{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GVJSP2AW2CTFXFSYM2JC54LWOU","short_pith_number":"pith:GVJSP2AW","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"},"canonical_sha256":"355327e816d0a65b965866922ef1767517b83e5ec73ceebdebae581cbd020679","source":{"kind":"arxiv","id":"2606.16731","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GVJSP2AW2CTFXFSYM2JC54LWOU","target":"record","payload":{"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"},"canonical_sha256":"355327e816d0a65b965866922ef1767517b83e5ec73ceebdebae581cbd020679","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"},"source_kind":"arxiv","source_id":"2606.16731","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"prVFPifuPlwfz2qatszWkYqGNm6fz5jB/lP76aL3Rf8xgbC6fxIcErgSfL6kmGkTS8LL2edldyoEZ+wRjLAiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:52:03.710665Z"},"content_sha256":"d4399eb9c4653f6dc991a0448628ffbd2ea1bb658728b9ddfbbef16f538e5cf5","schema_version":"1.0","event_id":"sha256:d4399eb9c4653f6dc991a0448628ffbd2ea1bb658728b9ddfbbef16f538e5cf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GVJSP2AW2CTFXFSYM2JC54LWOU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ARNOS/K6ujxeYMoZq652+iD8Y5hKng0MqO+8glG+ZDdNo7kV3eVKzDehNVZoHcCz/G+eMZiySiUhd669NcWiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:52:03.711245Z"},"content_sha256":"6b673108d3650c305eb915964ee9ffdc6884522af642541db2600e3483a9acf2","schema_version":"1.0","event_id":"sha256:6b673108d3650c305eb915964ee9ffdc6884522af642541db2600e3483a9acf2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/bundle.json","state_url":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T20:52:03Z","links":{"resolver":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU","bundle":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/bundle.json","state":"https://pith.science/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVJSP2AW2CTFXFSYM2JC54LWOU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiN15tISOzPDG10GhntHImUkX5nZuz+0lcT4hMz2jM9XeK+GhJNIdnKE7XP1YDp36mGIcmd/Mbv8/yw0+zJECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:52:03.715144Z","bundle_sha256":"977faabda0d252e5f65e57d9d2eaf5d4b38e70fa018ea630a5af3721db495af1"}}