{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FDOTVHI6SSGC3WX7W3M7HYYSJA","short_pith_number":"pith:FDOTVHI6","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"},"canonical_sha256":"28dd3a9d1e948c2ddaffb6d9f3e312482381bdf5a61d1515f7f26b0660784170","source":{"kind":"arxiv","id":"2108.13700","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FDOTVHI6SSGC3WX7W3M7HYYSJA","target":"record","payload":{"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"},"canonical_sha256":"28dd3a9d1e948c2ddaffb6d9f3e312482381bdf5a61d1515f7f26b0660784170","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"},"source_kind":"arxiv","source_id":"2108.13700","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:37:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S/WbkNtEVv65Kat5DgwaRDxUebvDRFeOrUZUJ2p2Y7XVRswkSuZrmsCmxtgytvUaLfPhhtVhwoWQ51WuZmgsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:08:11.551579Z"},"content_sha256":"187cea289cf03adf28c13a9fad7d428a082322fa7786f2fcc2c2572ea7e0142f","schema_version":"1.0","event_id":"sha256:187cea289cf03adf28c13a9fad7d428a082322fa7786f2fcc2c2572ea7e0142f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FDOTVHI6SSGC3WX7W3M7HYYSJA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:37:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmjuusOb4tq0BxMWivHdIx/7O7zAibiFbeU9VKGefGvfZfaZknW12l1kpmqkNOZCrAS0QG6udwhrJB1oKHJ9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:08:11.552160Z"},"content_sha256":"53dc5cb52cad433e4f3fec528269dcf5f53fb71ae52999a80adc1f5b227e7834","schema_version":"1.0","event_id":"sha256:53dc5cb52cad433e4f3fec528269dcf5f53fb71ae52999a80adc1f5b227e7834"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/bundle.json","state_url":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T10:08:11Z","links":{"resolver":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA","bundle":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/bundle.json","state":"https://pith.science/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDOTVHI6SSGC3WX7W3M7HYYSJA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UK5GcnMG6LeIowlceMKeTT9dTFZQO7GlvYize7BJADfZBULZX7CtqJEC7EsgbIaCwizBiPIwt4WUb3TpidjKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:08:11.555421Z","bundle_sha256":"88c7268810978cfc49ba5ae670faeb6a7a9aebcd5c9a7263ade546fa799b8c86"}}