{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4TSVLEBSXAFE5TLSVEZW5URTLW","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":"a43717f911dbb12b8e1f5cdb41dd1e37ed373dc5613b9602a88c23766a5b15a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T17:50:34Z","title_canon_sha256":"bf0070ac02bafb10c1e759be0cece311452a3357ad55b673743a6551cac0e8de"},"schema_version":"1.0","source":{"id":"2411.11770","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11770","created_at":"2026-07-05T10:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11770v4","created_at":"2026-07-05T10:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11770","created_at":"2026-07-05T10:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"4TSVLEBSXAFE","created_at":"2026-07-05T10:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"4TSVLEBSXAFE5TLS","created_at":"2026-07-05T10:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"4TSVLEBS","created_at":"2026-07-05T10:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:9e94b507f17f40d6fb2df3a0e92de3f0b3b77d25e366e5bc9ee99e4baa54f192","target":"graph","created_at":"2026-07-05T10:06:09Z","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/2411.11770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of converting Hanyu Pinyin abbreviations to Chinese characters is a significant branch within the domain of Chinese Spelling Correction (CSC). It plays an important role in many downstream applications such as named entity recognition and sentiment analysis. This task typically involves text-length alignment and seems easy to solve; however, due to the limited information content in pinyin abbreviations, achieving accurate conversion is challenging. In this paper, we treat this as a fill-mask task and propose CNMBERT, which stands for zh-CN Pinyin Multi-mask BERT Model, as a solution ","authors_text":"Feng Cao, Zishuo Feng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T17:50:34Z","title":"CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11770","kind":"arxiv","version":4},"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":"sha256:8a14c6ac693c2d45c8ab75abea45660f4c50ba9722d66d3b6e7777c00e7f6215","target":"record","created_at":"2026-07-05T10:06:09Z","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":"a43717f911dbb12b8e1f5cdb41dd1e37ed373dc5613b9602a88c23766a5b15a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T17:50:34Z","title_canon_sha256":"bf0070ac02bafb10c1e759be0cece311452a3357ad55b673743a6551cac0e8de"},"schema_version":"1.0","source":{"id":"2411.11770","kind":"arxiv","version":4}},"canonical_sha256":"e4e5559032b80a4ecd72a9336ed2335db427d6157c91a5fc0ff343cf59a7096c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4e5559032b80a4ecd72a9336ed2335db427d6157c91a5fc0ff343cf59a7096c","first_computed_at":"2026-07-05T10:06:09.190243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:09.190243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fr5heiBtYsvQuktaLjPMwxx4AGg6tn6ZzTSNZEkxVKxawJNfBK2O2PnV3gsz9zCyDpkqtkTClpHYgQGV+SBvAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:09.190758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11770","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a14c6ac693c2d45c8ab75abea45660f4c50ba9722d66d3b6e7777c00e7f6215","sha256:9e94b507f17f40d6fb2df3a0e92de3f0b3b77d25e366e5bc9ee99e4baa54f192"],"state_sha256":"eff7c48c166e6f5211f9ed8108d3cc143e20adb3fad312fc035ce05df11d9dd3"}