{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XVB2ZK2Q4FICMML2S32LC5NDBR","short_pith_number":"pith:XVB2ZK2Q","canonical_record":{"source":{"id":"2207.12089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-01T09:16:29Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"75b18e21364ba9ccc094c361a9ac298b760eceadfafe64e3b05298cdfbccc285","abstract_canon_sha256":"4a7818248bb4f57616e3c0b0d107cd0795e98cbdfbb3c6a2b91ad273397e0457"},"schema_version":"1.0"},"canonical_sha256":"bd43acab50e15026317a96f4b175a30c54e7eed9f3015828c281ddf6c69b6971","source":{"kind":"arxiv","id":"2207.12089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12089","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12089v1","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12089","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"XVB2ZK2Q4FIC","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"XVB2ZK2Q4FICMML2","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"XVB2ZK2Q","created_at":"2026-07-05T04:43:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XVB2ZK2Q4FICMML2S32LC5NDBR","target":"record","payload":{"canonical_record":{"source":{"id":"2207.12089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-01T09:16:29Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"75b18e21364ba9ccc094c361a9ac298b760eceadfafe64e3b05298cdfbccc285","abstract_canon_sha256":"4a7818248bb4f57616e3c0b0d107cd0795e98cbdfbb3c6a2b91ad273397e0457"},"schema_version":"1.0"},"canonical_sha256":"bd43acab50e15026317a96f4b175a30c54e7eed9f3015828c281ddf6c69b6971","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:13.103391Z","signature_b64":"DHaA7tUq+FyOx0FSv0/1pIerOpYozARiOctlDoz+fC4U6dmvgrKaWLfuXfR5rfbFPithWojQ9fnZ13SSh4/aDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd43acab50e15026317a96f4b175a30c54e7eed9f3015828c281ddf6c69b6971","last_reissued_at":"2026-07-05T04:43:13.103020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:13.103020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.12089","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":"2026-07-05T04:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hktHa3dnrR2+tNwX4m0lFUr+mGYfF5CY0KviQgoYHoBn6mjgheTjdknkUZCoHYbqwR8/cLtftSULDiqXtuZ2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:17:30.683156Z"},"content_sha256":"6312694d653a6a12719f65b93ccf00584f00cab900c552a6d19117bf1e3dbd85","schema_version":"1.0","event_id":"sha256:6312694d653a6a12719f65b93ccf00584f00cab900c552a6d19117bf1e3dbd85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XVB2ZK2Q4FICMML2S32LC5NDBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Polyphone BERT for Polyphone Disambiguation in Mandarin Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Baoxiang Li, Ken Zheng, Song Zhang, Xiaoxu Zhu","submitted_at":"2022-07-01T09:16:29Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion is an indispensable part of the Chinese Mandarin text-to-speech (TTS) system, and the core of G2P conversion is to solve the problem of polyphone disambiguation, which is to pick up the correct pronunciation for several candidates for a Chinese polyphonic character. In this paper, we propose a Chinese polyphone BERT model to predict the pronunciations of Chinese polyphonic characters. Firstly, we create 741 new Chinese monophonic characters from 354 source Chinese polyphonic characters by pronunciation. Then we get a Chinese polyphone BERT by extending a pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12089","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/2207.12089/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":"2026-07-05T04:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9SgGRNGD1F5fiMII4E021u1I+I+/VrkPYkJ2moLrkEEyACgOJkiDMs1PyOJxSb3SZxNKd8DXBAmfiJ4ANXSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:17:30.684611Z"},"content_sha256":"747d3dcf5059f2eb807bdc7f6d3e42df976f74387481b18324e35ccdc193f909","schema_version":"1.0","event_id":"sha256:747d3dcf5059f2eb807bdc7f6d3e42df976f74387481b18324e35ccdc193f909"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVB2ZK2Q4FICMML2S32LC5NDBR/bundle.json","state_url":"https://pith.science/pith/XVB2ZK2Q4FICMML2S32LC5NDBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVB2ZK2Q4FICMML2S32LC5NDBR/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":"2026-08-22T20:17:30Z","links":{"resolver":"https://pith.science/pith/XVB2ZK2Q4FICMML2S32LC5NDBR","bundle":"https://pith.science/pith/XVB2ZK2Q4FICMML2S32LC5NDBR/bundle.json","state":"https://pith.science/pith/XVB2ZK2Q4FICMML2S32LC5NDBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVB2ZK2Q4FICMML2S32LC5NDBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XVB2ZK2Q4FICMML2S32LC5NDBR","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":"4a7818248bb4f57616e3c0b0d107cd0795e98cbdfbb3c6a2b91ad273397e0457","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-01T09:16:29Z","title_canon_sha256":"75b18e21364ba9ccc094c361a9ac298b760eceadfafe64e3b05298cdfbccc285"},"schema_version":"1.0","source":{"id":"2207.12089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.12089","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2207.12089v1","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12089","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"XVB2ZK2Q4FIC","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"XVB2ZK2Q4FICMML2","created_at":"2026-07-05T04:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"XVB2ZK2Q","created_at":"2026-07-05T04:43:13Z"}],"graph_snapshots":[{"event_id":"sha256:747d3dcf5059f2eb807bdc7f6d3e42df976f74387481b18324e35ccdc193f909","target":"graph","created_at":"2026-07-05T04:43:13Z","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/2207.12089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion is an indispensable part of the Chinese Mandarin text-to-speech (TTS) system, and the core of G2P conversion is to solve the problem of polyphone disambiguation, which is to pick up the correct pronunciation for several candidates for a Chinese polyphonic character. In this paper, we propose a Chinese polyphone BERT model to predict the pronunciations of Chinese polyphonic characters. Firstly, we create 741 new Chinese monophonic characters from 354 source Chinese polyphonic characters by pronunciation. Then we get a Chinese polyphone BERT by extending a pr","authors_text":"Baoxiang Li, Ken Zheng, Song Zhang, Xiaoxu Zhu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-01T09:16:29Z","title":"A Polyphone BERT for Polyphone Disambiguation in Mandarin Chinese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12089","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":"sha256:6312694d653a6a12719f65b93ccf00584f00cab900c552a6d19117bf1e3dbd85","target":"record","created_at":"2026-07-05T04:43:13Z","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":"4a7818248bb4f57616e3c0b0d107cd0795e98cbdfbb3c6a2b91ad273397e0457","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-01T09:16:29Z","title_canon_sha256":"75b18e21364ba9ccc094c361a9ac298b760eceadfafe64e3b05298cdfbccc285"},"schema_version":"1.0","source":{"id":"2207.12089","kind":"arxiv","version":1}},"canonical_sha256":"bd43acab50e15026317a96f4b175a30c54e7eed9f3015828c281ddf6c69b6971","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd43acab50e15026317a96f4b175a30c54e7eed9f3015828c281ddf6c69b6971","first_computed_at":"2026-07-05T04:43:13.103020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:13.103020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DHaA7tUq+FyOx0FSv0/1pIerOpYozARiOctlDoz+fC4U6dmvgrKaWLfuXfR5rfbFPithWojQ9fnZ13SSh4/aDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:13.103391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.12089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6312694d653a6a12719f65b93ccf00584f00cab900c552a6d19117bf1e3dbd85","sha256:747d3dcf5059f2eb807bdc7f6d3e42df976f74387481b18324e35ccdc193f909"],"state_sha256":"c310c189927c513c1889c190f17d5e1173ee768e5f3394310ce5edd30bbf2b84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yC9BegOuGwlWzh4tFHLhaN+vzllbbf48P1/cR8mWts7wRIlFW3WKT1FiV7qXQMZ/EtnEyWbyOX92zVP6+Wt0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T20:17:30.690472Z","bundle_sha256":"aa244ee567c19ad6811b689c533b42ab2cf6eaa97d1f95166804fe551a54fa7e"}}