{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OPRGM36XGYZ4BYWSOBHVGDX74V","short_pith_number":"pith:OPRGM36X","schema_version":"1.0","canonical_sha256":"73e2666fd73633c0e2d2704f530effe5718178ab1ab953bc5ee1f34323e22eea","source":{"kind":"arxiv","id":"2203.10929","version":3},"attestation_state":"computed","paper":{"title":"General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunhui Ai, Guohong Fu, Lei Geng, Qi Lv, Xu Yan, Ziqiang Cao","submitted_at":"2022-03-21T12:49:44Z","abstract_excerpt":"The lack of label data is one of the significant bottlenecks for Chinese Spelling Check (CSC). Existing researches use the method of automatic generation by exploiting unlabeled data to expand the supervised corpus. However, there is a big gap between the real input scenario and automatic generated corpus. Thus, we develop a competitive general speller ECSpell which adopts the Error Consistent masking strategy to create data for pretraining. This error consistency masking strategy is used to specify the error types of automatically generated sentences which is consistent with real scene. The e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.10929","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-21T12:49:44Z","cross_cats_sorted":[],"title_canon_sha256":"b92e776f576aec010920ed525883bb26b28ad930161b45c9626df4b8ac1e1f05","abstract_canon_sha256":"faf484866bb5d63dec7f3833e1dfc8090b797e95d2e40cf725048dca8eb97c42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:08.465844Z","signature_b64":"lurB5zEQiY1/4Mcb6jMX0DQNVdtnNXMxD2KkLrQvUEN3U7W8BU5Kgqh8EG7Q02T3kXTHd+6b0hRrNxa487qeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e2666fd73633c0e2d2704f530effe5718178ab1ab953bc5ee1f34323e22eea","last_reissued_at":"2026-07-05T05:23:08.465398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:08.465398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"General and Domain Adaptive Chinese Spelling Check with Error Consistent Pretraining","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunhui Ai, Guohong Fu, Lei Geng, Qi Lv, Xu Yan, Ziqiang Cao","submitted_at":"2022-03-21T12:49:44Z","abstract_excerpt":"The lack of label data is one of the significant bottlenecks for Chinese Spelling Check (CSC). Existing researches use the method of automatic generation by exploiting unlabeled data to expand the supervised corpus. However, there is a big gap between the real input scenario and automatic generated corpus. Thus, we develop a competitive general speller ECSpell which adopts the Error Consistent masking strategy to create data for pretraining. This error consistency masking strategy is used to specify the error types of automatically generated sentences which is consistent with real scene. The e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10929","kind":"arxiv","version":3},"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/2203.10929/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.10929","created_at":"2026-07-05T05:23:08.465450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10929v3","created_at":"2026-07-05T05:23:08.465450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10929","created_at":"2026-07-05T05:23:08.465450+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPRGM36XGYZ4","created_at":"2026-07-05T05:23:08.465450+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPRGM36XGYZ4BYWS","created_at":"2026-07-05T05:23:08.465450+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPRGM36X","created_at":"2026-07-05T05:23:08.465450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V","json":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V.json","graph_json":"https://pith.science/api/pith-number/OPRGM36XGYZ4BYWSOBHVGDX74V/graph.json","events_json":"https://pith.science/api/pith-number/OPRGM36XGYZ4BYWSOBHVGDX74V/events.json","paper":"https://pith.science/paper/OPRGM36X"},"agent_actions":{"view_html":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V","download_json":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V.json","view_paper":"https://pith.science/paper/OPRGM36X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10929&json=true","fetch_graph":"https://pith.science/api/pith-number/OPRGM36XGYZ4BYWSOBHVGDX74V/graph.json","fetch_events":"https://pith.science/api/pith-number/OPRGM36XGYZ4BYWSOBHVGDX74V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V/action/storage_attestation","attest_author":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V/action/author_attestation","sign_citation":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V/action/citation_signature","submit_replication":"https://pith.science/pith/OPRGM36XGYZ4BYWSOBHVGDX74V/action/replication_record"}},"created_at":"2026-07-05T05:23:08.465450+00:00","updated_at":"2026-07-05T05:23:08.465450+00:00"}