{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6VTXM2G2P2WBG7G2Q4YUOEBXG4","short_pith_number":"pith:6VTXM2G2","canonical_record":{"source":{"id":"2412.18733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T01:35:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8b5f0ae5c5bccaddbe06ceb77e88ea36c110c5f15510856b2e289983d1d80e5a","abstract_canon_sha256":"c338f357296667c55fd1816bd22ca6b04a590fb41ed490242903946698c05027"},"schema_version":"1.0"},"canonical_sha256":"f5677668da7eac137cda873147103737187838ec03710d642c0c205c66cb1169","source":{"kind":"arxiv","id":"2412.18733","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18733","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18733v1","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18733","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"pith_short_12","alias_value":"6VTXM2G2P2WB","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"pith_short_16","alias_value":"6VTXM2G2P2WBG7G2","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"pith_short_8","alias_value":"6VTXM2G2","created_at":"2026-07-05T09:54:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6VTXM2G2P2WBG7G2Q4YUOEBXG4","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T01:35:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8b5f0ae5c5bccaddbe06ceb77e88ea36c110c5f15510856b2e289983d1d80e5a","abstract_canon_sha256":"c338f357296667c55fd1816bd22ca6b04a590fb41ed490242903946698c05027"},"schema_version":"1.0"},"canonical_sha256":"f5677668da7eac137cda873147103737187838ec03710d642c0c205c66cb1169","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:09.856955Z","signature_b64":"fJwzP+ONioZ5/JXaYQgZgx2ZVKyqtXK80GvaaQGigeZi5GpJMbElXgDk3WmN+A873im5kFMrVEcqMnv84UgmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5677668da7eac137cda873147103737187838ec03710d642c0c205c66cb1169","last_reissued_at":"2026-07-05T09:54:09.856566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:09.856566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18733","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q25V3oEIE/UPJ0jW7gQqfoYeqSk1rlBvg5McFrNWB3nvAEO7x108Apgbqp1M+CLfqrbLH7OPREdcdgltUuIfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:42:10.521193Z"},"content_sha256":"fec1a34ab0041a66eb592a21b84264ec277551f9762fc63ce0689b72259555ff","schema_version":"1.0","event_id":"sha256:fec1a34ab0041a66eb592a21b84264ec277551f9762fc63ce0689b72259555ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6VTXM2G2P2WBG7G2Q4YUOEBXG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Intra- and Inter-modal Context Interaction Modeling for Conversational Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Rui Liu, Zhenqi Jia","submitted_at":"2024-12-25T01:35:59Z","abstract_excerpt":"Conversational Speech Synthesis (CSS) aims to effectively take the multimodal dialogue history (MDH) to generate speech with appropriate conversational prosody for target utterance. The key challenge of CSS is to model the interaction between the MDH and the target utterance. Note that text and speech modalities in MDH have their own unique influences, and they complement each other to produce a comprehensive impact on the target utterance. Previous works did not explicitly model such intra-modal and inter-modal interactions. To address this issue, we propose a new intra-modal and inter-modal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18733","kind":"arxiv","version":1},"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/2412.18733/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":"2026-07-05T09:54:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9EsAkF0BUCR7FC0yHyw1hJkvIRDK9R95x1kVnsNGB5EDSLgx6p9hO1kaCF5PHIMZIGw8sHHmaRozho+t5bSNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:42:10.521713Z"},"content_sha256":"2646ce4bcd47ca02cd4a81c7194bb82fa58292319f9673df9c0ba7fef56e7a63","schema_version":"1.0","event_id":"sha256:2646ce4bcd47ca02cd4a81c7194bb82fa58292319f9673df9c0ba7fef56e7a63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4/bundle.json","state_url":"https://pith.science/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4/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":"2026-08-05T15:42:10Z","links":{"resolver":"https://pith.science/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4","bundle":"https://pith.science/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4/bundle.json","state":"https://pith.science/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6VTXM2G2P2WBG7G2Q4YUOEBXG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6VTXM2G2P2WBG7G2Q4YUOEBXG4","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":"c338f357296667c55fd1816bd22ca6b04a590fb41ed490242903946698c05027","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T01:35:59Z","title_canon_sha256":"8b5f0ae5c5bccaddbe06ceb77e88ea36c110c5f15510856b2e289983d1d80e5a"},"schema_version":"1.0","source":{"id":"2412.18733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18733","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18733v1","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18733","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"pith_short_12","alias_value":"6VTXM2G2P2WB","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"pith_short_16","alias_value":"6VTXM2G2P2WBG7G2","created_at":"2026-07-05T09:54:09Z"},{"alias_kind":"pith_short_8","alias_value":"6VTXM2G2","created_at":"2026-07-05T09:54:09Z"}],"graph_snapshots":[{"event_id":"sha256:2646ce4bcd47ca02cd4a81c7194bb82fa58292319f9673df9c0ba7fef56e7a63","target":"graph","created_at":"2026-07-05T09:54:09Z","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/2412.18733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversational Speech Synthesis (CSS) aims to effectively take the multimodal dialogue history (MDH) to generate speech with appropriate conversational prosody for target utterance. The key challenge of CSS is to model the interaction between the MDH and the target utterance. Note that text and speech modalities in MDH have their own unique influences, and they complement each other to produce a comprehensive impact on the target utterance. Previous works did not explicitly model such intra-modal and inter-modal interactions. To address this issue, we propose a new intra-modal and inter-modal ","authors_text":"Rui Liu, Zhenqi Jia","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T01:35:59Z","title":"Intra- and Inter-modal Context Interaction Modeling for Conversational Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18733","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:fec1a34ab0041a66eb592a21b84264ec277551f9762fc63ce0689b72259555ff","target":"record","created_at":"2026-07-05T09:54:09Z","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":"c338f357296667c55fd1816bd22ca6b04a590fb41ed490242903946698c05027","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T01:35:59Z","title_canon_sha256":"8b5f0ae5c5bccaddbe06ceb77e88ea36c110c5f15510856b2e289983d1d80e5a"},"schema_version":"1.0","source":{"id":"2412.18733","kind":"arxiv","version":1}},"canonical_sha256":"f5677668da7eac137cda873147103737187838ec03710d642c0c205c66cb1169","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5677668da7eac137cda873147103737187838ec03710d642c0c205c66cb1169","first_computed_at":"2026-07-05T09:54:09.856566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:09.856566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJwzP+ONioZ5/JXaYQgZgx2ZVKyqtXK80GvaaQGigeZi5GpJMbElXgDk3WmN+A873im5kFMrVEcqMnv84UgmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:09.856955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fec1a34ab0041a66eb592a21b84264ec277551f9762fc63ce0689b72259555ff","sha256:2646ce4bcd47ca02cd4a81c7194bb82fa58292319f9673df9c0ba7fef56e7a63"],"state_sha256":"06ab13ec430aead3cb1fe083025edc0a2cf255915839141a4cd5068d609cb1db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ig/jGDdkMowha/K5XlZqPX6hLRK9oezcSnXmtAb1kbA41xxeGSPuqnHsLpeEePzHXm/VNbk27fSjZJ5exThOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:42:10.526054Z","bundle_sha256":"b0af21e91186cf81925d3f1e7a05bbfcd0ee369bc8fdeba54a247c031559c7c0"}}