{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GVJSP2AW2CTFXFSYM2JC54LWOU","short_pith_number":"pith:GVJSP2AW","schema_version":"1.0","canonical_sha256":"355327e816d0a65b965866922ef1767517b83e5ec73ceebdebae581cbd020679","source":{"kind":"arxiv","id":"2606.16731","version":2},"attestation_state":"computed","paper":{"title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.SD","authors_text":"Gabriel Skantze, Haotian Qi","submitted_at":"2026-06-15T13:54:44Z","abstract_excerpt":"Current multiparty turn-taking models often rely on complex microphone arrays or multi-camera setups, limiting their applicability in human-robot interaction scenarios. We introduce MuVAP, a causal multimodal framework that extends Voice Activity Projection by grounding acoustic predictions in face tracks, enabling speaker-aware turn-taking predictions from a monaural audio stream and a single camera view. To address the combinatorial complexity of modeling multiple speakers, we propose Role-Relative Projection, which maps any N-speaker interaction onto a fixed current versus next floor-holder"},"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":"2606.16731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T13:54:44Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"3337f476d60875deb3456f9216c192f17469c03da532ad2c69e3cc21ba41ec99","abstract_canon_sha256":"31c607640308e26500c50e774fbfbe482eb7bb41de101a6b8a74eb22cf27be18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:10.025427Z","signature_b64":"DDQS3weIJabwtfEXBiS5S20RZncnCYtnzJ0q/yQTtPxML8eIic/PbOrOuS2+iL/dlEwQmKnQjDm5nhnktqq8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355327e816d0a65b965866922ef1767517b83e5ec73ceebdebae581cbd020679","last_reissued_at":"2026-06-23T01:12:10.024834Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:10.024834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.SD","authors_text":"Gabriel Skantze, Haotian Qi","submitted_at":"2026-06-15T13:54:44Z","abstract_excerpt":"Current multiparty turn-taking models often rely on complex microphone arrays or multi-camera setups, limiting their applicability in human-robot interaction scenarios. We introduce MuVAP, a causal multimodal framework that extends Voice Activity Projection by grounding acoustic predictions in face tracks, enabling speaker-aware turn-taking predictions from a monaural audio stream and a single camera view. To address the combinatorial complexity of modeling multiple speakers, we propose Role-Relative Projection, which maps any N-speaker interaction onto a fixed current versus next floor-holder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16731","kind":"arxiv","version":2},"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/2606.16731/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":"2606.16731","created_at":"2026-06-23T01:12:10.024910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.16731v2","created_at":"2026-06-23T01:12:10.024910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16731","created_at":"2026-06-23T01:12:10.024910+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVJSP2AW2CTF","created_at":"2026-06-23T01:12:10.024910+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVJSP2AW2CTFXFSY","created_at":"2026-06-23T01:12:10.024910+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVJSP2AW","created_at":"2026-06-23T01:12:10.024910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.16731","citing_title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU","json":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU.json","graph_json":"https://pith.science/api/pith-number/GVJSP2AW2CTFXFSYM2JC54LWOU/graph.json","events_json":"https://pith.science/api/pith-number/GVJSP2AW2CTFXFSYM2JC54LWOU/events.json","paper":"https://pith.science/paper/GVJSP2AW"},"agent_actions":{"view_html":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU","download_json":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU.json","view_paper":"https://pith.science/paper/GVJSP2AW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.16731&json=true","fetch_graph":"https://pith.science/api/pith-number/GVJSP2AW2CTFXFSYM2JC54LWOU/graph.json","fetch_events":"https://pith.science/api/pith-number/GVJSP2AW2CTFXFSYM2JC54LWOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/action/storage_attestation","attest_author":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/action/author_attestation","sign_citation":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/action/citation_signature","submit_replication":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/action/replication_record"}},"created_at":"2026-06-23T01:12:10.024910+00:00","updated_at":"2026-06-23T01:12:10.024910+00:00"}