{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UQ66U4ZLP3DX72J4S2N6J27MVO","short_pith_number":"pith:UQ66U4ZL","canonical_record":{"source":{"id":"2205.11737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T03:08:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d77c1a1730facc8577c34abbb98f12aee2d0c074948eb4b38efe604bf9e6a1f","abstract_canon_sha256":"1e59f38517e7af88b9f364f9bd256494e2c07414af81e58a3d1b67a138f38596"},"schema_version":"1.0"},"canonical_sha256":"a43dea732b7ec77fe93c969be4ebecab853ef0e712edf3e7f378cc80a84b6274","source":{"kind":"arxiv","id":"2205.11737","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11737","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11737v1","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11737","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"pith_short_12","alias_value":"UQ66U4ZLP3DX","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"pith_short_16","alias_value":"UQ66U4ZLP3DX72J4","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"pith_short_8","alias_value":"UQ66U4ZL","created_at":"2026-07-05T04:26:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UQ66U4ZLP3DX72J4S2N6J27MVO","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T03:08:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d77c1a1730facc8577c34abbb98f12aee2d0c074948eb4b38efe604bf9e6a1f","abstract_canon_sha256":"1e59f38517e7af88b9f364f9bd256494e2c07414af81e58a3d1b67a138f38596"},"schema_version":"1.0"},"canonical_sha256":"a43dea732b7ec77fe93c969be4ebecab853ef0e712edf3e7f378cc80a84b6274","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:07.702464Z","signature_b64":"8nsW3qxmUjpSlTkSiab5Bvy/kCA07Sc/5QiMq7Qtpq3WhluG09P6O/91gLhZW7JAnFUqpc2COdbEDMGdwlceCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a43dea732b7ec77fe93c969be4ebecab853ef0e712edf3e7f378cc80a84b6274","last_reissued_at":"2026-07-05T04:26:07.701992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:07.701992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11737","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":"2026-07-05T04:26:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wBfDGG+tBGMduX42AfNWTGx9S5rMaFo3F5XZAKPfY39KRANnVSR3Jrl1RgtA/LUxQuj6dzyOuIGPYbi+sIzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:37:31.594476Z"},"content_sha256":"5ba4c5d3a94e6216891d67003916e863d24705737efa3156da14544b55a13c42","schema_version":"1.0","event_id":"sha256:5ba4c5d3a94e6216891d67003916e863d24705737efa3156da14544b55a13c42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UQ66U4ZLP3DX72J4S2N6J27MVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PERT: A New Solution to Pinyin to Character Conversion Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haiteng Wu, Jinghui Xiao, Qun Liu, Xin Jiang, Yuanfeng Xiong, Zhe Zhang","submitted_at":"2022-05-24T03:08:27Z","abstract_excerpt":"Pinyin to Character conversion (P2C) task is the key task of Input Method Engine (IME) in commercial input software for Asian languages, such as Chinese, Japanese, Thai language and so on. It's usually treated as sequence labelling task and resolved by language model, i.e. n-gram or RNN. However, the low capacity of the n-gram or RNN limits its performance. This paper introduces a new solution named PERT which stands for bidirectional Pinyin Encoder Representations from Transformers. It achieves significant improvement of performance over baselines. Furthermore, we combine PERT with n-gram und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11737","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/2205.11737/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":"2026-07-05T04:26:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"48pPtR7bux7sl4CvvptGnKqbjERXCeCyKN5MCz/7TL8iFpmFSL6F4HS0mWM2mEWadpnhTvFq4lajJtYZgFVSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:37:31.594885Z"},"content_sha256":"85067e332ecc5cf8f7476450e0c9280ae29b095c4c701bd33451039b54ca4372","schema_version":"1.0","event_id":"sha256:85067e332ecc5cf8f7476450e0c9280ae29b095c4c701bd33451039b54ca4372"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQ66U4ZLP3DX72J4S2N6J27MVO/bundle.json","state_url":"https://pith.science/pith/UQ66U4ZLP3DX72J4S2N6J27MVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQ66U4ZLP3DX72J4S2N6J27MVO/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":"2026-07-06T18:37:31Z","links":{"resolver":"https://pith.science/pith/UQ66U4ZLP3DX72J4S2N6J27MVO","bundle":"https://pith.science/pith/UQ66U4ZLP3DX72J4S2N6J27MVO/bundle.json","state":"https://pith.science/pith/UQ66U4ZLP3DX72J4S2N6J27MVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQ66U4ZLP3DX72J4S2N6J27MVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UQ66U4ZLP3DX72J4S2N6J27MVO","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":"1e59f38517e7af88b9f364f9bd256494e2c07414af81e58a3d1b67a138f38596","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T03:08:27Z","title_canon_sha256":"3d77c1a1730facc8577c34abbb98f12aee2d0c074948eb4b38efe604bf9e6a1f"},"schema_version":"1.0","source":{"id":"2205.11737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11737","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11737v1","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11737","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"pith_short_12","alias_value":"UQ66U4ZLP3DX","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"pith_short_16","alias_value":"UQ66U4ZLP3DX72J4","created_at":"2026-07-05T04:26:07Z"},{"alias_kind":"pith_short_8","alias_value":"UQ66U4ZL","created_at":"2026-07-05T04:26:07Z"}],"graph_snapshots":[{"event_id":"sha256:85067e332ecc5cf8f7476450e0c9280ae29b095c4c701bd33451039b54ca4372","target":"graph","created_at":"2026-07-05T04:26:07Z","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/2205.11737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pinyin to Character conversion (P2C) task is the key task of Input Method Engine (IME) in commercial input software for Asian languages, such as Chinese, Japanese, Thai language and so on. It's usually treated as sequence labelling task and resolved by language model, i.e. n-gram or RNN. However, the low capacity of the n-gram or RNN limits its performance. This paper introduces a new solution named PERT which stands for bidirectional Pinyin Encoder Representations from Transformers. It achieves significant improvement of performance over baselines. Furthermore, we combine PERT with n-gram und","authors_text":"Haiteng Wu, Jinghui Xiao, Qun Liu, Xin Jiang, Yuanfeng Xiong, Zhe Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T03:08:27Z","title":"PERT: A New Solution to Pinyin to Character Conversion Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11737","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":"sha256:5ba4c5d3a94e6216891d67003916e863d24705737efa3156da14544b55a13c42","target":"record","created_at":"2026-07-05T04:26:07Z","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":"1e59f38517e7af88b9f364f9bd256494e2c07414af81e58a3d1b67a138f38596","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T03:08:27Z","title_canon_sha256":"3d77c1a1730facc8577c34abbb98f12aee2d0c074948eb4b38efe604bf9e6a1f"},"schema_version":"1.0","source":{"id":"2205.11737","kind":"arxiv","version":1}},"canonical_sha256":"a43dea732b7ec77fe93c969be4ebecab853ef0e712edf3e7f378cc80a84b6274","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a43dea732b7ec77fe93c969be4ebecab853ef0e712edf3e7f378cc80a84b6274","first_computed_at":"2026-07-05T04:26:07.701992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:07.701992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nsW3qxmUjpSlTkSiab5Bvy/kCA07Sc/5QiMq7Qtpq3WhluG09P6O/91gLhZW7JAnFUqpc2COdbEDMGdwlceCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:07.702464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ba4c5d3a94e6216891d67003916e863d24705737efa3156da14544b55a13c42","sha256:85067e332ecc5cf8f7476450e0c9280ae29b095c4c701bd33451039b54ca4372"],"state_sha256":"2ec1d83cb92329b72bd3694f5743d325006f4f06f6d2f1b76f32c60e2d61ecc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fBcchheazzppMyEnAqb7t4z0EdgHb1+NycVy4eLz1iWGxQxJj5WUcPTrFRcozAOrW8DuNgf9PO98a1NI4K71Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:37:31.597055Z","bundle_sha256":"f4b6d080ee7f62e61be17556f2b2fcd7552d6acf79fab13ae9f8f412aa0a22d1"}}