{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NITTELWRF2HVKDPH2GD6C7QHA4","short_pith_number":"pith:NITTELWR","schema_version":"1.0","canonical_sha256":"6a27322ed12e8f550de7d187e17e070720bc2ac6e76cbcbec5a8c67145f8072c","source":{"kind":"arxiv","id":"2508.07375","version":3},"attestation_state":"computed","paper":{"title":"TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haoli Bai, Irwin King, Lei Zhu, Lu Hou, Wenqian Cui, Xiaohui Li, Zhihan Guo","submitted_at":"2025-08-10T14:49:43Z","abstract_excerpt":"Full-Duplex Speech Language Models (FD-SLMs) are specialized foundation models designed to enable natural, real-time spoken interactions by modeling complex conversational turn-taking such as interruptions, backchannels, and overlapping speech. End-to-end (e2e) FD-SLMs leverage real-world double-channel conversational data to capture nuanced two-speaker dialogue patterns for human-like interactions, but their conversational abilities often degrade compared to pure-text conversation due to prolonged speech sequences and limited high-quality spoken dialogue data. Although interleaved text-speech"},"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":"2508.07375","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T14:49:43Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bab8dbeb77bbbadca961e05e7cfdf86f83d54bb89727595daad989da40856d64","abstract_canon_sha256":"a99853ccaf69d07c1cb6f00d18b8fa357a3d708c292b4f997005e46258088bab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:12.179595Z","signature_b64":"qK3t5BqwWHewbLFWu3cXsZ0KIi6Vy2vsNjyFNF3xGrSLY9O9zIgHZtS2xdGC5tKT2dezzaz5sk96tnpDicu7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a27322ed12e8f550de7d187e17e070720bc2ac6e76cbcbec5a8c67145f8072c","last_reissued_at":"2026-06-19T16:11:12.179182Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:12.179182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Haoli Bai, Irwin King, Lei Zhu, Lu Hou, Wenqian Cui, Xiaohui Li, Zhihan Guo","submitted_at":"2025-08-10T14:49:43Z","abstract_excerpt":"Full-Duplex Speech Language Models (FD-SLMs) are specialized foundation models designed to enable natural, real-time spoken interactions by modeling complex conversational turn-taking such as interruptions, backchannels, and overlapping speech. End-to-end (e2e) FD-SLMs leverage real-world double-channel conversational data to capture nuanced two-speaker dialogue patterns for human-like interactions, but their conversational abilities often degrade compared to pure-text conversation due to prolonged speech sequences and limited high-quality spoken dialogue data. Although interleaved text-speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07375","kind":"arxiv","version":3},"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/2508.07375/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":"2508.07375","created_at":"2026-06-19T16:11:12.179238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07375v3","created_at":"2026-06-19T16:11:12.179238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07375","created_at":"2026-06-19T16:11:12.179238+00:00"},{"alias_kind":"pith_short_12","alias_value":"NITTELWRF2HV","created_at":"2026-06-19T16:11:12.179238+00:00"},{"alias_kind":"pith_short_16","alias_value":"NITTELWRF2HVKDPH","created_at":"2026-06-19T16:11:12.179238+00:00"},{"alias_kind":"pith_short_8","alias_value":"NITTELWR","created_at":"2026-06-19T16:11:12.179238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.05927","citing_title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05927","citing_title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4","json":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4.json","graph_json":"https://pith.science/api/pith-number/NITTELWRF2HVKDPH2GD6C7QHA4/graph.json","events_json":"https://pith.science/api/pith-number/NITTELWRF2HVKDPH2GD6C7QHA4/events.json","paper":"https://pith.science/paper/NITTELWR"},"agent_actions":{"view_html":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4","download_json":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4.json","view_paper":"https://pith.science/paper/NITTELWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07375&json=true","fetch_graph":"https://pith.science/api/pith-number/NITTELWRF2HVKDPH2GD6C7QHA4/graph.json","fetch_events":"https://pith.science/api/pith-number/NITTELWRF2HVKDPH2GD6C7QHA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4/action/storage_attestation","attest_author":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4/action/author_attestation","sign_citation":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4/action/citation_signature","submit_replication":"https://pith.science/pith/NITTELWRF2HVKDPH2GD6C7QHA4/action/replication_record"}},"created_at":"2026-06-19T16:11:12.179238+00:00","updated_at":"2026-06-19T16:11:12.179238+00:00"}