{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5H554CIWO7QQGNWK6DD7M5S7Q7","short_pith_number":"pith:5H554CIW","canonical_record":{"source":{"id":"2103.15060","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-28T06:24:00Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c515173c4a7d4208163a90dc270a6f83d9e538ba88bba2f9f8954117e5ccfdd1","abstract_canon_sha256":"7da762b595981ed96aa42e37ee06ab40af33c8da5f8cb155df98e17b2f961a75"},"schema_version":"1.0"},"canonical_sha256":"e9fbde091677e10336caf0c7f6765f87fae4e2cb720ef9b04aed9ef9a4546b0d","source":{"kind":"arxiv","id":"2103.15060","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15060","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15060v3","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15060","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_12","alias_value":"5H554CIWO7QQ","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_16","alias_value":"5H554CIWO7QQGNWK","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_8","alias_value":"5H554CIW","created_at":"2026-07-05T02:46:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5H554CIWO7QQGNWK6DD7M5S7Q7","target":"record","payload":{"canonical_record":{"source":{"id":"2103.15060","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-28T06:24:00Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c515173c4a7d4208163a90dc270a6f83d9e538ba88bba2f9f8954117e5ccfdd1","abstract_canon_sha256":"7da762b595981ed96aa42e37ee06ab40af33c8da5f8cb155df98e17b2f961a75"},"schema_version":"1.0"},"canonical_sha256":"e9fbde091677e10336caf0c7f6765f87fae4e2cb720ef9b04aed9ef9a4546b0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:45.186013Z","signature_b64":"abVZlOQoXYbRjIyt3UrEmfMsi8NWhH1kAkCP0eEdbf3gIxgtL7yWj5CgQMp3R2dOs7Yr+ZaADqHno4DZbyTdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9fbde091677e10336caf0c7f6765f87fae4e2cb720ef9b04aed9ef9a4546b0d","last_reissued_at":"2026-07-05T02:46:45.185393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:45.185393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.15060","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":"2026-07-05T02:46:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PLiuiOM1tcii7DTMIZAoGjLpStuIeLX43Gc9ROEuCuqK7Qc9yh3mto+KlMo2ujJaS0ONWJDY/4PR9YFFFi7gBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:44:17.501226Z"},"content_sha256":"32552f81b5f734ddd846bfc6e00b615ce2c3a4e6acf4a088ac35130f1e12dd8e","schema_version":"1.0","event_id":"sha256:32552f81b5f734ddd846bfc6e00b615ce2c3a4e6acf4a088ac35130f1e12dd8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5H554CIWO7QQGNWK6DD7M5S7Q7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Heiga Zen, Jonathan Shen, Ye Jia, Yonghui Wu, Yu Zhang","submitted_at":"2021-03-28T06:24:00Z","abstract_excerpt":"This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between them. It can be pre-trained on a large text corpus in a self-supervised manner, and fine-tuned in a TTS task. Experimental results show that a neural TTS model using a pre-trained PnG BERT as its encoder yields more natural prosody and more accurate pronunciation than a baseline model using only phoneme input with no pre-training. Subjective side-by-side prefere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15060","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/2103.15060/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":"2026-07-05T02:46:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zgbj4X/XTDFIlN1WjAkVOcIsVznQXnQVKt8cq8vb4bDARes1tTL/faehuiPjlCULnEoZomdLRR4V3VA+JHzaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:44:17.501959Z"},"content_sha256":"054cfb2849e53fe1fb74719c5a9db607c78549744ac4aa4375c55e4d64f8625a","schema_version":"1.0","event_id":"sha256:054cfb2849e53fe1fb74719c5a9db607c78549744ac4aa4375c55e4d64f8625a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5H554CIWO7QQGNWK6DD7M5S7Q7/bundle.json","state_url":"https://pith.science/pith/5H554CIWO7QQGNWK6DD7M5S7Q7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5H554CIWO7QQGNWK6DD7M5S7Q7/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":"2026-08-14T12:44:17Z","links":{"resolver":"https://pith.science/pith/5H554CIWO7QQGNWK6DD7M5S7Q7","bundle":"https://pith.science/pith/5H554CIWO7QQGNWK6DD7M5S7Q7/bundle.json","state":"https://pith.science/pith/5H554CIWO7QQGNWK6DD7M5S7Q7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5H554CIWO7QQGNWK6DD7M5S7Q7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5H554CIWO7QQGNWK6DD7M5S7Q7","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":"7da762b595981ed96aa42e37ee06ab40af33c8da5f8cb155df98e17b2f961a75","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-28T06:24:00Z","title_canon_sha256":"c515173c4a7d4208163a90dc270a6f83d9e538ba88bba2f9f8954117e5ccfdd1"},"schema_version":"1.0","source":{"id":"2103.15060","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.15060","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"arxiv_version","alias_value":"2103.15060v3","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15060","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_12","alias_value":"5H554CIWO7QQ","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_16","alias_value":"5H554CIWO7QQGNWK","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_8","alias_value":"5H554CIW","created_at":"2026-07-05T02:46:45Z"}],"graph_snapshots":[{"event_id":"sha256:054cfb2849e53fe1fb74719c5a9db607c78549744ac4aa4375c55e4d64f8625a","target":"graph","created_at":"2026-07-05T02:46:45Z","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/2103.15060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between them. It can be pre-trained on a large text corpus in a self-supervised manner, and fine-tuned in a TTS task. Experimental results show that a neural TTS model using a pre-trained PnG BERT as its encoder yields more natural prosody and more accurate pronunciation than a baseline model using only phoneme input with no pre-training. Subjective side-by-side prefere","authors_text":"Heiga Zen, Jonathan Shen, Ye Jia, Yonghui Wu, Yu Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-28T06:24:00Z","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15060","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":"sha256:32552f81b5f734ddd846bfc6e00b615ce2c3a4e6acf4a088ac35130f1e12dd8e","target":"record","created_at":"2026-07-05T02:46:45Z","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":"7da762b595981ed96aa42e37ee06ab40af33c8da5f8cb155df98e17b2f961a75","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-28T06:24:00Z","title_canon_sha256":"c515173c4a7d4208163a90dc270a6f83d9e538ba88bba2f9f8954117e5ccfdd1"},"schema_version":"1.0","source":{"id":"2103.15060","kind":"arxiv","version":3}},"canonical_sha256":"e9fbde091677e10336caf0c7f6765f87fae4e2cb720ef9b04aed9ef9a4546b0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9fbde091677e10336caf0c7f6765f87fae4e2cb720ef9b04aed9ef9a4546b0d","first_computed_at":"2026-07-05T02:46:45.185393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:45.185393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"abVZlOQoXYbRjIyt3UrEmfMsi8NWhH1kAkCP0eEdbf3gIxgtL7yWj5CgQMp3R2dOs7Yr+ZaADqHno4DZbyTdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:45.186013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.15060","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32552f81b5f734ddd846bfc6e00b615ce2c3a4e6acf4a088ac35130f1e12dd8e","sha256:054cfb2849e53fe1fb74719c5a9db607c78549744ac4aa4375c55e4d64f8625a"],"state_sha256":"ad5a4a3c3bddcc8469f40bb32eb5d1797ba656707dfdfedefbfda99db2616322"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+A7VTNuaOdpdJ4G5CG5ftGBwaEkjhEETVH/Glp1xDaE1SazXiyUNw9mITQiqQlczaSUFPr4ERjpjeMxi8Zt0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:44:17.508666Z","bundle_sha256":"862c9db93969dc5afc14a0d6b70563c7f28bbb55b34cead7969f13f06dd7cad7"}}