{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S5QSIDQ7A2FGANPPYRR4ELKJLH","short_pith_number":"pith:S5QSIDQ7","canonical_record":{"source":{"id":"2606.30944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-29T21:55:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d211ddedfa358eeca1010903a8563e2fe4e8219c29f3de000047b72b60bd3719","abstract_canon_sha256":"119697e09dc2fae6ecb9f94dbbd77eea83800526696e90b0cef7f24f9c83bcb5"},"schema_version":"1.0"},"canonical_sha256":"9761240e1f068a6035efc463c22d4959e8a76f97e522748ee6dea618d91decac","source":{"kind":"arxiv","id":"2606.30944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30944","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30944v1","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30944","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"S5QSIDQ7A2FG","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"S5QSIDQ7A2FGANPP","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"S5QSIDQ7","created_at":"2026-07-01T00:17:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S5QSIDQ7A2FGANPPYRR4ELKJLH","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-29T21:55:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d211ddedfa358eeca1010903a8563e2fe4e8219c29f3de000047b72b60bd3719","abstract_canon_sha256":"119697e09dc2fae6ecb9f94dbbd77eea83800526696e90b0cef7f24f9c83bcb5"},"schema_version":"1.0"},"canonical_sha256":"9761240e1f068a6035efc463c22d4959e8a76f97e522748ee6dea618d91decac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:22.263957Z","signature_b64":"9ZslD41PL0VD3avzD2Nmyt3x+OCPa7DC6/u93bSx+EtXUfocQgKmFzUQODDx5u7fJjHCqPKssfoEIwjlRPItBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9761240e1f068a6035efc463c22d4959e8a76f97e522748ee6dea618d91decac","last_reissued_at":"2026-07-01T00:17:22.263538Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:22.263538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30944","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":"2026-07-01T00:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ow/FG5Y59+T7iOStiV24YFonTJVbd8YH8VofL7hCTQR8E46qbU9sGw+39Aji2WM7oYSkDy/o8TLmMg1FEWHOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:15:43.788678Z"},"content_sha256":"684fe866f57b18b2fd53760996d2c72f4e1c9818f8068f0eb48c986468797319","schema_version":"1.0","event_id":"sha256:684fe866f57b18b2fd53760996d2c72f4e1c9818f8068f0eb48c986468797319"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S5QSIDQ7A2FGANPPYRR4ELKJLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Heming Wang, Heng Lu, Jian Xue, Jinyu Li, Ruchao Fan, Shuohang Wang, Xiaofei Wang, Yao Qian, Yelong Shen, Young Jin Kim, Yuxuan Hu","submitted_at":"2026-06-29T21:55:18Z","abstract_excerpt":"Strong speech-to-text (S2T) LLMs already provide robust speech perception and text reasoning, but adding speech-to-speech (S2S) output is challenging: fine-tuning the backbone can degrade the original S2T performance, while attaching a downstream talker reintroduces a serial text-to-speech bottleneck. We present PRIME-Speech, a frozen-backbone S2S conversion framework that trains only speech-generation modules. PRIME-Speech synchronizes a causal audio post-decoder with intermediate hidden states of the frozen backbone, so codec tokens are generated from the model's evolving reasoning trajector"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30944","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/2606.30944/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":"2026-07-01T00:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gHasHLSYfT584CbeZGYPOiP5aoYj1Y9RV0cokr4yEBcpUxIUn43IpxaapLb1hY+iqEJkxllwkZKVdQsF6fwfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T08:15:43.789051Z"},"content_sha256":"3a978bec17bad47c19c4e4f3c231b430cdb005351fd967f27357c6ea428f2268","schema_version":"1.0","event_id":"sha256:3a978bec17bad47c19c4e4f3c231b430cdb005351fd967f27357c6ea428f2268"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH/bundle.json","state_url":"https://pith.science/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH/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":"2026-07-02T08:15:43Z","links":{"resolver":"https://pith.science/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH","bundle":"https://pith.science/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH/bundle.json","state":"https://pith.science/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5QSIDQ7A2FGANPPYRR4ELKJLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S5QSIDQ7A2FGANPPYRR4ELKJLH","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":"119697e09dc2fae6ecb9f94dbbd77eea83800526696e90b0cef7f24f9c83bcb5","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-29T21:55:18Z","title_canon_sha256":"d211ddedfa358eeca1010903a8563e2fe4e8219c29f3de000047b72b60bd3719"},"schema_version":"1.0","source":{"id":"2606.30944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30944","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30944v1","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30944","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"S5QSIDQ7A2FG","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"S5QSIDQ7A2FGANPP","created_at":"2026-07-01T00:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"S5QSIDQ7","created_at":"2026-07-01T00:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:3a978bec17bad47c19c4e4f3c231b430cdb005351fd967f27357c6ea428f2268","target":"graph","created_at":"2026-07-01T00:17:22Z","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/2606.30944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Strong speech-to-text (S2T) LLMs already provide robust speech perception and text reasoning, but adding speech-to-speech (S2S) output is challenging: fine-tuning the backbone can degrade the original S2T performance, while attaching a downstream talker reintroduces a serial text-to-speech bottleneck. We present PRIME-Speech, a frozen-backbone S2S conversion framework that trains only speech-generation modules. PRIME-Speech synchronizes a causal audio post-decoder with intermediate hidden states of the frozen backbone, so codec tokens are generated from the model's evolving reasoning trajector","authors_text":"Heming Wang, Heng Lu, Jian Xue, Jinyu Li, Ruchao Fan, Shuohang Wang, Xiaofei Wang, Yao Qian, Yelong Shen, Young Jin Kim, Yuxuan Hu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-29T21:55:18Z","title":"Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30944","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":"sha256:684fe866f57b18b2fd53760996d2c72f4e1c9818f8068f0eb48c986468797319","target":"record","created_at":"2026-07-01T00:17:22Z","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":"119697e09dc2fae6ecb9f94dbbd77eea83800526696e90b0cef7f24f9c83bcb5","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-29T21:55:18Z","title_canon_sha256":"d211ddedfa358eeca1010903a8563e2fe4e8219c29f3de000047b72b60bd3719"},"schema_version":"1.0","source":{"id":"2606.30944","kind":"arxiv","version":1}},"canonical_sha256":"9761240e1f068a6035efc463c22d4959e8a76f97e522748ee6dea618d91decac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9761240e1f068a6035efc463c22d4959e8a76f97e522748ee6dea618d91decac","first_computed_at":"2026-07-01T00:17:22.263538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:22.263538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ZslD41PL0VD3avzD2Nmyt3x+OCPa7DC6/u93bSx+EtXUfocQgKmFzUQODDx5u7fJjHCqPKssfoEIwjlRPItBg==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:22.263957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:684fe866f57b18b2fd53760996d2c72f4e1c9818f8068f0eb48c986468797319","sha256:3a978bec17bad47c19c4e4f3c231b430cdb005351fd967f27357c6ea428f2268"],"state_sha256":"bd9b40bef6227f758b41fecdc1f5a7e9f4a3a1fd87edd44f78540af76cae61c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BeT7qx/eYtoGx8sZoR+oxxGW4Db4wEx+BBYfn7SZ8cNkbE0qzHvFHwp7iNtEjYEIq3iQZuW1KJEOVtM1W1QDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T08:15:43.791007Z","bundle_sha256":"bb487aa76e3654a3954b0a3f9b361777bd96b8d98bce225fcd0783195ddf8bee"}}