{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OMIO357EX3KK4FXLMQUWWUE4YS","short_pith_number":"pith:OMIO357E","schema_version":"1.0","canonical_sha256":"7310edf7e4bed4ae16eb64296b509cc499a511ba8a7b655e514c3543f7cdb834","source":{"kind":"arxiv","id":"1702.03519","version":1},"attestation_state":"computed","paper":{"title":"A Technical Report: Entity Extraction using Both Character-based and Token-based Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dong Deng, Kotagiri Ramamohanarao, Rui Zhang, Zeyi Wen","submitted_at":"2017-02-12T12:46:40Z","abstract_excerpt":"Entity extraction is fundamental to many text mining tasks such as organisation name recognition. A popular approach to entity extraction is based on matching sub-string candidates in a document against a dictionary of entities. To handle spelling errors and name variations of entities, usually the matching is approximate and edit or Jaccard distance is used to measure dissimilarity between sub-string candidates and the entities. For approximate entity extraction from free text, existing work considers solely character-based or solely token-based similarity and hence cannot simultaneously deal"},"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":"1702.03519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-02-12T12:46:40Z","cross_cats_sorted":[],"title_canon_sha256":"d9a9fdbb0b4f3a02c51f1194e74a4285edba974df5a3fba1fcfbc422ad00ba70","abstract_canon_sha256":"be5883f7afd4e66fb69071e79ff5dd392023a290a671b9db2f0bd49a0132bead"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:53.606410Z","signature_b64":"oQ1bRACv/DIQ5YomXRqILu9uCEiid7PQSABKNBlo1Exg/sY8Jn4Yv5E+Ix23/PEkYrIMs8lcgRPnR0N+79BBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7310edf7e4bed4ae16eb64296b509cc499a511ba8a7b655e514c3543f7cdb834","last_reissued_at":"2026-05-18T00:50:53.605866Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:53.605866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Technical Report: Entity Extraction using Both Character-based and Token-based Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Dong Deng, Kotagiri Ramamohanarao, Rui Zhang, Zeyi Wen","submitted_at":"2017-02-12T12:46:40Z","abstract_excerpt":"Entity extraction is fundamental to many text mining tasks such as organisation name recognition. A popular approach to entity extraction is based on matching sub-string candidates in a document against a dictionary of entities. To handle spelling errors and name variations of entities, usually the matching is approximate and edit or Jaccard distance is used to measure dissimilarity between sub-string candidates and the entities. For approximate entity extraction from free text, existing work considers solely character-based or solely token-based similarity and hence cannot simultaneously deal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03519","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1702.03519","created_at":"2026-05-18T00:50:53.605943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.03519v1","created_at":"2026-05-18T00:50:53.605943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03519","created_at":"2026-05-18T00:50:53.605943+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMIO357EX3KK","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMIO357EX3KK4FXL","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMIO357E","created_at":"2026-05-18T12:31:34.259226+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/OMIO357EX3KK4FXLMQUWWUE4YS","json":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS.json","graph_json":"https://pith.science/api/pith-number/OMIO357EX3KK4FXLMQUWWUE4YS/graph.json","events_json":"https://pith.science/api/pith-number/OMIO357EX3KK4FXLMQUWWUE4YS/events.json","paper":"https://pith.science/paper/OMIO357E"},"agent_actions":{"view_html":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS","download_json":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS.json","view_paper":"https://pith.science/paper/OMIO357E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.03519&json=true","fetch_graph":"https://pith.science/api/pith-number/OMIO357EX3KK4FXLMQUWWUE4YS/graph.json","fetch_events":"https://pith.science/api/pith-number/OMIO357EX3KK4FXLMQUWWUE4YS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS/action/storage_attestation","attest_author":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS/action/author_attestation","sign_citation":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS/action/citation_signature","submit_replication":"https://pith.science/pith/OMIO357EX3KK4FXLMQUWWUE4YS/action/replication_record"}},"created_at":"2026-05-18T00:50:53.605943+00:00","updated_at":"2026-05-18T00:50:53.605943+00:00"}