{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:O5WO5TQD4FQVHZZCKX3TFIBWGN","short_pith_number":"pith:O5WO5TQD","canonical_record":{"source":{"id":"1308.0661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-08-03T05:57:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"48aa0a04c1da376e5c258f5407242d98f3436b68df0514a8c44f2db0ecd9a9e6","abstract_canon_sha256":"e70ea01c8a7ec105cc885143c4db741b030eb197efd41a4842b24d537b5653ea"},"schema_version":"1.0"},"canonical_sha256":"776ceece03e16153e72255f732a0363360bda16e929f8af1703b44a444aa5c85","source":{"kind":"arxiv","id":"1308.0661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1308.0661","created_at":"2026-05-18T03:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"1308.0661v1","created_at":"2026-05-18T03:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1308.0661","created_at":"2026-05-18T03:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"O5WO5TQD4FQV","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"O5WO5TQD4FQVHZZC","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"O5WO5TQD","created_at":"2026-05-18T12:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:O5WO5TQD4FQVHZZCKX3TFIBWGN","target":"record","payload":{"canonical_record":{"source":{"id":"1308.0661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-08-03T05:57:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"48aa0a04c1da376e5c258f5407242d98f3436b68df0514a8c44f2db0ecd9a9e6","abstract_canon_sha256":"e70ea01c8a7ec105cc885143c4db741b030eb197efd41a4842b24d537b5653ea"},"schema_version":"1.0"},"canonical_sha256":"776ceece03e16153e72255f732a0363360bda16e929f8af1703b44a444aa5c85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:06:13.022610Z","signature_b64":"p3loWJmmp/W0qkCTBa+TfRyoTYXl52zlvPuMPsGda8DlSAnw2d+YUVw+iFJdE07IX9dT6f7YIAuqK4Z1bO/3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"776ceece03e16153e72255f732a0363360bda16e929f8af1703b44a444aa5c85","last_reissued_at":"2026-05-18T03:06:13.022101Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:06:13.022101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1308.0661","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":"2026-05-18T03:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqBreArjX5dHUvRZ4hiaS/yjrCN0SXjgnBJTIxwekV6xT8zydx9J9Q2wOqSVL7s3UEVvVc8jUYyV268fJSNUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:49:23.090451Z"},"content_sha256":"01c25676ae841c6222f4afef0b9fbf39d06239294415b38f726bdfdd940330bd","schema_version":"1.0","event_id":"sha256:01c25676ae841c6222f4afef0b9fbf39d06239294415b38f726bdfdd940330bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:O5WO5TQD4FQVHZZCKX3TFIBWGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison of Named Entity Recognition Tools Applied to Biographical Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Samet Atda\\u{g}, Vincent Labatut","submitted_at":"2013-08-03T05:57:48Z","abstract_excerpt":"Named entity recognition (NER) is a popular domain of natural language processing. For this reason, many tools exist to perform this task. Amongst other points, they differ in the processing method they rely upon, the entity types they can detect, the nature of the text they can handle, and their input/output formats. This makes it difficult for a user to select an appropriate NER tool for a specific situation. In this article, we try to answer this question in the context of biographic texts. For this matter, we first constitute a new corpus by annotating Wikipedia articles. We then select pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1308.0661","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yyw9YKHOgfDi7S2RV6UYCZIQ7DWbmtd4GL6Fwbez6SY/SaVHHoFnj9UAxIJs1yMcWSAzxeUGfBtxABffzeL7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:49:23.090815Z"},"content_sha256":"b0479e64365a93af72d3ad77c156e49651af98886d574bb26f6c7765b627ef89","schema_version":"1.0","event_id":"sha256:b0479e64365a93af72d3ad77c156e49651af98886d574bb26f6c7765b627ef89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN/bundle.json","state_url":"https://pith.science/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN/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":"2026-05-30T12:49:23Z","links":{"resolver":"https://pith.science/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN","bundle":"https://pith.science/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN/bundle.json","state":"https://pith.science/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5WO5TQD4FQVHZZCKX3TFIBWGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:O5WO5TQD4FQVHZZCKX3TFIBWGN","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":"e70ea01c8a7ec105cc885143c4db741b030eb197efd41a4842b24d537b5653ea","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-08-03T05:57:48Z","title_canon_sha256":"48aa0a04c1da376e5c258f5407242d98f3436b68df0514a8c44f2db0ecd9a9e6"},"schema_version":"1.0","source":{"id":"1308.0661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1308.0661","created_at":"2026-05-18T03:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"1308.0661v1","created_at":"2026-05-18T03:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1308.0661","created_at":"2026-05-18T03:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"O5WO5TQD4FQV","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"O5WO5TQD4FQVHZZC","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"O5WO5TQD","created_at":"2026-05-18T12:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:b0479e64365a93af72d3ad77c156e49651af98886d574bb26f6c7765b627ef89","target":"graph","created_at":"2026-05-18T03:06:13Z","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"},"paper":{"abstract_excerpt":"Named entity recognition (NER) is a popular domain of natural language processing. For this reason, many tools exist to perform this task. Amongst other points, they differ in the processing method they rely upon, the entity types they can detect, the nature of the text they can handle, and their input/output formats. This makes it difficult for a user to select an appropriate NER tool for a specific situation. In this article, we try to answer this question in the context of biographic texts. For this matter, we first constitute a new corpus by annotating Wikipedia articles. We then select pu","authors_text":"Samet Atda\\u{g}, Vincent Labatut","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-08-03T05:57:48Z","title":"A Comparison of Named Entity Recognition Tools Applied to Biographical Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1308.0661","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":"sha256:01c25676ae841c6222f4afef0b9fbf39d06239294415b38f726bdfdd940330bd","target":"record","created_at":"2026-05-18T03:06:13Z","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":"e70ea01c8a7ec105cc885143c4db741b030eb197efd41a4842b24d537b5653ea","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-08-03T05:57:48Z","title_canon_sha256":"48aa0a04c1da376e5c258f5407242d98f3436b68df0514a8c44f2db0ecd9a9e6"},"schema_version":"1.0","source":{"id":"1308.0661","kind":"arxiv","version":1}},"canonical_sha256":"776ceece03e16153e72255f732a0363360bda16e929f8af1703b44a444aa5c85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"776ceece03e16153e72255f732a0363360bda16e929f8af1703b44a444aa5c85","first_computed_at":"2026-05-18T03:06:13.022101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:06:13.022101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3loWJmmp/W0qkCTBa+TfRyoTYXl52zlvPuMPsGda8DlSAnw2d+YUVw+iFJdE07IX9dT6f7YIAuqK4Z1bO/3Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T03:06:13.022610Z","signed_message":"canonical_sha256_bytes"},"source_id":"1308.0661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01c25676ae841c6222f4afef0b9fbf39d06239294415b38f726bdfdd940330bd","sha256:b0479e64365a93af72d3ad77c156e49651af98886d574bb26f6c7765b627ef89"],"state_sha256":"d4bdd5a72254a6abf6611c6a96cc53e10cecea8cb237ea948197f751d434895a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dP3E4cCqQJF0brgnBkAlBxr7JUJ+GpwzOkVeILCN/3XHTgttTue57f0DPpCvhGJseXgqeRCOpeFH32Ce3+SyAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:49:23.092836Z","bundle_sha256":"688a741657c5085d32f9d86befdc23de22b6e1589eee29c7349749507359f158"}}