{"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"}