{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5RGITEMCHMP3HVF4FPL3EUGXYL","short_pith_number":"pith:5RGITEMC","canonical_record":{"source":{"id":"2606.21888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T05:19:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0b88669d0dddd6ccf6275ae88e6d022d5112b85be96f96ea2f409217f1bf968f","abstract_canon_sha256":"cc391a8ff2a21053303df5895d65e9f1e435640a06968519e52f83b2458e95b8"},"schema_version":"1.0"},"canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","source":{"kind":"arxiv","id":"2606.21888","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21888","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21888v1","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21888","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"5RGITEMCHMP3","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"5RGITEMCHMP3HVF4","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"5RGITEMC","created_at":"2026-06-23T02:13:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5RGITEMCHMP3HVF4FPL3EUGXYL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21888","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T05:19:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0b88669d0dddd6ccf6275ae88e6d022d5112b85be96f96ea2f409217f1bf968f","abstract_canon_sha256":"cc391a8ff2a21053303df5895d65e9f1e435640a06968519e52f83b2458e95b8"},"schema_version":"1.0"},"canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:01.960080Z","signature_b64":"1CZPjaGg7UlaBAaxax2ngojtcRh+iNj5n0VCCOSzGMQHJqv+M+925e5ekFrtzLJ69VAIC1Ty4NMNel3EXZkKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","last_reissued_at":"2026-06-23T02:13:01.959699Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:01.959699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21888","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWCNR4lWoCWLCshWV0SwQNHA6ouy55y7loqj42vr/JGOnRnJVLQMhbP/wyFjfo5e8dsVFv5mSW+EpKb0hPrXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:29:48.342161Z"},"content_sha256":"f0deb80432fc2cd59649d399d1c3e5a035a3d237a70b529cb7eb565c1d549e3b","schema_version":"1.0","event_id":"sha256:f0deb80432fc2cd59649d399d1c3e5a035a3d237a70b529cb7eb565c1d549e3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5RGITEMCHMP3HVF4FPL3EUGXYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung, Shujie Hu","submitted_at":"2026-06-20T05:19:07Z","abstract_excerpt":"Neural speech codecs efficiently compress speech and have become a foundation for speech generation, but they are typically learned as holistic representations that intertwine linguistic content, speaker identity, and prosody. While this design is effective for zero-shot voice cloning, it hinders downstream tasks that require prosody preservation or transfer, such as voice conversion. To address this, we introduce ProsoCodec, a prosody-oriented speech codec that models prosody as a conditional residual rather than as a disentangled stream. Specifically, by conditioning both the encoder and dec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21888","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/2606.21888/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KEERyeDSTlFcQz5OlPdRktoald/BNk7sPJF3UbUXYRMU3Wre30JV1AuLQJHIECkI3ioh/HQSYYOJz0cgruKJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:29:48.342547Z"},"content_sha256":"4fc5c198090b35b1c863a3f07e1d797fcbe08630c2ceb0fec4f08524704f743b","schema_version":"1.0","event_id":"sha256:4fc5c198090b35b1c863a3f07e1d797fcbe08630c2ceb0fec4f08524704f743b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/bundle.json","state_url":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T18:29:48Z","links":{"resolver":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL","bundle":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/bundle.json","state":"https://pith.science/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RGITEMCHMP3HVF4FPL3EUGXYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5RGITEMCHMP3HVF4FPL3EUGXYL","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":"cc391a8ff2a21053303df5895d65e9f1e435640a06968519e52f83b2458e95b8","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T05:19:07Z","title_canon_sha256":"0b88669d0dddd6ccf6275ae88e6d022d5112b85be96f96ea2f409217f1bf968f"},"schema_version":"1.0","source":{"id":"2606.21888","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21888","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21888v1","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21888","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_12","alias_value":"5RGITEMCHMP3","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_16","alias_value":"5RGITEMCHMP3HVF4","created_at":"2026-06-23T02:13:01Z"},{"alias_kind":"pith_short_8","alias_value":"5RGITEMC","created_at":"2026-06-23T02:13:01Z"}],"graph_snapshots":[{"event_id":"sha256:4fc5c198090b35b1c863a3f07e1d797fcbe08630c2ceb0fec4f08524704f743b","target":"graph","created_at":"2026-06-23T02:13:01Z","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/2606.21888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural speech codecs efficiently compress speech and have become a foundation for speech generation, but they are typically learned as holistic representations that intertwine linguistic content, speaker identity, and prosody. While this design is effective for zero-shot voice cloning, it hinders downstream tasks that require prosody preservation or transfer, such as voice conversion. To address this, we introduce ProsoCodec, a prosody-oriented speech codec that models prosody as a conditional residual rather than as a disentangled stream. Specifically, by conditioning both the encoder and dec","authors_text":"Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung, Shujie Hu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T05:19:07Z","title":"ProsoCodec: Prosody-Oriented Speech Codec for Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21888","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:f0deb80432fc2cd59649d399d1c3e5a035a3d237a70b529cb7eb565c1d549e3b","target":"record","created_at":"2026-06-23T02:13:01Z","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":"cc391a8ff2a21053303df5895d65e9f1e435640a06968519e52f83b2458e95b8","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-20T05:19:07Z","title_canon_sha256":"0b88669d0dddd6ccf6275ae88e6d022d5112b85be96f96ea2f409217f1bf968f"},"schema_version":"1.0","source":{"id":"2606.21888","kind":"arxiv","version":1}},"canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4c8991823b1fb3d4bc2bd7b250d7c2df8e92265a1c786e14a6c2a7a659c3f9","first_computed_at":"2026-06-23T02:13:01.959699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:01.959699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1CZPjaGg7UlaBAaxax2ngojtcRh+iNj5n0VCCOSzGMQHJqv+M+925e5ekFrtzLJ69VAIC1Ty4NMNel3EXZkKCg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:01.960080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21888","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0deb80432fc2cd59649d399d1c3e5a035a3d237a70b529cb7eb565c1d549e3b","sha256:4fc5c198090b35b1c863a3f07e1d797fcbe08630c2ceb0fec4f08524704f743b"],"state_sha256":"a148f46056f3f6d21bcaaf03374b686973246174ed4e646cde7ade88d6a83281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DxYVld30ru9QV9g2T1MIKTD3JiN/cCJEyuWLX5E4kulLxTWTUpk0huhRkfiB8t/Q6ErAC1ChIQcgPujFq2iXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:29:48.344572Z","bundle_sha256":"e8fdff7ce4a2a35f09e72edc819c771b3d0cdd3810b9d224b36ec8a6e1710f0a"}}