{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DGUA3OHTQCYBDUM64BE7H5PEUF","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":"744c46990ade40db94f7b3b82dc8aec808679965ec710a2fe4a0cd3df2a109d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-19T09:15:37Z","title_canon_sha256":"54e9f42f6506f25addf057b4b533d9880de5a5b1b05cbb703797907e4fa92097"},"schema_version":"1.0","source":{"id":"1710.07045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.07045","created_at":"2026-05-18T00:32:27Z"},{"alias_kind":"arxiv_version","alias_value":"1710.07045v1","created_at":"2026-05-18T00:32:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07045","created_at":"2026-05-18T00:32:27Z"},{"alias_kind":"pith_short_12","alias_value":"DGUA3OHTQCYB","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DGUA3OHTQCYBDUM6","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DGUA3OHT","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:c7eea4af5d075b9559896354a4a4390166536ae5b03a7689d20f1b5b50e43083","target":"graph","created_at":"2026-05-18T00:32:27Z","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"},"paper":{"abstract_excerpt":"We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. To tune the parameters of this model, we generate self-induced spelling error corpora. We perform our experiments for two languages. For English, we greatly outperform off-the-shelf spelling correction tools on a manually annot","authors_text":"Pieter Fivez, Simon \\v{S}uster, Walter Daelemans","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-19T09:15:37Z","title":"Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07045","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":"sha256:47822f66f0f236764060854f8ff69e8885a27089d27f45fb9ccd267962e5d6dd","target":"record","created_at":"2026-05-18T00:32:27Z","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":"744c46990ade40db94f7b3b82dc8aec808679965ec710a2fe4a0cd3df2a109d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-19T09:15:37Z","title_canon_sha256":"54e9f42f6506f25addf057b4b533d9880de5a5b1b05cbb703797907e4fa92097"},"schema_version":"1.0","source":{"id":"1710.07045","kind":"arxiv","version":1}},"canonical_sha256":"19a80db8f380b011d19ee049f3f5e4a1595c7a3e2e5ae57e6dd44c4949180ed0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19a80db8f380b011d19ee049f3f5e4a1595c7a3e2e5ae57e6dd44c4949180ed0","first_computed_at":"2026-05-18T00:32:27.223059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:27.223059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iwdi9XIs1B50oxxtKostyh3LUVADpiP16NwyHE3YHQJeECoSLpC32vyx3qWhUatOXYdFsu0d6/vCdL7sJ9wZCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:27.223663Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.07045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47822f66f0f236764060854f8ff69e8885a27089d27f45fb9ccd267962e5d6dd","sha256:c7eea4af5d075b9559896354a4a4390166536ae5b03a7689d20f1b5b50e43083"],"state_sha256":"bd434e669f8618dc90178fdd3abd607eb6d25c77061cb8282ed4b500a9f4e7ea"}