{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IH4RMJF6EY44JEMUMU433GL25Z","short_pith_number":"pith:IH4RMJF6","schema_version":"1.0","canonical_sha256":"41f91624be2639c491946539bd997aee5fe2e72cd7f20ba077b8aceeaf18de68","source":{"kind":"arxiv","id":"2506.02872","version":1},"attestation_state":"computed","paper":{"title":"Token and Span Classification for Entity Recognition in French Historical Encyclopedias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"H\\'edi Zeghidi, Ludovic Moncla","submitted_at":"2025-06-03T13:37:44Z","abstract_excerpt":"Named Entity Recognition (NER) in historical texts presents unique challenges due to non-standardized language, archaic orthography, and nested or overlapping entities. This study benchmarks a diverse set of NER approaches, ranging from classical Conditional Random Fields (CRFs) and spaCy-based models to transformer-based architectures such as CamemBERT and sequence-labeling models like Flair. Experiments are conducted on the GeoEDdA dataset, a richly annotated corpus derived from 18th-century French encyclopedias. We propose framing NER as both token-level and span-level classification to acc"},"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":"2506.02872","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T13:37:44Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d6047443b6cac620003936c572f977daf091fac14cfc66b2c1a04ad6b65c6efb","abstract_canon_sha256":"45fff4e53406654e8e7dc2ac3c0813336a5031f9ea16e27448ee67f763dbbd00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:10.797195Z","signature_b64":"1IZQwXDSvn4G9Y0acKVOHT6lmQ0GvMmy5SD1RQzTqsodjwif+XJ3nbQGJyuAzU9HYE6YEtwqNwOg8Vly+hNSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41f91624be2639c491946539bd997aee5fe2e72cd7f20ba077b8aceeaf18de68","last_reissued_at":"2026-07-05T11:15:10.796416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:10.796416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Token and Span Classification for Entity Recognition in French Historical Encyclopedias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"H\\'edi Zeghidi, Ludovic Moncla","submitted_at":"2025-06-03T13:37:44Z","abstract_excerpt":"Named Entity Recognition (NER) in historical texts presents unique challenges due to non-standardized language, archaic orthography, and nested or overlapping entities. This study benchmarks a diverse set of NER approaches, ranging from classical Conditional Random Fields (CRFs) and spaCy-based models to transformer-based architectures such as CamemBERT and sequence-labeling models like Flair. Experiments are conducted on the GeoEDdA dataset, a richly annotated corpus derived from 18th-century French encyclopedias. We propose framing NER as both token-level and span-level classification to acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02872","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/2506.02872/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":"2506.02872","created_at":"2026-07-05T11:15:10.796557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02872v1","created_at":"2026-07-05T11:15:10.796557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02872","created_at":"2026-07-05T11:15:10.796557+00:00"},{"alias_kind":"pith_short_12","alias_value":"IH4RMJF6EY44","created_at":"2026-07-05T11:15:10.796557+00:00"},{"alias_kind":"pith_short_16","alias_value":"IH4RMJF6EY44JEMU","created_at":"2026-07-05T11:15:10.796557+00:00"},{"alias_kind":"pith_short_8","alias_value":"IH4RMJF6","created_at":"2026-07-05T11:15:10.796557+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/IH4RMJF6EY44JEMUMU433GL25Z","json":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z.json","graph_json":"https://pith.science/api/pith-number/IH4RMJF6EY44JEMUMU433GL25Z/graph.json","events_json":"https://pith.science/api/pith-number/IH4RMJF6EY44JEMUMU433GL25Z/events.json","paper":"https://pith.science/paper/IH4RMJF6"},"agent_actions":{"view_html":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z","download_json":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z.json","view_paper":"https://pith.science/paper/IH4RMJF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02872&json=true","fetch_graph":"https://pith.science/api/pith-number/IH4RMJF6EY44JEMUMU433GL25Z/graph.json","fetch_events":"https://pith.science/api/pith-number/IH4RMJF6EY44JEMUMU433GL25Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z/action/storage_attestation","attest_author":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z/action/author_attestation","sign_citation":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z/action/citation_signature","submit_replication":"https://pith.science/pith/IH4RMJF6EY44JEMUMU433GL25Z/action/replication_record"}},"created_at":"2026-07-05T11:15:10.796557+00:00","updated_at":"2026-07-05T11:15:10.796557+00:00"}