{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FDOTVHI6SSGC3WX7W3M7HYYSJA","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":"9df366b44253d090e30713f510503f0558c5ea04ad62fc8b81dde4d30ca5e96f","cross_cats_sorted":["cs.AI","cs.IR","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T09:24:16Z","title_canon_sha256":"4d98198ccfcb5fce5eff20b096df5ac5def7f48e2ec4767b10103f948bf8943d"},"schema_version":"1.0","source":{"id":"2108.13700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13700","created_at":"2026-07-05T03:37:45Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13700v1","created_at":"2026-07-05T03:37:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13700","created_at":"2026-07-05T03:37:45Z"},{"alias_kind":"pith_short_12","alias_value":"FDOTVHI6SSGC","created_at":"2026-07-05T03:37:45Z"},{"alias_kind":"pith_short_16","alias_value":"FDOTVHI6SSGC3WX7","created_at":"2026-07-05T03:37:45Z"},{"alias_kind":"pith_short_8","alias_value":"FDOTVHI6","created_at":"2026-07-05T03:37:45Z"}],"graph_snapshots":[{"event_id":"sha256:53dc5cb52cad433e4f3fec528269dcf5f53fb71ae52999a80adc1f5b227e7834","target":"graph","created_at":"2026-07-05T03:37:45Z","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/2108.13700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Armin Haller, Kerry Taylor, Pouya G. Omran, Sandaru Seneviratne, Sergio J. Rodr\\'iguez M\\'endez, Xuecheng Zhang","cross_cats":["cs.AI","cs.IR","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T09:24:16Z","title":"TNNT: The Named Entity Recognition Toolkit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13700","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":"sha256:187cea289cf03adf28c13a9fad7d428a082322fa7786f2fcc2c2572ea7e0142f","target":"record","created_at":"2026-07-05T03:37:45Z","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":"9df366b44253d090e30713f510503f0558c5ea04ad62fc8b81dde4d30ca5e96f","cross_cats_sorted":["cs.AI","cs.IR","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T09:24:16Z","title_canon_sha256":"4d98198ccfcb5fce5eff20b096df5ac5def7f48e2ec4767b10103f948bf8943d"},"schema_version":"1.0","source":{"id":"2108.13700","kind":"arxiv","version":1}},"canonical_sha256":"28dd3a9d1e948c2ddaffb6d9f3e312482381bdf5a61d1515f7f26b0660784170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28dd3a9d1e948c2ddaffb6d9f3e312482381bdf5a61d1515f7f26b0660784170","first_computed_at":"2026-07-05T03:37:45.500681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:45.500681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KR1kTUYjCa91vm6JcRxnA234uWlPhGlSElsNGIqbCWPRIh/kfc3bG3tCWjyKyRU2RTrQZndxtLnvYJJLfAZMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:45.501125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.13700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:187cea289cf03adf28c13a9fad7d428a082322fa7786f2fcc2c2572ea7e0142f","sha256:53dc5cb52cad433e4f3fec528269dcf5f53fb71ae52999a80adc1f5b227e7834"],"state_sha256":"8321f8e152dbe8c838f1e69129f44c5b42a9251871c13ef1e35a8f8a09a63f86"}