{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EXI47KYLOJ6RZU4FJGQKXRVE6O","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":"08a2e9aea97053f36206fd8329b1892bfc3cbffca75f7e4e46707a4a7033e3d4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T07:50:29Z","title_canon_sha256":"a2ea91fb56ebaa5ea079d607f6f3d5d76a42b8416efda3791d28c56e6af104a4"},"schema_version":"1.0","source":{"id":"2403.06487","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06487","created_at":"2026-07-05T07:56:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06487v3","created_at":"2026-07-05T07:56:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06487","created_at":"2026-07-05T07:56:22Z"},{"alias_kind":"pith_short_12","alias_value":"EXI47KYLOJ6R","created_at":"2026-07-05T07:56:22Z"},{"alias_kind":"pith_short_16","alias_value":"EXI47KYLOJ6RZU4F","created_at":"2026-07-05T07:56:22Z"},{"alias_kind":"pith_short_8","alias_value":"EXI47KYL","created_at":"2026-07-05T07:56:22Z"}],"graph_snapshots":[{"event_id":"sha256:63e7c3ed7682ad3b90b5267c63fb41bde3510cff2ced2163cba52968192f2f83","target":"graph","created_at":"2026-07-05T07:56:22Z","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/2403.06487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the application of voice activity projection (VAP), a predictive turn-taking model for spoken dialogue, on multilingual data, encompassing English, Mandarin, and Japanese. The VAP model continuously predicts the upcoming voice activities of participants in dyadic dialogue, leveraging a cross-attention Transformer to capture the dynamic interplay between participants. The results show that a monolingual VAP model trained on one language does not make good predictions when applied to other languages. However, a multilingual model, trained on all three languages, demonstra","authors_text":"Bing'er Jiang, Erik Ekstedt, Gabriel Skantze, Koji Inoue, Tatsuya Kawahara","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T07:50:29Z","title":"Multilingual Turn-taking Prediction Using Voice Activity Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06487","kind":"arxiv","version":3},"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:d5854cbffb70a199365e36526d16502e3ac01d2f331a0a1f9428aab6b78b7228","target":"record","created_at":"2026-07-05T07:56:22Z","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":"08a2e9aea97053f36206fd8329b1892bfc3cbffca75f7e4e46707a4a7033e3d4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T07:50:29Z","title_canon_sha256":"a2ea91fb56ebaa5ea079d607f6f3d5d76a42b8416efda3791d28c56e6af104a4"},"schema_version":"1.0","source":{"id":"2403.06487","kind":"arxiv","version":3}},"canonical_sha256":"25d1cfab0b727d1cd38549a0abc6a4f3a0ac9238c072a8abd9de393060225a5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25d1cfab0b727d1cd38549a0abc6a4f3a0ac9238c072a8abd9de393060225a5f","first_computed_at":"2026-07-05T07:56:22.039383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:22.039383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mvjB59eu0tdHTuefAWxDr/MZzyYWNgh4c4rG730VMC05ziMaV6h8+M+ybOl11gG1uR2+aFacQRIbah+AKkkCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:22.039863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06487","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5854cbffb70a199365e36526d16502e3ac01d2f331a0a1f9428aab6b78b7228","sha256:63e7c3ed7682ad3b90b5267c63fb41bde3510cff2ced2163cba52968192f2f83"],"state_sha256":"5e789954f3936bb7b249a625e00b29b912384dfe390f8c8f7c2f4b31704d545a"}