{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UZDSM4W5OK6Z7RNTDMBXZIVXRL","short_pith_number":"pith:UZDSM4W5","schema_version":"1.0","canonical_sha256":"a6472672dd72bd9fc5b31b037ca2b78ac518c305dd8675e2852305c9158ea2c2","source":{"kind":"arxiv","id":"2309.10770","version":1},"attestation_state":"computed","paper":{"title":"FRASIMED: a Clinical French Annotated Resource Produced through Crosslingual BERT-Based Annotation Projection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Lovis, Christophe Gaudet-Blavignac, Jamil Zaghir, Jean-Philippe Goldman, Mina Bjelogrlic, Souka\\\"ina Aananou","submitted_at":"2023-09-19T17:17:28Z","abstract_excerpt":"Natural language processing (NLP) applications such as named entity recognition (NER) for low-resource corpora do not benefit from recent advances in the development of large language models (LLMs) where there is still a need for larger annotated datasets. This research article introduces a methodology for generating translated versions of annotated datasets through crosslingual annotation projection. Leveraging a language agnostic BERT-based approach, it is an efficient solution to increase low-resource corpora with few human efforts and by only using already available open data resources. Qu"},"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":"2309.10770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T17:17:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb8e8b54efafb838462cf9855490273d06a4ce2d7ca2646579195709aad28d15","abstract_canon_sha256":"537309e5a01cdb976745028be0a3625ffe7de1f36ec7134e966fb30a9b60235a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:37.752785Z","signature_b64":"t/j52O0vVurxWzliznJd+/z/UT8cb8EZbYiFO22RJRtmP73H2dTcMOmjGw6dAvguoCLX71NtlpDOQig7VJ+fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6472672dd72bd9fc5b31b037ca2b78ac518c305dd8675e2852305c9158ea2c2","last_reissued_at":"2026-07-05T11:39:37.752202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:37.752202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRASIMED: a Clinical French Annotated Resource Produced through Crosslingual BERT-Based Annotation Projection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Lovis, Christophe Gaudet-Blavignac, Jamil Zaghir, Jean-Philippe Goldman, Mina Bjelogrlic, Souka\\\"ina Aananou","submitted_at":"2023-09-19T17:17:28Z","abstract_excerpt":"Natural language processing (NLP) applications such as named entity recognition (NER) for low-resource corpora do not benefit from recent advances in the development of large language models (LLMs) where there is still a need for larger annotated datasets. This research article introduces a methodology for generating translated versions of annotated datasets through crosslingual annotation projection. Leveraging a language agnostic BERT-based approach, it is an efficient solution to increase low-resource corpora with few human efforts and by only using already available open data resources. Qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10770","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/2309.10770/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":"2309.10770","created_at":"2026-07-05T11:39:37.752272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10770v1","created_at":"2026-07-05T11:39:37.752272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10770","created_at":"2026-07-05T11:39:37.752272+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZDSM4W5OK6Z","created_at":"2026-07-05T11:39:37.752272+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZDSM4W5OK6Z7RNT","created_at":"2026-07-05T11:39:37.752272+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZDSM4W5","created_at":"2026-07-05T11:39:37.752272+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/UZDSM4W5OK6Z7RNTDMBXZIVXRL","json":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL.json","graph_json":"https://pith.science/api/pith-number/UZDSM4W5OK6Z7RNTDMBXZIVXRL/graph.json","events_json":"https://pith.science/api/pith-number/UZDSM4W5OK6Z7RNTDMBXZIVXRL/events.json","paper":"https://pith.science/paper/UZDSM4W5"},"agent_actions":{"view_html":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL","download_json":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL.json","view_paper":"https://pith.science/paper/UZDSM4W5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10770&json=true","fetch_graph":"https://pith.science/api/pith-number/UZDSM4W5OK6Z7RNTDMBXZIVXRL/graph.json","fetch_events":"https://pith.science/api/pith-number/UZDSM4W5OK6Z7RNTDMBXZIVXRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL/action/storage_attestation","attest_author":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL/action/author_attestation","sign_citation":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL/action/citation_signature","submit_replication":"https://pith.science/pith/UZDSM4W5OK6Z7RNTDMBXZIVXRL/action/replication_record"}},"created_at":"2026-07-05T11:39:37.752272+00:00","updated_at":"2026-07-05T11:39:37.752272+00:00"}