{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GVJSP2AW2CTFXFSYM2JC54LWOU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"31c607640308e26500c50e774fbfbe482eb7bb41de101a6b8a74eb22cf27be18","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T13:54:44Z","title_canon_sha256":"3337f476d60875deb3456f9216c192f17469c03da532ad2c69e3cc21ba41ec99"},"schema_version":"1.0","source":{"id":"2606.16731","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16731","created_at":"2026-06-23T01:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16731v2","created_at":"2026-06-23T01:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16731","created_at":"2026-06-23T01:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"GVJSP2AW2CTF","created_at":"2026-06-23T01:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"GVJSP2AW2CTFXFSY","created_at":"2026-06-23T01:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"GVJSP2AW","created_at":"2026-06-23T01:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:6b673108d3650c305eb915964ee9ffdc6884522af642541db2600e3483a9acf2","target":"graph","created_at":"2026-06-23T01:12:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.16731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gabriel Skantze, Haotian Qi","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T13:54:44Z","title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16731","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d4399eb9c4653f6dc991a0448628ffbd2ea1bb658728b9ddfbbef16f538e5cf5","target":"record","created_at":"2026-06-23T01:12:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"31c607640308e26500c50e774fbfbe482eb7bb41de101a6b8a74eb22cf27be18","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T13:54:44Z","title_canon_sha256":"3337f476d60875deb3456f9216c192f17469c03da532ad2c69e3cc21ba41ec99"},"schema_version":"1.0","source":{"id":"2606.16731","kind":"arxiv","version":2}},"canonical_sha256":"355327e816d0a65b965866922ef1767517b83e5ec73ceebdebae581cbd020679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"355327e816d0a65b965866922ef1767517b83e5ec73ceebdebae581cbd020679","first_computed_at":"2026-06-23T01:12:10.024834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:10.024834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DDQS3weIJabwtfEXBiS5S20RZncnCYtnzJ0q/yQTtPxML8eIic/PbOrOuS2+iL/dlEwQmKnQjDm5nhnktqq8BA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:10.025427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.16731","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4399eb9c4653f6dc991a0448628ffbd2ea1bb658728b9ddfbbef16f538e5cf5","sha256:6b673108d3650c305eb915964ee9ffdc6884522af642541db2600e3483a9acf2"],"state_sha256":"b60e6ac91a0a146dbbcf2601d57d36dee01ba7b021ab97ce00914894fe776eee"}