{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M6Y55NZEUWZPCWOFTQSFGXRGAA","short_pith_number":"pith:M6Y55NZE","schema_version":"1.0","canonical_sha256":"67b1deb724a5b2f159c59c24535e26001e2dd768aa35e586df0dfa5f28354906","source":{"kind":"arxiv","id":"2211.08788","version":3},"attestation_state":"computed","paper":{"title":"CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jie Zhou, Yong Hu","submitted_at":"2022-11-16T09:25:42Z","abstract_excerpt":"In this paper, we present CSCD-NS, the first Chinese spelling check (CSC) dataset designed for native speakers, containing 40,000 samples from a Chinese social platform. Compared with existing CSC datasets aimed at Chinese learners, CSCD-NS is ten times larger in scale and exhibits a distinct error distribution, with a significantly higher proportion of word-level errors. To further enhance the data resource, we propose a novel method that simulates the input process through an input method, generating large-scale and high-quality pseudo data that closely resembles the actual error distributio"},"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":"2211.08788","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:25:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"066ba62f04a38978efbe5be82eefdeed9b93e895af494920f886cd3d0e7057e8","abstract_canon_sha256":"0c88881a99f1649ce5f14f932533016a19299bf9f6704f8c3ec5db2ead8f35b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:37.217476Z","signature_b64":"b+N74srmvkfDwpUkOeW9lpUDLzqlvJLXGaCE3cvcToT6VQB4gEkrchUYrrMeQHP80agVsLs0Zxs3IGbWnuF0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67b1deb724a5b2f159c59c24535e26001e2dd768aa35e586df0dfa5f28354906","last_reissued_at":"2026-07-05T08:21:37.216850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:37.216850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jie Zhou, Yong Hu","submitted_at":"2022-11-16T09:25:42Z","abstract_excerpt":"In this paper, we present CSCD-NS, the first Chinese spelling check (CSC) dataset designed for native speakers, containing 40,000 samples from a Chinese social platform. Compared with existing CSC datasets aimed at Chinese learners, CSCD-NS is ten times larger in scale and exhibits a distinct error distribution, with a significantly higher proportion of word-level errors. To further enhance the data resource, we propose a novel method that simulates the input process through an input method, generating large-scale and high-quality pseudo data that closely resembles the actual error distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08788","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/2211.08788/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":"2211.08788","created_at":"2026-07-05T08:21:37.216905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08788v3","created_at":"2026-07-05T08:21:37.216905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08788","created_at":"2026-07-05T08:21:37.216905+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6Y55NZEUWZP","created_at":"2026-07-05T08:21:37.216905+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6Y55NZEUWZPCWOF","created_at":"2026-07-05T08:21:37.216905+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6Y55NZE","created_at":"2026-07-05T08:21:37.216905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09082","citing_title":"CEC-Zero: Chinese Error Correction Solution Based on LLM","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA","json":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA.json","graph_json":"https://pith.science/api/pith-number/M6Y55NZEUWZPCWOFTQSFGXRGAA/graph.json","events_json":"https://pith.science/api/pith-number/M6Y55NZEUWZPCWOFTQSFGXRGAA/events.json","paper":"https://pith.science/paper/M6Y55NZE"},"agent_actions":{"view_html":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA","download_json":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA.json","view_paper":"https://pith.science/paper/M6Y55NZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08788&json=true","fetch_graph":"https://pith.science/api/pith-number/M6Y55NZEUWZPCWOFTQSFGXRGAA/graph.json","fetch_events":"https://pith.science/api/pith-number/M6Y55NZEUWZPCWOFTQSFGXRGAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA/action/storage_attestation","attest_author":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA/action/author_attestation","sign_citation":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA/action/citation_signature","submit_replication":"https://pith.science/pith/M6Y55NZEUWZPCWOFTQSFGXRGAA/action/replication_record"}},"created_at":"2026-07-05T08:21:37.216905+00:00","updated_at":"2026-07-05T08:21:37.216905+00:00"}