44Z"},{"alias_kind":"pith_short_8","alias_value":"FXTFWQJW","created_at":"2026-07-05T11:23:44Z"}],"graph_snapshots":[{"event_id":"sha256:12bc9f9c66fb2cba8da052dfc03f5e41c33fad899f5a39f19276759577b939cf","target":"graph","created_at":"2026-07-05T11:23:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.15456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single model. HAC leverages two knowledge distillation objectives: one from a pre-trained speech encoder (HuBERT) for phoneme-level structure, and another from a text-based encoder (LaBSE) for lexical cues. Experiments on English and multilingual data show that HAC's factorized bottleneck yields disentangled token sets: one aligns with phonemes, while another captures word-level semantics. Quantitative evaluations confirm ","authors_text":"Amir Hussein, Antoine Laurent, Chiori Hori, Dominik Bobos, Dominik Klement, Ellen Zhang, Francois G. Germain, Gordon Wichern, Jonathan Le Roux, Juraj Novosad, Peter Gazdik, Ricard Marxer, Ryo Aihara, Sameer Khurana, Yoshiki Masuyama, Zili Huang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-18T13:36:34Z","title":"Factorized RVQ-GAN For Disentangled Speech Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15456","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d767aa06663b3335762747d273829d21c8a0f00565fd6507d53a22a436087517","target":"record","created_at":"2026-07-05T11:23:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"951e656dbce75348adc1ac8d6e7ac520df85f16714d0263621622f50d0955757","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-18T13:36:34Z","title_canon_sha256":"95d6c4998f25d6442b045f2c6fc55c042accc876a57427c3665e732ed0fa625a"},"schema_version":"1.0","source":{"id":"2506.15456","kind":"arxiv","version":1}},"canonical_sha256":"2de65b41361d808114787a2b2221188ec8c6cea6f65d6e0e64694f127ba29a6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2de65b41361d808114787a2b2221188ec8c6cea6f65d6e0e64694f127ba29a6d","first_computed_at":"2026-07-05T11:23:44.011506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:44.011506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yezTIpM4M5MBOAkjaBtzFc98p92PICPshHrS1kp5LRSQPmmU41Vbwqy6mnXpfNPpWzpoLN+xQLrvnZ7OzGcFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:44.011985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d767aa06663b3335762747d273829d21c8a0f00565fd6507d53a22a436087517","sha256:12bc9f9c66fb2cba8da052dfc03f5e41c33fad899f5a39f19276759577b939cf"],"state_sha256":"d15374164137a5a33bab2200626ffd9661bea6c77d93a91fcf57e6b628a3aa43"}