{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ODCFYRSAI6HK2BJ7ESJA4CL3BR","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":"0b0222ef4058e15068f6960d3e2dd6bef637f7220216516338b0cf18e96ff1a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:10:03Z","title_canon_sha256":"c062715f5b008976c08a00e6b4d3f2d29559255b8d709e22fe3b405422707f40"},"schema_version":"1.0","source":{"id":"2506.03980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03980","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03980v1","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03980","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"ODCFYRSAI6HK","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"ODCFYRSAI6HK2BJ7","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"ODCFYRSA","created_at":"2026-07-05T11:15:54Z"}],"graph_snapshots":[{"event_id":"sha256:35a217a4dada8f29a632d3fbf124a0ca648b58ba209ed6b122f275ab62ddf8b7","target":"graph","created_at":"2026-07-05T11:15:54Z","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/2506.03980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Catherine Pelachaud, Takeshi Saga","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:10:03Z","title":"Voice Activity Projection Model with Multimodal Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03980","kind":"arxiv","version":1},"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":"sha256:344390411d3690225086fd7f0cb83b27fb998e097445fdada322ef36c829793b","target":"record","created_at":"2026-07-05T11:15:54Z","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":"0b0222ef4058e15068f6960d3e2dd6bef637f7220216516338b0cf18e96ff1a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:10:03Z","title_canon_sha256":"c062715f5b008976c08a00e6b4d3f2d29559255b8d709e22fe3b405422707f40"},"schema_version":"1.0","source":{"id":"2506.03980","kind":"arxiv","version":1}},"canonical_sha256":"70c45c4640478ead053f24920e097b0c7590e5f17defebab4e8bbce376f8e1a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70c45c4640478ead053f24920e097b0c7590e5f17defebab4e8bbce376f8e1a5","first_computed_at":"2026-07-05T11:15:54.847044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:54.847044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p2J/IJkD/5QEBlPaEI0xhtOrTQvOL7WXP4FLD+tD/E67dctMlCY0SlsvBv7aB/N2/djEQNvrZMU+/+trodVYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:54.847611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:344390411d3690225086fd7f0cb83b27fb998e097445fdada322ef36c829793b","sha256:35a217a4dada8f29a632d3fbf124a0ca648b58ba209ed6b122f275ab62ddf8b7"],"state_sha256":"47b37906864e38bf05522644efbbfaa487734fd6bbe56bc06ff1cfddb50ea5ba"}