{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7S4Z7POEOLOB5GSTNPDCWGSBC4","short_pith_number":"pith:7S4Z7POE","schema_version":"1.0","canonical_sha256":"fcb99fbdc472dc1e9a536bc62b1a411720d6f35f129e4934e23d251bf064fe0b","source":{"kind":"arxiv","id":"2501.08946","version":1},"attestation_state":"computed","paper":{"title":"Applying General Turn-taking Models to Conversational Human-Robot Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CL","authors_text":"Bahar Irfan, Gabriel Skantze","submitted_at":"2025-01-15T16:49:22Z","abstract_excerpt":"Turn-taking is a fundamental aspect of conversation, but current Human-Robot Interaction (HRI) systems often rely on simplistic, silence-based models, leading to unnatural pauses and interruptions. This paper investigates, for the first time, the application of general turn-taking models, specifically TurnGPT and Voice Activity Projection (VAP), to improve conversational dynamics in HRI. These models are trained on human-human dialogue data using self-supervised learning objectives, without requiring domain-specific fine-tuning. We propose methods for using these models in tandem to predict wh"},"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":"2501.08946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T16:49:22Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"05c5012b0f30913ae19cd9c669421ca5698568116c1d586ea303500cbbcdd67c","abstract_canon_sha256":"f9e3fc8aaf91a2038e4698a7caaa8293b82645637867c4e5e0ce2e0988991ed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:28.284517Z","signature_b64":"3FSPBADW5XRHPGeZujhY+1guEe4vXibW47yFhc/HRpZ+1aqZrCyfdCx7WJF5GmNH7v5OfA9K/Y9ZfYDGCTbcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcb99fbdc472dc1e9a536bc62b1a411720d6f35f129e4934e23d251bf064fe0b","last_reissued_at":"2026-07-05T10:01:28.284040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:28.284040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Applying General Turn-taking Models to Conversational Human-Robot Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CL","authors_text":"Bahar Irfan, Gabriel Skantze","submitted_at":"2025-01-15T16:49:22Z","abstract_excerpt":"Turn-taking is a fundamental aspect of conversation, but current Human-Robot Interaction (HRI) systems often rely on simplistic, silence-based models, leading to unnatural pauses and interruptions. This paper investigates, for the first time, the application of general turn-taking models, specifically TurnGPT and Voice Activity Projection (VAP), to improve conversational dynamics in HRI. These models are trained on human-human dialogue data using self-supervised learning objectives, without requiring domain-specific fine-tuning. We propose methods for using these models in tandem to predict wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08946","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/2501.08946/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":"2501.08946","created_at":"2026-07-05T10:01:28.284099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08946v1","created_at":"2026-07-05T10:01:28.284099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08946","created_at":"2026-07-05T10:01:28.284099+00:00"},{"alias_kind":"pith_short_12","alias_value":"7S4Z7POEOLOB","created_at":"2026-07-05T10:01:28.284099+00:00"},{"alias_kind":"pith_short_16","alias_value":"7S4Z7POEOLOB5GST","created_at":"2026-07-05T10:01:28.284099+00:00"},{"alias_kind":"pith_short_8","alias_value":"7S4Z7POE","created_at":"2026-07-05T10:01:28.284099+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/7S4Z7POEOLOB5GSTNPDCWGSBC4","json":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4.json","graph_json":"https://pith.science/api/pith-number/7S4Z7POEOLOB5GSTNPDCWGSBC4/graph.json","events_json":"https://pith.science/api/pith-number/7S4Z7POEOLOB5GSTNPDCWGSBC4/events.json","paper":"https://pith.science/paper/7S4Z7POE"},"agent_actions":{"view_html":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4","download_json":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4.json","view_paper":"https://pith.science/paper/7S4Z7POE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08946&json=true","fetch_graph":"https://pith.science/api/pith-number/7S4Z7POEOLOB5GSTNPDCWGSBC4/graph.json","fetch_events":"https://pith.science/api/pith-number/7S4Z7POEOLOB5GSTNPDCWGSBC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4/action/storage_attestation","attest_author":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4/action/author_attestation","sign_citation":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4/action/citation_signature","submit_replication":"https://pith.science/pith/7S4Z7POEOLOB5GSTNPDCWGSBC4/action/replication_record"}},"created_at":"2026-07-05T10:01:28.284099+00:00","updated_at":"2026-07-05T10:01:28.284099+00:00"}