{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FDRD7BHMR76XUOABVEPKP7RBK3","short_pith_number":"pith:FDRD7BHM","schema_version":"1.0","canonical_sha256":"28e23f84ec8ffd7a3801a91ea7fe2156e6efb456ae8c840ca339a6af61212ee5","source":{"kind":"arxiv","id":"2510.02327","version":2},"attestation_state":"computed","paper":{"title":"KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"So Kuroki, Takuya Akiba, Yotaro Kubo, Yujin Tang","submitted_at":"2025-09-26T00:46:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.02327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-26T00:46:34Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"ed68462c3c77dc94ecbe63ff45fda18ab20d1dc7baaf1d2ec828818e8916be17","abstract_canon_sha256":"50b0cc787db1b8c8922dc4e3735abbab9ea0b9d7c8e015f34946f27986796f08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:02.729686Z","signature_b64":"LzxcnmSAnUc4WeJuQ/qx8EJ3xCNaSWbzvhByoj2SJmkwlWKA6K9KR7TDJnA97+Begowz8CasJ09jGhGSyDwYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28e23f84ec8ffd7a3801a91ea7fe2156e6efb456ae8c840ca339a6af61212ee5","last_reissued_at":"2026-05-26T02:05:02.728877Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:02.728877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"So Kuroki, Takuya Akiba, Yotaro Kubo, Yujin Tang","submitted_at":"2025-09-26T00:46:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02327","kind":"arxiv","version":2},"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/2510.02327/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.02327","created_at":"2026-05-26T02:05:02.729007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.02327v2","created_at":"2026-05-26T02:05:02.729007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02327","created_at":"2026-05-26T02:05:02.729007+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDRD7BHMR76X","created_at":"2026-05-26T02:05:02.729007+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDRD7BHMR76XUOAB","created_at":"2026-05-26T02:05:02.729007+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDRD7BHM","created_at":"2026-05-26T02:05:02.729007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":88,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3","json":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3.json","graph_json":"https://pith.science/api/pith-number/FDRD7BHMR76XUOABVEPKP7RBK3/graph.json","events_json":"https://pith.science/api/pith-number/FDRD7BHMR76XUOABVEPKP7RBK3/events.json","paper":"https://pith.science/paper/FDRD7BHM"},"agent_actions":{"view_html":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3","download_json":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3.json","view_paper":"https://pith.science/paper/FDRD7BHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.02327&json=true","fetch_graph":"https://pith.science/api/pith-number/FDRD7BHMR76XUOABVEPKP7RBK3/graph.json","fetch_events":"https://pith.science/api/pith-number/FDRD7BHMR76XUOABVEPKP7RBK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3/action/storage_attestation","attest_author":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3/action/author_attestation","sign_citation":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3/action/citation_signature","submit_replication":"https://pith.science/pith/FDRD7BHMR76XUOABVEPKP7RBK3/action/replication_record"}},"created_at":"2026-05-26T02:05:02.729007+00:00","updated_at":"2026-05-26T02:05:02.729007+00:00"}