{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FWOKHC4L4Z6NGUWAOQUJWZBDCU","short_pith_number":"pith:FWOKHC4L","canonical_record":{"source":{"id":"2004.03136","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T05:44:58Z","cross_cats_sorted":[],"title_canon_sha256":"35420c08805014435ce218a56e335348cd1e1a6424fe59a1adfc5fcba284a169","abstract_canon_sha256":"9b6626a42c71eefa4c7f13fdf21df9d413031f4c475dbe183d6c94e79fc45a9a"},"schema_version":"1.0"},"canonical_sha256":"2d9ca38b8be67cd352c074289b64231512e208bca294f76737e648e2714fa73e","source":{"kind":"arxiv","id":"2004.03136","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03136","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03136v5","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03136","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"FWOKHC4L4Z6N","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"pith_short_16","alias_value":"FWOKHC4L4Z6NGUWA","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"pith_short_8","alias_value":"FWOKHC4L","created_at":"2026-07-05T01:36:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FWOKHC4L4Z6NGUWAOQUJWZBDCU","target":"record","payload":{"canonical_record":{"source":{"id":"2004.03136","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T05:44:58Z","cross_cats_sorted":[],"title_canon_sha256":"35420c08805014435ce218a56e335348cd1e1a6424fe59a1adfc5fcba284a169","abstract_canon_sha256":"9b6626a42c71eefa4c7f13fdf21df9d413031f4c475dbe183d6c94e79fc45a9a"},"schema_version":"1.0"},"canonical_sha256":"2d9ca38b8be67cd352c074289b64231512e208bca294f76737e648e2714fa73e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:08.918934Z","signature_b64":"00L+HlZtvPJCkV7Su809wMlT7J+nn9BtebZHX4LF8AA88sO62mLzal7efkfDNM7peYKOrLIjSCW/Gjkl/8VcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d9ca38b8be67cd352c074289b64231512e208bca294f76737e648e2714fa73e","last_reissued_at":"2026-07-05T01:36:08.918382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:08.918382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.03136","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:36:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHQitAa4Q6EI8bA/T3sATmAKSQFrQAfF8njFCv+DpnbfKGJ3vAGtnMDGMEDQr6utJ3wR0W16pEa2KcqTgSqYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:40:02.214730Z"},"content_sha256":"b686403af0913e6f56913706203b793a001f58b8c41d3e1570706381edbcf115","schema_version":"1.0","event_id":"sha256:b686403af0913e6f56913706203b793a001f58b8c41d3e1570706381edbcf115"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FWOKHC4L4Z6NGUWAOQUJWZBDCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyubyong Park, Seanie Lee","submitted_at":"2020-04-07T05:44:58Z","abstract_excerpt":"Conversion of Chinese graphemes to phonemes (G2P) is an essential component in Mandarin Chinese Text-To-Speech (TTS) systems. One of the biggest challenges in Chinese G2P conversion is how to disambiguate the pronunciation of polyphones - characters having multiple pronunciations. Although many academic efforts have been made to address it, there has been no open dataset that can serve as a standard benchmark for fair comparison to date. In addition, most of the reported systems are hard to employ for researchers or practitioners who want to convert Chinese text into pinyin at their convenienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03136","kind":"arxiv","version":5},"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/2004.03136/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":"2026-07-05T01:36:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5baJWwT7Q0V9G9kLiwcS+xYIs1vutalZYRtsgW1jjnpcUe1WkzWysUnvytRB21T2bGp9RQM9mRo5Sf5dvmI0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:40:02.215385Z"},"content_sha256":"f57f21fcf7eb196ab069da1e7487bad0e64cfba59769f0a94d6067ba50b49316","schema_version":"1.0","event_id":"sha256:f57f21fcf7eb196ab069da1e7487bad0e64cfba59769f0a94d6067ba50b49316"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU/bundle.json","state_url":"https://pith.science/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU/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":"2026-08-10T14:40:02Z","links":{"resolver":"https://pith.science/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU","bundle":"https://pith.science/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU/bundle.json","state":"https://pith.science/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWOKHC4L4Z6NGUWAOQUJWZBDCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FWOKHC4L4Z6NGUWAOQUJWZBDCU","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":"9b6626a42c71eefa4c7f13fdf21df9d413031f4c475dbe183d6c94e79fc45a9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T05:44:58Z","title_canon_sha256":"35420c08805014435ce218a56e335348cd1e1a6424fe59a1adfc5fcba284a169"},"schema_version":"1.0","source":{"id":"2004.03136","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03136","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03136v5","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03136","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"FWOKHC4L4Z6N","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"pith_short_16","alias_value":"FWOKHC4L4Z6NGUWA","created_at":"2026-07-05T01:36:08Z"},{"alias_kind":"pith_short_8","alias_value":"FWOKHC4L","created_at":"2026-07-05T01:36:08Z"}],"graph_snapshots":[{"event_id":"sha256:f57f21fcf7eb196ab069da1e7487bad0e64cfba59769f0a94d6067ba50b49316","target":"graph","created_at":"2026-07-05T01:36:08Z","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/2004.03136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversion of Chinese graphemes to phonemes (G2P) is an essential component in Mandarin Chinese Text-To-Speech (TTS) systems. One of the biggest challenges in Chinese G2P conversion is how to disambiguate the pronunciation of polyphones - characters having multiple pronunciations. Although many academic efforts have been made to address it, there has been no open dataset that can serve as a standard benchmark for fair comparison to date. In addition, most of the reported systems are hard to employ for researchers or practitioners who want to convert Chinese text into pinyin at their convenienc","authors_text":"Kyubyong Park, Seanie Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T05:44:58Z","title":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03136","kind":"arxiv","version":5},"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:b686403af0913e6f56913706203b793a001f58b8c41d3e1570706381edbcf115","target":"record","created_at":"2026-07-05T01:36:08Z","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":"9b6626a42c71eefa4c7f13fdf21df9d413031f4c475dbe183d6c94e79fc45a9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T05:44:58Z","title_canon_sha256":"35420c08805014435ce218a56e335348cd1e1a6424fe59a1adfc5fcba284a169"},"schema_version":"1.0","source":{"id":"2004.03136","kind":"arxiv","version":5}},"canonical_sha256":"2d9ca38b8be67cd352c074289b64231512e208bca294f76737e648e2714fa73e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d9ca38b8be67cd352c074289b64231512e208bca294f76737e648e2714fa73e","first_computed_at":"2026-07-05T01:36:08.918382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:08.918382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"00L+HlZtvPJCkV7Su809wMlT7J+nn9BtebZHX4LF8AA88sO62mLzal7efkfDNM7peYKOrLIjSCW/Gjkl/8VcCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:08.918934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.03136","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b686403af0913e6f56913706203b793a001f58b8c41d3e1570706381edbcf115","sha256:f57f21fcf7eb196ab069da1e7487bad0e64cfba59769f0a94d6067ba50b49316"],"state_sha256":"aff2d9b9caa65f5366d327e5ebeec9ac9c86f876a658bef19e532c58b16449ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0nixJDYOju5Nase9OiYTSphb8ucvcYRNQEvOYAvlAck3/8b1TkENI2GUpYEsyEjlRFdGBVnwtVhmzmUSKYTYDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:40:02.220940Z","bundle_sha256":"d22b4bc2d02c24822a9b1f4f3e1bd292afbaa91227f3250b1f120d44959f25fd"}}