{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3HAV3KMUHWRDUNI46ZA6AXHIKY","short_pith_number":"pith:3HAV3KMU","canonical_record":{"source":{"id":"2302.10204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-20T12:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"0e3ce6acd98d1542d420d81a282713fc23195bd6e4238639fa880caf1ea721d6","abstract_canon_sha256":"e3bdd5bd29e19b0c383761d62942446d8cb530a90379dca33ab53954e0636d7c"},"schema_version":"1.0"},"canonical_sha256":"d9c15da9943da23a351cf641e05ce85615a54d80622f3e0de283fbc809169d20","source":{"kind":"arxiv","id":"2302.10204","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10204","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10204v1","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10204","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"pith_short_12","alias_value":"3HAV3KMUHWRD","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"pith_short_16","alias_value":"3HAV3KMUHWRDUNI4","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"pith_short_8","alias_value":"3HAV3KMU","created_at":"2026-07-05T05:43:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3HAV3KMUHWRDUNI46ZA6AXHIKY","target":"record","payload":{"canonical_record":{"source":{"id":"2302.10204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-20T12:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"0e3ce6acd98d1542d420d81a282713fc23195bd6e4238639fa880caf1ea721d6","abstract_canon_sha256":"e3bdd5bd29e19b0c383761d62942446d8cb530a90379dca33ab53954e0636d7c"},"schema_version":"1.0"},"canonical_sha256":"d9c15da9943da23a351cf641e05ce85615a54d80622f3e0de283fbc809169d20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:36.540224Z","signature_b64":"Fgt2U7/rMucsOrGMk0zJAs1TgUZUZWQnBNCqwQsv4kiG/OtZC+TXXLmTen9Bd+Oi3YK62ZpxdBYz4u7WjikBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9c15da9943da23a351cf641e05ce85615a54d80622f3e0de283fbc809169d20","last_reissued_at":"2026-07-05T05:43:36.539774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:36.539774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.10204","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":"2026-07-05T05:43:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P3D6NFftQlsGGfZrmSDfG7PZMDEZWvjyHVbPtlT4KRJX0b48kh+StV0+dG5nSQUqRsvli5OHkHY78FaBQfP4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:46:59.104548Z"},"content_sha256":"9767e61df73d59adb627d2ea0eefaf78fbb7745305001966d2c065c1cb003ba7","schema_version":"1.0","event_id":"sha256:9767e61df73d59adb627d2ea0eefaf78fbb7745305001966d2c065c1cb003ba7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3HAV3KMUHWRDUNI46ZA6AXHIKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Benchmark of Nested Named Entity Recognition Approaches in Historical Structured Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bertrand Dum\\'enieu (CRH), Edwin Carlinet (LRDE), J Chazalon (LRDE), Nathalie Abadie (LaSTIG), Solenn Tual (LaSTIG)","submitted_at":"2023-02-20T12:47:38Z","abstract_excerpt":"Named Entity Recognition (NER) is a key step in the creation of structured data from digitised historical documents. Traditional NER approaches deal with flat named entities, whereas entities often are nested. For example, a postal address might contain a street name and a number. This work compares three nested NER approaches, including two state-of-the-art approaches using Transformer-based architectures. We introduce a new Transformer-based approach based on joint labelling and semantic weighting of errors, evaluated on a collection of 19 th-century Paris trade directories. We evaluate appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10204","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/2302.10204/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":"2026-07-05T05:43:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/cdWl+vl8WtoCoT6uEr6K5DVsxVty1nEkb3Ya6G8m5K4em9ev+nPV0o6L2XEq3PXXrqSYml88dSov4AhM7zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:46:59.105080Z"},"content_sha256":"384c42d95934211211bd6a9090a9c530fa3fe450a9a20792bf920231b10b29e4","schema_version":"1.0","event_id":"sha256:384c42d95934211211bd6a9090a9c530fa3fe450a9a20792bf920231b10b29e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY/bundle.json","state_url":"https://pith.science/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY/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":"2026-08-08T19:46:59Z","links":{"resolver":"https://pith.science/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY","bundle":"https://pith.science/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY/bundle.json","state":"https://pith.science/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HAV3KMUHWRDUNI46ZA6AXHIKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3HAV3KMUHWRDUNI46ZA6AXHIKY","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":"e3bdd5bd29e19b0c383761d62942446d8cb530a90379dca33ab53954e0636d7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-20T12:47:38Z","title_canon_sha256":"0e3ce6acd98d1542d420d81a282713fc23195bd6e4238639fa880caf1ea721d6"},"schema_version":"1.0","source":{"id":"2302.10204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10204","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10204v1","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10204","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"pith_short_12","alias_value":"3HAV3KMUHWRD","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"pith_short_16","alias_value":"3HAV3KMUHWRDUNI4","created_at":"2026-07-05T05:43:36Z"},{"alias_kind":"pith_short_8","alias_value":"3HAV3KMU","created_at":"2026-07-05T05:43:36Z"}],"graph_snapshots":[{"event_id":"sha256:384c42d95934211211bd6a9090a9c530fa3fe450a9a20792bf920231b10b29e4","target":"graph","created_at":"2026-07-05T05:43:36Z","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/2302.10204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named Entity Recognition (NER) is a key step in the creation of structured data from digitised historical documents. Traditional NER approaches deal with flat named entities, whereas entities often are nested. For example, a postal address might contain a street name and a number. This work compares three nested NER approaches, including two state-of-the-art approaches using Transformer-based architectures. We introduce a new Transformer-based approach based on joint labelling and semantic weighting of errors, evaluated on a collection of 19 th-century Paris trade directories. We evaluate appr","authors_text":"Bertrand Dum\\'enieu (CRH), Edwin Carlinet (LRDE), J Chazalon (LRDE), Nathalie Abadie (LaSTIG), Solenn Tual (LaSTIG)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-20T12:47:38Z","title":"A Benchmark of Nested Named Entity Recognition Approaches in Historical Structured Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10204","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":"sha256:9767e61df73d59adb627d2ea0eefaf78fbb7745305001966d2c065c1cb003ba7","target":"record","created_at":"2026-07-05T05:43:36Z","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":"e3bdd5bd29e19b0c383761d62942446d8cb530a90379dca33ab53954e0636d7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-20T12:47:38Z","title_canon_sha256":"0e3ce6acd98d1542d420d81a282713fc23195bd6e4238639fa880caf1ea721d6"},"schema_version":"1.0","source":{"id":"2302.10204","kind":"arxiv","version":1}},"canonical_sha256":"d9c15da9943da23a351cf641e05ce85615a54d80622f3e0de283fbc809169d20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9c15da9943da23a351cf641e05ce85615a54d80622f3e0de283fbc809169d20","first_computed_at":"2026-07-05T05:43:36.539774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:36.539774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fgt2U7/rMucsOrGMk0zJAs1TgUZUZWQnBNCqwQsv4kiG/OtZC+TXXLmTen9Bd+Oi3YK62ZpxdBYz4u7WjikBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:36.540224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9767e61df73d59adb627d2ea0eefaf78fbb7745305001966d2c065c1cb003ba7","sha256:384c42d95934211211bd6a9090a9c530fa3fe450a9a20792bf920231b10b29e4"],"state_sha256":"e22c54d552124776be1838b0e4e011e573b42348357dadea04d0a9e50157b3be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ROPeu+l+EXlfMN25FPwGR/4zAYh/NXhV1CBRtwurpaNN1DZsNXUmEQccYLLRykpKTaytKkDR+5rVuqwwnhsDBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:46:59.109389Z","bundle_sha256":"fb08dc06d7ce81883b846849ff0661bb2a976323f3eae711af2ec199550f9294"}}