{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:74KRSFYYPTSMIEURIASXXC6V3D","short_pith_number":"pith:74KRSFYY","canonical_record":{"source":{"id":"2501.01102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T06:51:52Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"9318b7bb69efd08921138238ea64574c0c6db25c13ce0de30258a3fbed57e71c","abstract_canon_sha256":"5d3c4b595531327bc0b607191f3caf23b1187be4400674a47f7973a1cb5951d0"},"schema_version":"1.0"},"canonical_sha256":"ff151917187ce4c4129140257b8bd5d8c4a1a69d38f568a6ec491ff88fadefee","source":{"kind":"arxiv","id":"2501.01102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01102","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01102v1","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01102","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"pith_short_12","alias_value":"74KRSFYYPTSM","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"pith_short_16","alias_value":"74KRSFYYPTSMIEUR","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"pith_short_8","alias_value":"74KRSFYY","created_at":"2026-07-05T09:56:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:74KRSFYYPTSMIEURIASXXC6V3D","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T06:51:52Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"9318b7bb69efd08921138238ea64574c0c6db25c13ce0de30258a3fbed57e71c","abstract_canon_sha256":"5d3c4b595531327bc0b607191f3caf23b1187be4400674a47f7973a1cb5951d0"},"schema_version":"1.0"},"canonical_sha256":"ff151917187ce4c4129140257b8bd5d8c4a1a69d38f568a6ec491ff88fadefee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:14.712871Z","signature_b64":"ddbTOztvUslMoh/45qfZ1ofK9yS2V3XXDMCYApVxsk6M6BBd/kWO4k2xPVMsoDTvXp9PpTyB9Vubqg4ZRd+GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff151917187ce4c4129140257b8bd5d8c4a1a69d38f568a6ec491ff88fadefee","last_reissued_at":"2026-07-05T09:56:14.712427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:14.712427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01102","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":"2026-07-05T09:56:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bDkeInMWY/GCB8p7enb9tjUle+JIoo+SNUjjsSuwO2Q+oFH7qnxgmRKzzCVCOvMpceMqwCtakjcWQJaoOGHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T13:11:02.630760Z"},"content_sha256":"86fdef927588f162e34d3e92b6a6d43576b8a4f40db59f2a7e8ce68be6d839c7","schema_version":"1.0","event_id":"sha256:86fdef927588f162e34d3e92b6a6d43576b8a4f40db59f2a7e8ce68be6d839c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:74KRSFYYPTSMIEURIASXXC6V3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dan Su, Dongyang Dai, Dong Yu, Helen Meng, Jia Jia, Shiyin Kang, Xixin Wu, Zhiyong Wu","submitted_at":"2025-01-02T06:51:52Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the pronunciation of a polyphonic character, which accepts sentence containing polyphonic character as input in the form of Chinese character sequence without the necessity of any preprocessing. The proposed method consists of a pre-trained bidirectional encoder representations from Transformers (BERT) model and a neural network (NN) based classifier. The pre-trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01102","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/2501.01102/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":"2026-07-05T09:56:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6LuHUamc4ZXQw6C3Fr1czAZSl3qatKaPWVkzPlcOT6yJ4s9uytaQN2LjjxeFmzbpgJMLKP3hxfqEv1Kc4W9YDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T13:11:02.631128Z"},"content_sha256":"b6c970d1cc11588949d3a42a6092b9ae9d2ccbba269086e852941de853bf3639","schema_version":"1.0","event_id":"sha256:b6c970d1cc11588949d3a42a6092b9ae9d2ccbba269086e852941de853bf3639"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74KRSFYYPTSMIEURIASXXC6V3D/bundle.json","state_url":"https://pith.science/pith/74KRSFYYPTSMIEURIASXXC6V3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74KRSFYYPTSMIEURIASXXC6V3D/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":"2026-07-24T13:11:02Z","links":{"resolver":"https://pith.science/pith/74KRSFYYPTSMIEURIASXXC6V3D","bundle":"https://pith.science/pith/74KRSFYYPTSMIEURIASXXC6V3D/bundle.json","state":"https://pith.science/pith/74KRSFYYPTSMIEURIASXXC6V3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74KRSFYYPTSMIEURIASXXC6V3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:74KRSFYYPTSMIEURIASXXC6V3D","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":"5d3c4b595531327bc0b607191f3caf23b1187be4400674a47f7973a1cb5951d0","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T06:51:52Z","title_canon_sha256":"9318b7bb69efd08921138238ea64574c0c6db25c13ce0de30258a3fbed57e71c"},"schema_version":"1.0","source":{"id":"2501.01102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01102","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01102v1","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01102","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"pith_short_12","alias_value":"74KRSFYYPTSM","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"pith_short_16","alias_value":"74KRSFYYPTSMIEUR","created_at":"2026-07-05T09:56:14Z"},{"alias_kind":"pith_short_8","alias_value":"74KRSFYY","created_at":"2026-07-05T09:56:14Z"}],"graph_snapshots":[{"event_id":"sha256:b6c970d1cc11588949d3a42a6092b9ae9d2ccbba269086e852941de853bf3639","target":"graph","created_at":"2026-07-05T09:56:14Z","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/2501.01102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the pronunciation of a polyphonic character, which accepts sentence containing polyphonic character as input in the form of Chinese character sequence without the necessity of any preprocessing. The proposed method consists of a pre-trained bidirectional encoder representations from Transformers (BERT) model and a neural network (NN) based classifier. The pre-trained ","authors_text":"Dan Su, Dongyang Dai, Dong Yu, Helen Meng, Jia Jia, Shiyin Kang, Xixin Wu, Zhiyong Wu","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T06:51:52Z","title":"Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01102","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":"sha256:86fdef927588f162e34d3e92b6a6d43576b8a4f40db59f2a7e8ce68be6d839c7","target":"record","created_at":"2026-07-05T09:56:14Z","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":"5d3c4b595531327bc0b607191f3caf23b1187be4400674a47f7973a1cb5951d0","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-02T06:51:52Z","title_canon_sha256":"9318b7bb69efd08921138238ea64574c0c6db25c13ce0de30258a3fbed57e71c"},"schema_version":"1.0","source":{"id":"2501.01102","kind":"arxiv","version":1}},"canonical_sha256":"ff151917187ce4c4129140257b8bd5d8c4a1a69d38f568a6ec491ff88fadefee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff151917187ce4c4129140257b8bd5d8c4a1a69d38f568a6ec491ff88fadefee","first_computed_at":"2026-07-05T09:56:14.712427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:14.712427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ddbTOztvUslMoh/45qfZ1ofK9yS2V3XXDMCYApVxsk6M6BBd/kWO4k2xPVMsoDTvXp9PpTyB9Vubqg4ZRd+GAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:14.712871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86fdef927588f162e34d3e92b6a6d43576b8a4f40db59f2a7e8ce68be6d839c7","sha256:b6c970d1cc11588949d3a42a6092b9ae9d2ccbba269086e852941de853bf3639"],"state_sha256":"a06a544e865507d0188e1862c74e33aa6e8a1355b14bd5e5249ed9ea11d65b94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/IuQVYWhJf1OripKL3lsjRGFhxjYAY4E3nIkUqkZ8zdwzAnfmwjqNPS3gyZ7TpZpscUNaWFTJKE4xLB3r2ueBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T13:11:02.633638Z","bundle_sha256":"f26b9cf7b58a049f59b300d059eb8ced8dacf0ee40b2c93ff2a1c15e4176320c"}}