{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GWL33VA56YELFK73XCUSHV6FEM","short_pith_number":"pith:GWL33VA5","canonical_record":{"source":{"id":"2308.16021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-30T13:21:51Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e39213d95f1cd33b5f5344385f103f91cdc4d54593e1f49a8ad66ce4c7089647","abstract_canon_sha256":"575845b8853093ca89593362d8b7cef17ffbf477ed2346aa44005fad2cb12535"},"schema_version":"1.0"},"canonical_sha256":"3597bdd41df608b2abfbb8a923d7c52323e6f253a409f253bb20b31d57fb4474","source":{"kind":"arxiv","id":"2308.16021","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16021","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16021v1","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16021","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"GWL33VA56YEL","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"pith_short_16","alias_value":"GWL33VA56YELFK73","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"pith_short_8","alias_value":"GWL33VA5","created_at":"2026-07-05T06:46:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GWL33VA56YELFK73XCUSHV6FEM","target":"record","payload":{"canonical_record":{"source":{"id":"2308.16021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-30T13:21:51Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e39213d95f1cd33b5f5344385f103f91cdc4d54593e1f49a8ad66ce4c7089647","abstract_canon_sha256":"575845b8853093ca89593362d8b7cef17ffbf477ed2346aa44005fad2cb12535"},"schema_version":"1.0"},"canonical_sha256":"3597bdd41df608b2abfbb8a923d7c52323e6f253a409f253bb20b31d57fb4474","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:17.327501Z","signature_b64":"n9zn5eUOjmKyz5TuVW0ZJQKinssVSIVoT8Kyg8oFeNJTnrL8Dqdaqgd56pAYbarda97ro94rVWEI6iRJsG/uCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3597bdd41df608b2abfbb8a923d7c52323e6f253a409f253bb20b31d57fb4474","last_reissued_at":"2026-07-05T06:46:17.327028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:17.327028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.16021","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":"2026-07-05T06:46:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6MoW8wDH2NjXWiTDVO08EAer5nNGO7BfBE/PuaGUJghNxu3a/oOTke0Gadq3huM5irz+tzxPmh3tmAPUlwAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:12.294305Z"},"content_sha256":"02eeffc712bcac73a3a23b93e549bcecf0a5b948ab63b60e314f6f052263155f","schema_version":"1.0","event_id":"sha256:02eeffc712bcac73a3a23b93e549bcecf0a5b948ab63b60e314f6f052263155f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GWL33VA56YELFK73XCUSHV6FEM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CALM: Contrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chi Sun, Helen Meng, Hui Zhan, Tingtian Li, Xiang Li, Xinyu Xiao, Yi Meng, Zhiyong Wu, Zixun Sun","submitted_at":"2023-08-30T13:21:51Z","abstract_excerpt":"To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are obtained by manual selection which is resource-consuming, or selected by semantic features. However, semantic features contain not only style-related information, but also style irrelevant information. The information irrelevant to speaking style in the text could interfere the reference audio selection and result in improper speaking styles. To improve the referen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16021","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/2308.16021/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":"2026-07-05T06:46:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uNpoKBtELyz1qFeLsTNcsw3zE+TiADDYSq3v98blu8u73A4fzxOQUm/k2B/561wLD78O5Thvbh5vbQ3lgRXlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:12.306903Z"},"content_sha256":"4a702a388984e65b16a7e9509cae50b87e00d5b52b6fc3d6e77dbff26aab9459","schema_version":"1.0","event_id":"sha256:4a702a388984e65b16a7e9509cae50b87e00d5b52b6fc3d6e77dbff26aab9459"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWL33VA56YELFK73XCUSHV6FEM/bundle.json","state_url":"https://pith.science/pith/GWL33VA56YELFK73XCUSHV6FEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWL33VA56YELFK73XCUSHV6FEM/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":"2026-08-09T05:16:12Z","links":{"resolver":"https://pith.science/pith/GWL33VA56YELFK73XCUSHV6FEM","bundle":"https://pith.science/pith/GWL33VA56YELFK73XCUSHV6FEM/bundle.json","state":"https://pith.science/pith/GWL33VA56YELFK73XCUSHV6FEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWL33VA56YELFK73XCUSHV6FEM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GWL33VA56YELFK73XCUSHV6FEM","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":"575845b8853093ca89593362d8b7cef17ffbf477ed2346aa44005fad2cb12535","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-30T13:21:51Z","title_canon_sha256":"e39213d95f1cd33b5f5344385f103f91cdc4d54593e1f49a8ad66ce4c7089647"},"schema_version":"1.0","source":{"id":"2308.16021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16021","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16021v1","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16021","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"GWL33VA56YEL","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"pith_short_16","alias_value":"GWL33VA56YELFK73","created_at":"2026-07-05T06:46:17Z"},{"alias_kind":"pith_short_8","alias_value":"GWL33VA5","created_at":"2026-07-05T06:46:17Z"}],"graph_snapshots":[{"event_id":"sha256:4a702a388984e65b16a7e9509cae50b87e00d5b52b6fc3d6e77dbff26aab9459","target":"graph","created_at":"2026-07-05T06:46:17Z","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/2308.16021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are obtained by manual selection which is resource-consuming, or selected by semantic features. However, semantic features contain not only style-related information, but also style irrelevant information. The information irrelevant to speaking style in the text could interfere the reference audio selection and result in improper speaking styles. To improve the referen","authors_text":"Chi Sun, Helen Meng, Hui Zhan, Tingtian Li, Xiang Li, Xinyu Xiao, Yi Meng, Zhiyong Wu, Zixun Sun","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-30T13:21:51Z","title":"CALM: Contrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16021","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":"sha256:02eeffc712bcac73a3a23b93e549bcecf0a5b948ab63b60e314f6f052263155f","target":"record","created_at":"2026-07-05T06:46:17Z","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":"575845b8853093ca89593362d8b7cef17ffbf477ed2346aa44005fad2cb12535","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-30T13:21:51Z","title_canon_sha256":"e39213d95f1cd33b5f5344385f103f91cdc4d54593e1f49a8ad66ce4c7089647"},"schema_version":"1.0","source":{"id":"2308.16021","kind":"arxiv","version":1}},"canonical_sha256":"3597bdd41df608b2abfbb8a923d7c52323e6f253a409f253bb20b31d57fb4474","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3597bdd41df608b2abfbb8a923d7c52323e6f253a409f253bb20b31d57fb4474","first_computed_at":"2026-07-05T06:46:17.327028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:17.327028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n9zn5eUOjmKyz5TuVW0ZJQKinssVSIVoT8Kyg8oFeNJTnrL8Dqdaqgd56pAYbarda97ro94rVWEI6iRJsG/uCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:17.327501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02eeffc712bcac73a3a23b93e549bcecf0a5b948ab63b60e314f6f052263155f","sha256:4a702a388984e65b16a7e9509cae50b87e00d5b52b6fc3d6e77dbff26aab9459"],"state_sha256":"7eacf2409efce86eab1385ba1aed7184fcc1f4d3439b85d0b974205598dc028a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BTHcbq/HyVxtSSaE+NgZ4/ktSRQ+23HrNPQGVyFBH0AqWBcS8rL9opVfuSZ4BGIMsKbBttJYDMhrnZVhlQuvDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:16:12.315230Z","bundle_sha256":"599be661cd3d30e8b20135518fa6b75eb0a59c879f4afad49917185c708f4a3c"}}