{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:H56YQ2JG5SRVQBVTEAUEMP6XMP","short_pith_number":"pith:H56YQ2JG","schema_version":"1.0","canonical_sha256":"3f7d886926eca35806b32028463fd763c6f71ee140de4fe1fc9c62ec291deffb","source":{"kind":"arxiv","id":"1611.02839","version":1},"attestation_state":"computed","paper":{"title":"Old Content and Modern Tools - Searching Named Entities in a Finnish OCRed Historical Newspaper Collection 1771-1910","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eetu M\\\"akel\\\"a, Juha Kuokkala, Kimmo Kettunen, Laura L\\\"ofberg, Teemu Ruokolainen","submitted_at":"2016-11-09T07:37:28Z","abstract_excerpt":"Named Entity Recognition (NER), search, classification and tagging of names and name like frequent informational elements in texts, has become a standard information extraction procedure for textual data. NER has been applied to many types of texts and different types of entities: newspapers, fiction, historical records, persons, locations, chemical compounds, protein families, animals etc. In general a NER system's performance is genre and domain dependent and also used entity categories vary (Nadeau and Sekine, 2007). The most general set of named entities is usually some version of three pa"},"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":"1611.02839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-09T07:37:28Z","cross_cats_sorted":[],"title_canon_sha256":"b7760e6782bf95d782c35f41024fdcc7446ef46800a8953ab679bdfbf4eab12f","abstract_canon_sha256":"6cf71b7b9846863543203194c4f0f4113e0fac958748f120f3c57b53758fc39d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:43.473805Z","signature_b64":"CtFbidkMNGc4NjPVn9G1JYwNQlhVwShORO2YanA1KGWBAlrfnLya4rJ4L6JCzavRMsxjqd/WqQwaulEu4xt9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f7d886926eca35806b32028463fd763c6f71ee140de4fe1fc9c62ec291deffb","last_reissued_at":"2026-05-18T00:59:43.472989Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:43.472989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Old Content and Modern Tools - Searching Named Entities in a Finnish OCRed Historical Newspaper Collection 1771-1910","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eetu M\\\"akel\\\"a, Juha Kuokkala, Kimmo Kettunen, Laura L\\\"ofberg, Teemu Ruokolainen","submitted_at":"2016-11-09T07:37:28Z","abstract_excerpt":"Named Entity Recognition (NER), search, classification and tagging of names and name like frequent informational elements in texts, has become a standard information extraction procedure for textual data. NER has been applied to many types of texts and different types of entities: newspapers, fiction, historical records, persons, locations, chemical compounds, protein families, animals etc. In general a NER system's performance is genre and domain dependent and also used entity categories vary (Nadeau and Sekine, 2007). The most general set of named entities is usually some version of three pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02839","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":"1611.02839","created_at":"2026-05-18T00:59:43.473112+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02839v1","created_at":"2026-05-18T00:59:43.473112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02839","created_at":"2026-05-18T00:59:43.473112+00:00"},{"alias_kind":"pith_short_12","alias_value":"H56YQ2JG5SRV","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"H56YQ2JG5SRVQBVT","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"H56YQ2JG","created_at":"2026-05-18T12:30:19.053100+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/H56YQ2JG5SRVQBVTEAUEMP6XMP","json":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP.json","graph_json":"https://pith.science/api/pith-number/H56YQ2JG5SRVQBVTEAUEMP6XMP/graph.json","events_json":"https://pith.science/api/pith-number/H56YQ2JG5SRVQBVTEAUEMP6XMP/events.json","paper":"https://pith.science/paper/H56YQ2JG"},"agent_actions":{"view_html":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP","download_json":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP.json","view_paper":"https://pith.science/paper/H56YQ2JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02839&json=true","fetch_graph":"https://pith.science/api/pith-number/H56YQ2JG5SRVQBVTEAUEMP6XMP/graph.json","fetch_events":"https://pith.science/api/pith-number/H56YQ2JG5SRVQBVTEAUEMP6XMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP/action/storage_attestation","attest_author":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP/action/author_attestation","sign_citation":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP/action/citation_signature","submit_replication":"https://pith.science/pith/H56YQ2JG5SRVQBVTEAUEMP6XMP/action/replication_record"}},"created_at":"2026-05-18T00:59:43.473112+00:00","updated_at":"2026-05-18T00:59:43.473112+00:00"}