{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ODCFYRSAI6HK2BJ7ESJA4CL3BR","short_pith_number":"pith:ODCFYRSA","schema_version":"1.0","canonical_sha256":"70c45c4640478ead053f24920e097b0c7590e5f17defebab4e8bbce376f8e1a5","source":{"kind":"arxiv","id":"2506.03980","version":1},"attestation_state":"computed","paper":{"title":"Voice Activity Projection Model with Multimodal Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Pelachaud, Takeshi Saga","submitted_at":"2025-06-04T14:10:03Z","abstract_excerpt":"Turn-taking management is crucial for any social interaction. Still, it is challenging to model human-machine interaction due to the complexity of the social context and its multimodal nature. Unlike conventional systems based on silence duration, previous existing voice activity projection (VAP) models successfully utilized a unified representation of turn-taking behaviors as prediction targets, which improved turn-taking prediction performance. Recently, a multimodal VAP model outperformed the previous state-of-the-art model by a significant margin. In this paper, we propose a multimodal mod"},"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":"2506.03980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"c062715f5b008976c08a00e6b4d3f2d29559255b8d709e22fe3b405422707f40","abstract_canon_sha256":"0b0222ef4058e15068f6960d3e2dd6bef637f7220216516338b0cf18e96ff1a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:54.847611Z","signature_b64":"p2J/IJkD/5QEBlPaEI0xhtOrTQvOL7WXP4FLD+tD/E67dctMlCY0SlsvBv7aB/N2/djEQNvrZMU+/+trodVYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c45c4640478ead053f24920e097b0c7590e5f17defebab4e8bbce376f8e1a5","last_reissued_at":"2026-07-05T11:15:54.847044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:54.847044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voice Activity Projection Model with Multimodal Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Catherine Pelachaud, Takeshi Saga","submitted_at":"2025-06-04T14:10:03Z","abstract_excerpt":"Turn-taking management is crucial for any social interaction. Still, it is challenging to model human-machine interaction due to the complexity of the social context and its multimodal nature. Unlike conventional systems based on silence duration, previous existing voice activity projection (VAP) models successfully utilized a unified representation of turn-taking behaviors as prediction targets, which improved turn-taking prediction performance. Recently, a multimodal VAP model outperformed the previous state-of-the-art model by a significant margin. In this paper, we propose a multimodal mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03980","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/2506.03980/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":"2506.03980","created_at":"2026-07-05T11:15:54.847089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03980v1","created_at":"2026-07-05T11:15:54.847089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03980","created_at":"2026-07-05T11:15:54.847089+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODCFYRSAI6HK","created_at":"2026-07-05T11:15:54.847089+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODCFYRSAI6HK2BJ7","created_at":"2026-07-05T11:15:54.847089+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODCFYRSA","created_at":"2026-07-05T11:15:54.847089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07294","citing_title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR","json":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR.json","graph_json":"https://pith.science/api/pith-number/ODCFYRSAI6HK2BJ7ESJA4CL3BR/graph.json","events_json":"https://pith.science/api/pith-number/ODCFYRSAI6HK2BJ7ESJA4CL3BR/events.json","paper":"https://pith.science/paper/ODCFYRSA"},"agent_actions":{"view_html":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR","download_json":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR.json","view_paper":"https://pith.science/paper/ODCFYRSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03980&json=true","fetch_graph":"https://pith.science/api/pith-number/ODCFYRSAI6HK2BJ7ESJA4CL3BR/graph.json","fetch_events":"https://pith.science/api/pith-number/ODCFYRSAI6HK2BJ7ESJA4CL3BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR/action/storage_attestation","attest_author":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR/action/author_attestation","sign_citation":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR/action/citation_signature","submit_replication":"https://pith.science/pith/ODCFYRSAI6HK2BJ7ESJA4CL3BR/action/replication_record"}},"created_at":"2026-07-05T11:15:54.847089+00:00","updated_at":"2026-07-05T11:15:54.847089+00:00"}