{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MY57E57NC7T5YUXQT7AQZXQQIP","short_pith_number":"pith:MY57E57N","schema_version":"1.0","canonical_sha256":"663bf277ed17e7dc52f09fc10cde1043f4f74dfab2ffa2ea7794746a433e6ffe","source":{"kind":"arxiv","id":"2607.23204","version":1},"attestation_state":"computed","paper":{"title":"Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.RO","authors_text":"Koji Inoue, Yoshiki Ohira, Yuki Okafuji","submitted_at":"2026-07-25T13:54:50Z","abstract_excerpt":"Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage incremental framework that decouples prefatory-response preparation from speech onset. Once user intent becomes predictable, an intent readiness detector triggers LLM-based generation of a short prefatory response. Concurrently, a voice activity projection (VAP) model determines when to deliver it. Through a field experiment with a route-guidance robot in a shopping m"},"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":"2607.23204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-25T13:54:50Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a96f5ab0d2b5bd5b1985bb2b3ab780b1f4735b43f62fa481bfee70dd0abfb87e","abstract_canon_sha256":"4503a0c5a26a881b1db5420588fef8d3705f5706ec6b5c85beaefb78d753afd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:41.836399Z","signature_b64":"ap7jSrPa14KdWJ71HCE3EpVJTZYh92b9go+45UHAdQ8mJfvUlQvfOr0I4oal/7mBQSiDqw1I0PLRsOnu1Ic8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"663bf277ed17e7dc52f09fc10cde1043f4f74dfab2ffa2ea7794746a433e6ffe","last_reissued_at":"2026-07-28T01:22:41.835445Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:41.835445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.RO","authors_text":"Koji Inoue, Yoshiki Ohira, Yuki Okafuji","submitted_at":"2026-07-25T13:54:50Z","abstract_excerpt":"Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage incremental framework that decouples prefatory-response preparation from speech onset. Once user intent becomes predictable, an intent readiness detector triggers LLM-based generation of a short prefatory response. Concurrently, a voice activity projection (VAP) model determines when to deliver it. Through a field experiment with a route-guidance robot in a shopping m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23204","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/2607.23204/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":"2607.23204","created_at":"2026-07-28T01:22:41.835899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23204v1","created_at":"2026-07-28T01:22:41.835899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23204","created_at":"2026-07-28T01:22:41.835899+00:00"},{"alias_kind":"pith_short_12","alias_value":"MY57E57NC7T5","created_at":"2026-07-28T01:22:41.835899+00:00"},{"alias_kind":"pith_short_16","alias_value":"MY57E57NC7T5YUXQ","created_at":"2026-07-28T01:22:41.835899+00:00"},{"alias_kind":"pith_short_8","alias_value":"MY57E57N","created_at":"2026-07-28T01:22:41.835899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP","json":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP.json","graph_json":"https://pith.science/api/pith-number/MY57E57NC7T5YUXQT7AQZXQQIP/graph.json","events_json":"https://pith.science/api/pith-number/MY57E57NC7T5YUXQT7AQZXQQIP/events.json","paper":"https://pith.science/paper/MY57E57N"},"agent_actions":{"view_html":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP","download_json":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP.json","view_paper":"https://pith.science/paper/MY57E57N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23204&json=true","fetch_graph":"https://pith.science/api/pith-number/MY57E57NC7T5YUXQT7AQZXQQIP/graph.json","fetch_events":"https://pith.science/api/pith-number/MY57E57NC7T5YUXQT7AQZXQQIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP/action/storage_attestation","attest_author":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP/action/author_attestation","sign_citation":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP/action/citation_signature","submit_replication":"https://pith.science/pith/MY57E57NC7T5YUXQT7AQZXQQIP/action/replication_record"}},"created_at":"2026-07-28T01:22:41.835899+00:00","updated_at":"2026-07-28T01:22:41.835899+00:00"}