{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:D2XPL5DN2IBXTC4JFPXXPNNOPH","short_pith_number":"pith:D2XPL5DN","canonical_record":{"source":{"id":"1808.01410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-04T02:21:07Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"f9180cde054826da0f7d6ad554af2a710ec2fc96b71a0afb82b2d38b5ace0584","abstract_canon_sha256":"49f9bbe9102e0fa4ebabb2cfd266f0cb77aefa2ee43d2eb8f35f0a93d4cbab88"},"schema_version":"1.0"},"canonical_sha256":"1eaef5f46dd203798b892bef77b5ae79c963a29ca8d53000abe22759359ef489","source":{"kind":"arxiv","id":"1808.01410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.01410","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"1808.01410v1","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01410","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"D2XPL5DN2IBX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D2XPL5DN2IBXTC4J","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D2XPL5DN","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:D2XPL5DN2IBXTC4JFPXXPNNOPH","target":"record","payload":{"canonical_record":{"source":{"id":"1808.01410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-04T02:21:07Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"f9180cde054826da0f7d6ad554af2a710ec2fc96b71a0afb82b2d38b5ace0584","abstract_canon_sha256":"49f9bbe9102e0fa4ebabb2cfd266f0cb77aefa2ee43d2eb8f35f0a93d4cbab88"},"schema_version":"1.0"},"canonical_sha256":"1eaef5f46dd203798b892bef77b5ae79c963a29ca8d53000abe22759359ef489","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:53.090213Z","signature_b64":"LDPSpaKkZFKZr5K85zbWldpqrXEfIRPXb7O90VP2N0cWbk5uoVlFDhHyuudCxomMRZqt4i/NZGR0ImDWm2c8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eaef5f46dd203798b892bef77b5ae79c963a29ca8d53000abe22759359ef489","last_reissued_at":"2026-05-18T00:08:53.089496Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:53.089496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.01410","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":"2026-05-18T00:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GG3T4aEKmRh8KImD4mlZCN/npM5yAarS7d8w8tw/c3qIVn7cxERA6FsOSZTw5xRRh1eGvckalzG8DhHCeKMTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:09:04.811330Z"},"content_sha256":"dbaea4d665310a1c3fe393a16f3ef2b14279d13bbebb81f35490bbddb9635376","schema_version":"1.0","event_id":"sha256:dbaea4d665310a1c3fe393a16f3ef2b14279d13bbebb81f35490bbddb9635376"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:D2XPL5DN2IBXTC4JFPXXPNNOPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.CL","authors_text":"Daisy Stanton, RJ Skerry-Ryan, Yuxuan Wang","submitted_at":"2018-08-04T02:21:07Z","abstract_excerpt":"Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a state-of-the-art end-to-end text-to-speech synthesis system, to uncover expressive factors of variation in speaking style. In this work, we introduce the Text-Predicted Global Style Token (TP-GST) architecture, which treats GST combination weights or style embeddings as \"virtual\" speaking style labels within Tacotron. TP-GST learns to predict stylistic renderings from text alone, requiring neither explicit labels during training no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01410","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":""},"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":"2026-05-18T00:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AL/+oC9ugLBn6Drir2tCcYupnzC+Yt1Q4a8Kv9I0xABxZ0FS8to5MJponuM5b2wPoz/jedQlpkyObdqSCPGjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:09:04.812000Z"},"content_sha256":"f4a71abe82290883de399885cf35f1ba9895753c914edc675b2a23c02cfd604e","schema_version":"1.0","event_id":"sha256:f4a71abe82290883de399885cf35f1ba9895753c914edc675b2a23c02cfd604e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH/bundle.json","state_url":"https://pith.science/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH/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":"2026-05-25T23:09:04Z","links":{"resolver":"https://pith.science/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH","bundle":"https://pith.science/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH/bundle.json","state":"https://pith.science/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D2XPL5DN2IBXTC4JFPXXPNNOPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:D2XPL5DN2IBXTC4JFPXXPNNOPH","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":"49f9bbe9102e0fa4ebabb2cfd266f0cb77aefa2ee43d2eb8f35f0a93d4cbab88","cross_cats_sorted":["cs.LG","cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-04T02:21:07Z","title_canon_sha256":"f9180cde054826da0f7d6ad554af2a710ec2fc96b71a0afb82b2d38b5ace0584"},"schema_version":"1.0","source":{"id":"1808.01410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.01410","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"1808.01410v1","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01410","created_at":"2026-05-18T00:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"D2XPL5DN2IBX","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"D2XPL5DN2IBXTC4J","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"D2XPL5DN","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:f4a71abe82290883de399885cf35f1ba9895753c914edc675b2a23c02cfd604e","target":"graph","created_at":"2026-05-18T00:08:53Z","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"},"paper":{"abstract_excerpt":"Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a state-of-the-art end-to-end text-to-speech synthesis system, to uncover expressive factors of variation in speaking style. In this work, we introduce the Text-Predicted Global Style Token (TP-GST) architecture, which treats GST combination weights or style embeddings as \"virtual\" speaking style labels within Tacotron. TP-GST learns to predict stylistic renderings from text alone, requiring neither explicit labels during training no","authors_text":"Daisy Stanton, RJ Skerry-Ryan, Yuxuan Wang","cross_cats":["cs.LG","cs.SD","eess.AS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-04T02:21:07Z","title":"Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01410","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:dbaea4d665310a1c3fe393a16f3ef2b14279d13bbebb81f35490bbddb9635376","target":"record","created_at":"2026-05-18T00:08:53Z","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":"49f9bbe9102e0fa4ebabb2cfd266f0cb77aefa2ee43d2eb8f35f0a93d4cbab88","cross_cats_sorted":["cs.LG","cs.SD","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-04T02:21:07Z","title_canon_sha256":"f9180cde054826da0f7d6ad554af2a710ec2fc96b71a0afb82b2d38b5ace0584"},"schema_version":"1.0","source":{"id":"1808.01410","kind":"arxiv","version":1}},"canonical_sha256":"1eaef5f46dd203798b892bef77b5ae79c963a29ca8d53000abe22759359ef489","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eaef5f46dd203798b892bef77b5ae79c963a29ca8d53000abe22759359ef489","first_computed_at":"2026-05-18T00:08:53.089496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:53.089496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LDPSpaKkZFKZr5K85zbWldpqrXEfIRPXb7O90VP2N0cWbk5uoVlFDhHyuudCxomMRZqt4i/NZGR0ImDWm2c8AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:53.090213Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.01410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbaea4d665310a1c3fe393a16f3ef2b14279d13bbebb81f35490bbddb9635376","sha256:f4a71abe82290883de399885cf35f1ba9895753c914edc675b2a23c02cfd604e"],"state_sha256":"db5f0aa1d830f9f7485d73c3325a3bc73d62652b51fa4b95d92ca2bf90987e3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IlFZ2hzUTKkayArERzRp/WOO42j6fVuT39H4debs8gWQicL5kcm8kUfMx3fLEIa/8R5DbUaHiiL2I/aGP5F7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:09:04.815596Z","bundle_sha256":"c1891804a7c52503eacf3e32ef933967d9f701c13090086dd4749e269fd66e88"}}