{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZOWNAQOTY26PLPB5SK2BPF44X6","short_pith_number":"pith:ZOWNAQOT","schema_version":"1.0","canonical_sha256":"cbacd041d3c6bcf5bc3d92b417979cbf81f3af24bb7ade18271720d3806ae53a","source":{"kind":"arxiv","id":"2409.11727","version":1},"attestation_state":"computed","paper":{"title":"Enabling Real-Time Conversations with Minimal Training Costs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuo Wang, Wang Xu, Wanxiang Che, Weilin Zhao, Xu Han, Yudi Zhang, Yukun Yan, Zhe Tao, Zhiyuan Liu","submitted_at":"2024-09-18T06:27:26Z","abstract_excerpt":"Large language models (LLMs) have demonstrated the ability to improve human efficiency through conversational interactions. Conventional LLM-powered dialogue systems, operating on a turn-based paradigm, preclude real-time interaction during response generation. To address this limitation, researchers have proposed duplex models. These models can dynamically adapt to user input, facilitating real-time interactive feedback. However, these methods typically require substantial computational resources to acquire the ability. To reduce overhead, this paper presents a new duplex decoding approach th"},"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":"2409.11727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T06:27:26Z","cross_cats_sorted":[],"title_canon_sha256":"8a6110190de72016a8b8b0bf59c3738a9280fc157c6d8ab36ff0656bca37866a","abstract_canon_sha256":"98707cbf7f20f33e2eba16a699b6a8ecfb1e30da4d219fbada21e2979bd67b77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:36.664505Z","signature_b64":"eiA8SF7tZjJVbAl0Xse/rD/BBGdkcoaargAtgOoBxdNEdV0PWFFNh8u5TccQUnStSBZM53Hn1nX+G4+3pXcvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbacd041d3c6bcf5bc3d92b417979cbf81f3af24bb7ade18271720d3806ae53a","last_reissued_at":"2026-07-05T09:08:36.663632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:36.663632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Real-Time Conversations with Minimal Training Costs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuo Wang, Wang Xu, Wanxiang Che, Weilin Zhao, Xu Han, Yudi Zhang, Yukun Yan, Zhe Tao, Zhiyuan Liu","submitted_at":"2024-09-18T06:27:26Z","abstract_excerpt":"Large language models (LLMs) have demonstrated the ability to improve human efficiency through conversational interactions. Conventional LLM-powered dialogue systems, operating on a turn-based paradigm, preclude real-time interaction during response generation. To address this limitation, researchers have proposed duplex models. These models can dynamically adapt to user input, facilitating real-time interactive feedback. However, these methods typically require substantial computational resources to acquire the ability. To reduce overhead, this paper presents a new duplex decoding approach th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11727","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/2409.11727/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":"2409.11727","created_at":"2026-07-05T09:08:36.663693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11727v1","created_at":"2026-07-05T09:08:36.663693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11727","created_at":"2026-07-05T09:08:36.663693+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOWNAQOTY26P","created_at":"2026-07-05T09:08:36.663693+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOWNAQOTY26PLPB5","created_at":"2026-07-05T09:08:36.663693+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOWNAQOT","created_at":"2026-07-05T09:08:36.663693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.08528","citing_title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6","json":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6.json","graph_json":"https://pith.science/api/pith-number/ZOWNAQOTY26PLPB5SK2BPF44X6/graph.json","events_json":"https://pith.science/api/pith-number/ZOWNAQOTY26PLPB5SK2BPF44X6/events.json","paper":"https://pith.science/paper/ZOWNAQOT"},"agent_actions":{"view_html":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6","download_json":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6.json","view_paper":"https://pith.science/paper/ZOWNAQOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11727&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOWNAQOTY26PLPB5SK2BPF44X6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOWNAQOTY26PLPB5SK2BPF44X6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6/action/storage_attestation","attest_author":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6/action/author_attestation","sign_citation":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6/action/citation_signature","submit_replication":"https://pith.science/pith/ZOWNAQOTY26PLPB5SK2BPF44X6/action/replication_record"}},"created_at":"2026-07-05T09:08:36.663693+00:00","updated_at":"2026-07-05T09:08:36.663693+00:00"}