{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FDOTVHI6SSGC3WX7W3M7HYYSJA","short_pith_number":"pith:FDOTVHI6","schema_version":"1.0","canonical_sha256":"28dd3a9d1e948c2ddaffb6d9f3e312482381bdf5a61d1515f7f26b0660784170","source":{"kind":"arxiv","id":"2108.13700","version":1},"attestation_state":"computed","paper":{"title":"TNNT: The Named Entity Recognition Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.SE"],"primary_cat":"cs.CL","authors_text":"Armin Haller, Kerry Taylor, Pouya G. Omran, Sandaru Seneviratne, Sergio J. Rodr\\'iguez M\\'endez, Xuecheng Zhang","submitted_at":"2021-08-31T09:24:16Z","abstract_excerpt":"Extraction of categorised named entities from text is a complex task given the availability of a variety of Named Entity Recognition (NER) models and the unstructured information encoded in different source document formats. Processing the documents to extract text, identifying suitable NER models for a task, and obtaining statistical information is important in data analysis to make informed decisions. This paper presents TNNT, a toolkit that automates the extraction of categorised named entities from unstructured information encoded in source documents, using diverse state-of-the-art Natural"},"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":"2108.13700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T09:24:16Z","cross_cats_sorted":["cs.AI","cs.IR","cs.SE"],"title_canon_sha256":"4d98198ccfcb5fce5eff20b096df5ac5def7f48e2ec4767b10103f948bf8943d","abstract_canon_sha256":"9df366b44253d090e30713f510503f0558c5ea04ad62fc8b81dde4d30ca5e96f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:45.501125Z","signature_b64":"KR1kTUYjCa91vm6JcRxnA234uWlPhGlSElsNGIqbCWPRIh/kfc3bG3tCWjyKyRU2RTrQZndxtLnvYJJLfAZMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28dd3a9d1e948c2ddaffb6d9f3e312482381bdf5a61d1515f7f26b0660784170","last_reissued_at":"2026-07-05T03:37:45.500681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:45.500681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TNNT: The Named Entity Recognition Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.SE"],"primary_cat":"cs.CL","authors_text":"Armin Haller, Kerry Taylor, Pouya G. Omran, Sandaru Seneviratne, Sergio J. Rodr\\'iguez M\\'endez, Xuecheng Zhang","submitted_at":"2021-08-31T09:24:16Z","abstract_excerpt":"Extraction of categorised named entities from text is a complex task given the availability of a variety of Named Entity Recognition (NER) models and the unstructured information encoded in different source document formats. Processing the documents to extract text, identifying suitable NER models for a task, and obtaining statistical information is important in data analysis to make informed decisions. This paper presents TNNT, a toolkit that automates the extraction of categorised named entities from unstructured information encoded in source documents, using diverse state-of-the-art Natural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13700","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.13700/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":"2108.13700","created_at":"2026-07-05T03:37:45.500739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.13700v1","created_at":"2026-07-05T03:37:45.500739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13700","created_at":"2026-07-05T03:37:45.500739+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDOTVHI6SSGC","created_at":"2026-07-05T03:37:45.500739+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDOTVHI6SSGC3WX7","created_at":"2026-07-05T03:37:45.500739+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDOTVHI6","created_at":"2026-07-05T03:37:45.500739+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/FDOTVHI6SSGC3WX7W3M7HYYSJA","json":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA.json","graph_json":"https://pith.science/api/pith-number/FDOTVHI6SSGC3WX7W3M7HYYSJA/graph.json","events_json":"https://pith.science/api/pith-number/FDOTVHI6SSGC3WX7W3M7HYYSJA/events.json","paper":"https://pith.science/paper/FDOTVHI6"},"agent_actions":{"view_html":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA","download_json":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA.json","view_paper":"https://pith.science/paper/FDOTVHI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.13700&json=true","fetch_graph":"https://pith.science/api/pith-number/FDOTVHI6SSGC3WX7W3M7HYYSJA/graph.json","fetch_events":"https://pith.science/api/pith-number/FDOTVHI6SSGC3WX7W3M7HYYSJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/action/storage_attestation","attest_author":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/action/author_attestation","sign_citation":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/action/citation_signature","submit_replication":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/action/replication_record"}},"created_at":"2026-07-05T03:37:45.500739+00:00","updated_at":"2026-07-05T03:37:45.500739+00:00"}