{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EXI47KYLOJ6RZU4FJGQKXRVE6O","short_pith_number":"pith:EXI47KYL","canonical_record":{"source":{"id":"2403.06487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T07:50:29Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a2ea91fb56ebaa5ea079d607f6f3d5d76a42b8416efda3791d28c56e6af104a4","abstract_canon_sha256":"08a2e9aea97053f36206fd8329b1892bfc3cbffca75f7e4e46707a4a7033e3d4"},"schema_version":"1.0"},"canonical_sha256":"25d1cfab0b727d1cd38549a0abc6a4f3a0ac9238c072a8abd9de393060225a5f","source":{"kind":"arxiv","id":"2403.06487","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EXI47KYLOJ6RZU4FJGQKXRVE6O","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T07:50:29Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a2ea91fb56ebaa5ea079d607f6f3d5d76a42b8416efda3791d28c56e6af104a4","abstract_canon_sha256":"08a2e9aea97053f36206fd8329b1892bfc3cbffca75f7e4e46707a4a7033e3d4"},"schema_version":"1.0"},"canonical_sha256":"25d1cfab0b727d1cd38549a0abc6a4f3a0ac9238c072a8abd9de393060225a5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:22.039863Z","signature_b64":"mvjB59eu0tdHTuefAWxDr/MZzyYWNgh4c4rG730VMC05ziMaV6h8+M+ybOl11gG1uR2+aFacQRIbah+AKkkCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d1cfab0b727d1cd38549a0abc6a4f3a0ac9238c072a8abd9de393060225a5f","last_reissued_at":"2026-07-05T07:56:22.039383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:22.039383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06487","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g+ws+rS0Nf96WYhpkP/1sXKB9y5IACoUcwQkxkQ+/VX1yH//HyWFl39X6R1XMMKu0aILhDlAMF7WtUmL/P0HCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:14:24.736399Z"},"content_sha256":"d5854cbffb70a199365e36526d16502e3ac01d2f331a0a1f9428aab6b78b7228","schema_version":"1.0","event_id":"sha256:d5854cbffb70a199365e36526d16502e3ac01d2f331a0a1f9428aab6b78b7228"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EXI47KYLOJ6RZU4FJGQKXRVE6O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Turn-taking Prediction Using Voice Activity Projection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bing'er Jiang, Erik Ekstedt, Gabriel Skantze, Koji Inoue, Tatsuya Kawahara","submitted_at":"2024-03-11T07:50:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06487","kind":"arxiv","version":3},"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/2403.06487/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":"2026-07-05T07:56:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CkCdi9RoZpTEsB1RuXsIVisjkaEWgkBJb1VIUn1cTnpSZyXdV6FnWWQwXCUUctZ5HhT9NGvy32lsHRnSB8lEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:14:24.736896Z"},"content_sha256":"63e7c3ed7682ad3b90b5267c63fb41bde3510cff2ced2163cba52968192f2f83","schema_version":"1.0","event_id":"sha256:63e7c3ed7682ad3b90b5267c63fb41bde3510cff2ced2163cba52968192f2f83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O/bundle.json","state_url":"https://pith.science/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O/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":"2026-08-05T04:14:24Z","links":{"resolver":"https://pith.science/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O","bundle":"https://pith.science/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O/bundle.json","state":"https://pith.science/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXI47KYLOJ6RZU4FJGQKXRVE6O/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0ozQwlk2xcD5KAkhnDoF99b+VjuwCCWUHxfOFeX72sAzE2l+qHISBHi766mFT3BV8wgKJsnUr2EixFCMloFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:14:24.740391Z","bundle_sha256":"f15c641ebac931cc97bae58b3f7f26e304c405e57e6285ca1cfb413b07ce6b24"}}