{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M6Y55NZEUWZPCWOFTQSFGXRGAA","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":"0c88881a99f1649ce5f14f932533016a19299bf9f6704f8c3ec5db2ead8f35b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:25:42Z","title_canon_sha256":"066ba62f04a38978efbe5be82eefdeed9b93e895af494920f886cd3d0e7057e8"},"schema_version":"1.0","source":{"id":"2211.08788","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08788","created_at":"2026-07-05T08:21:37Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08788v3","created_at":"2026-07-05T08:21:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08788","created_at":"2026-07-05T08:21:37Z"},{"alias_kind":"pith_short_12","alias_value":"M6Y55NZEUWZP","created_at":"2026-07-05T08:21:37Z"},{"alias_kind":"pith_short_16","alias_value":"M6Y55NZEUWZPCWOF","created_at":"2026-07-05T08:21:37Z"},{"alias_kind":"pith_short_8","alias_value":"M6Y55NZE","created_at":"2026-07-05T08:21:37Z"}],"graph_snapshots":[{"event_id":"sha256:52dff30cf46dc4ff7707ad1c2d4788b838fed16629ab41689ed577077429ca79","target":"graph","created_at":"2026-07-05T08:21:37Z","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/2211.08788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fandong Meng, Jie Zhou, Yong Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:25:42Z","title":"CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08788","kind":"arxiv","version":3},"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":"sha256:4bfabcf33c0ae23b7747557f09e1eb936afde3ad668926fe5d93f828545884bd","target":"record","created_at":"2026-07-05T08:21:37Z","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":"0c88881a99f1649ce5f14f932533016a19299bf9f6704f8c3ec5db2ead8f35b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T09:25:42Z","title_canon_sha256":"066ba62f04a38978efbe5be82eefdeed9b93e895af494920f886cd3d0e7057e8"},"schema_version":"1.0","source":{"id":"2211.08788","kind":"arxiv","version":3}},"canonical_sha256":"67b1deb724a5b2f159c59c24535e26001e2dd768aa35e586df0dfa5f28354906","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67b1deb724a5b2f159c59c24535e26001e2dd768aa35e586df0dfa5f28354906","first_computed_at":"2026-07-05T08:21:37.216850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:37.216850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+N74srmvkfDwpUkOeW9lpUDLzqlvJLXGaCE3cvcToT6VQB4gEkrchUYrrMeQHP80agVsLs0Zxs3IGbWnuF0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:37.217476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08788","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bfabcf33c0ae23b7747557f09e1eb936afde3ad668926fe5d93f828545884bd","sha256:52dff30cf46dc4ff7707ad1c2d4788b838fed16629ab41689ed577077429ca79"],"state_sha256":"afc99f94c899db39ade67835ce7f8161fe6e42c2b1a37111e17fc1b7ea41f97e"}