{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4BCWFKVU6SXMLEBWUHETFAG6TU","short_pith_number":"pith:4BCWFKVU","schema_version":"1.0","canonical_sha256":"e04562aab4f4aec59036a1c93280de9d0dee961e0032af58931adf509bceb1bf","source":{"kind":"arxiv","id":"2409.15594","version":1},"attestation_state":"computed","paper":{"title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bandhav Veluri, Benjamin N Peloquin, Bokai Yu, Hongyu Gong, Shyamnath Gollakota","submitted_at":"2024-09-23T23:01:31Z","abstract_excerpt":"Despite broad interest in modeling spoken dialogue agents, most approaches are inherently \"half-duplex\" -- restricted to turn-based interaction with responses requiring explicit prompting by the user or implicit tracking of interruption or silence events. Human dialogue, by contrast, is \"full-duplex\" allowing for rich synchronicity in the form of quick and dynamic turn-taking, overlapping speech, and backchanneling. Technically, the challenge of achieving full-duplex dialogue with LLMs lies in modeling synchrony as pre-trained LLMs do not have a sense of \"time\". To bridge this gap, we propose "},"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":"2409.15594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T23:01:31Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8b51f83d29dab63dae8bb6a90dbb1253763ca5a3a43cd3af2101e52de2dc35a9","abstract_canon_sha256":"a949d48c99007d8f75174a4a8135076ae020892e92e58b87ac81378ddf015f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:57.088264Z","signature_b64":"ZooMi9UHktS4J8atuGXF9+vxHHIziLy/9iznDf9XXkyg9PhpL4TS2IE4hCEjKUgEKCFkFilJXI27UM2V1CkKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e04562aab4f4aec59036a1c93280de9d0dee961e0032af58931adf509bceb1bf","last_reissued_at":"2026-07-05T09:10:57.087743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:57.087743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bandhav Veluri, Benjamin N Peloquin, Bokai Yu, Hongyu Gong, Shyamnath Gollakota","submitted_at":"2024-09-23T23:01:31Z","abstract_excerpt":"Despite broad interest in modeling spoken dialogue agents, most approaches are inherently \"half-duplex\" -- restricted to turn-based interaction with responses requiring explicit prompting by the user or implicit tracking of interruption or silence events. Human dialogue, by contrast, is \"full-duplex\" allowing for rich synchronicity in the form of quick and dynamic turn-taking, overlapping speech, and backchanneling. Technically, the challenge of achieving full-duplex dialogue with LLMs lies in modeling synchrony as pre-trained LLMs do not have a sense of \"time\". To bridge this gap, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15594","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/2409.15594/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":"2409.15594","created_at":"2026-07-05T09:10:57.087804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15594v1","created_at":"2026-07-05T09:10:57.087804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15594","created_at":"2026-07-05T09:10:57.087804+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BCWFKVU6SXM","created_at":"2026-07-05T09:10:57.087804+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BCWFKVU6SXMLEBW","created_at":"2026-07-05T09:10:57.087804+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BCWFKVU","created_at":"2026-07-05T09:10:57.087804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU","json":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU.json","graph_json":"https://pith.science/api/pith-number/4BCWFKVU6SXMLEBWUHETFAG6TU/graph.json","events_json":"https://pith.science/api/pith-number/4BCWFKVU6SXMLEBWUHETFAG6TU/events.json","paper":"https://pith.science/paper/4BCWFKVU"},"agent_actions":{"view_html":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU","download_json":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU.json","view_paper":"https://pith.science/paper/4BCWFKVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15594&json=true","fetch_graph":"https://pith.science/api/pith-number/4BCWFKVU6SXMLEBWUHETFAG6TU/graph.json","fetch_events":"https://pith.science/api/pith-number/4BCWFKVU6SXMLEBWUHETFAG6TU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU/action/storage_attestation","attest_author":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU/action/author_attestation","sign_citation":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU/action/citation_signature","submit_replication":"https://pith.science/pith/4BCWFKVU6SXMLEBWUHETFAG6TU/action/replication_record"}},"created_at":"2026-07-05T09:10:57.087804+00:00","updated_at":"2026-07-05T09:10:57.087804+00:00"}