{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UYSY7OEGIRHBSOZTY6DXGTH5PF","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":"83d039de1195dab577834c49e8032381529dcdc97bbb62294628ea2772ab0448","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T05:38:39Z","title_canon_sha256":"d92c57d068affa0d66c75f728ecf6e67886aed2526dd4785dbf66de21e88c540"},"schema_version":"1.0","source":{"id":"2506.00843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00843","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00843v1","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00843","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"UYSY7OEGIRHB","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_16","alias_value":"UYSY7OEGIRHBSOZT","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_8","alias_value":"UYSY7OEG","created_at":"2026-07-05T11:13:41Z"}],"graph_snapshots":[{"event_id":"sha256:dc53d7a3cc9dda6821a7e27e08a3f09234c35831b0dbc114b82b4a919b3f92c5","target":"graph","created_at":"2026-07-05T11:13:41Z","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/2506.00843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective speech representations for spoken language models must balance semantic relevance with acoustic fidelity for high-quality reconstruction. However, existing approaches struggle to achieve both simultaneously. To address this, we introduce Hierarchical Acoustic and Semantic Representation Disentanglement (HASRD, pronounced `hazard'), a framework that factorizes self-supervised learning representations into discrete semantic and acoustic tokens. HASRD assigns the semantic representation to the first codebook, while encoding acoustic residuals in subsequent codebooks. This preserves ASR ","authors_text":"Amir Hussein, Francois G. Germain, Gordon Wichern, Jonathan Le Roux, Sameer Khurana","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T05:38:39Z","title":"HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00843","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":"sha256:91d9350b06807b32d6a9fcc64eef52b307830de0799f707da1414592a91e0d0c","target":"record","created_at":"2026-07-05T11:13:41Z","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":"83d039de1195dab577834c49e8032381529dcdc97bbb62294628ea2772ab0448","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-01T05:38:39Z","title_canon_sha256":"d92c57d068affa0d66c75f728ecf6e67886aed2526dd4785dbf66de21e88c540"},"schema_version":"1.0","source":{"id":"2506.00843","kind":"arxiv","version":1}},"canonical_sha256":"a6258fb886444e193b33c787734cfd79766d074e2d052b5259c377af931de2b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6258fb886444e193b33c787734cfd79766d074e2d052b5259c377af931de2b5","first_computed_at":"2026-07-05T11:13:41.510447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:41.510447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ZIQ6VvUvKUbjO708RG4Qxvu/2rX6JjTBDFfCoY0OZpede8vuUX/w0dJb8Z7gzfM2i+x02WUwBAEiGHBzz5ZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:41.510958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91d9350b06807b32d6a9fcc64eef52b307830de0799f707da1414592a91e0d0c","sha256:dc53d7a3cc9dda6821a7e27e08a3f09234c35831b0dbc114b82b4a919b3f92c5"],"state_sha256":"77184428a8820b9887bd5814ac20c23a6a604ca6d1a07a730ee23202f85ea750"}