{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FDRD7BHMR76XUOABVEPKP7RBK3","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":"50b0cc787db1b8c8922dc4e3735abbab9ea0b9d7c8e015f34946f27986796f08","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-26T00:46:34Z","title_canon_sha256":"ed68462c3c77dc94ecbe63ff45fda18ab20d1dc7baaf1d2ec828818e8916be17"},"schema_version":"1.0","source":{"id":"2510.02327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.02327","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2510.02327v2","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02327","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"FDRD7BHMR76X","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"FDRD7BHMR76XUOAB","created_at":"2026-05-26T02:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"FDRD7BHM","created_at":"2026-05-26T02:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:dacf4b99bc5fdfe1b9769566ac12800233ce3ba76c8e9ef4686166ff1d16fe74","target":"graph","created_at":"2026-05-26T02:05:02Z","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/2510.02327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and semantic understanding. Conversely, cascaded systems combining automatic speech recognition, a text-based Large Language Model (LLM), and text-to-speech synthesis offer superior knowledge representation at the cost of high latency, which disrupts the flow of natural interaction. This paper introduces a novel hybrid architecture that bridges the gap between these two paradigms. Our framework processes user speech through an S2S transformer for immediate res","authors_text":"So Kuroki, Takuya Akiba, Yotaro Kubo, Yujin Tang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-26T00:46:34Z","title":"KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02327","kind":"arxiv","version":2},"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":"sha256:4c2741b2ca2a748fe64a3d3bb5c1e5b89ecc86f8f1690d1f6c74132b0c0070fb","target":"record","created_at":"2026-05-26T02:05:02Z","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":"50b0cc787db1b8c8922dc4e3735abbab9ea0b9d7c8e015f34946f27986796f08","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-26T00:46:34Z","title_canon_sha256":"ed68462c3c77dc94ecbe63ff45fda18ab20d1dc7baaf1d2ec828818e8916be17"},"schema_version":"1.0","source":{"id":"2510.02327","kind":"arxiv","version":2}},"canonical_sha256":"28e23f84ec8ffd7a3801a91ea7fe2156e6efb456ae8c840ca339a6af61212ee5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28e23f84ec8ffd7a3801a91ea7fe2156e6efb456ae8c840ca339a6af61212ee5","first_computed_at":"2026-05-26T02:05:02.728877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:02.728877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LzxcnmSAnUc4WeJuQ/qx8EJ3xCNaSWbzvhByoj2SJmkwlWKA6K9KR7TDJnA97+Begowz8CasJ09jGhGSyDwYDQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:02.729686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.02327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c2741b2ca2a748fe64a3d3bb5c1e5b89ecc86f8f1690d1f6c74132b0c0070fb","sha256:dacf4b99bc5fdfe1b9769566ac12800233ce3ba76c8e9ef4686166ff1d16fe74"],"state_sha256":"11932482dff070c6560ce86ddbe94654193dcff5c4b91cf1e527d8f1cd656a2c"}