{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FGTRPRPQMGKTPDORZYRVUHN6G3","short_pith_number":"pith:FGTRPRPQ","schema_version":"1.0","canonical_sha256":"29a717c5f06195378dd1ce235a1dbe36cae4129fd78a1ea1ba9c52208a6d3ea9","source":{"kind":"arxiv","id":"2311.11564","version":1},"attestation_state":"computed","paper":{"title":"KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juntao Li, Jun Zhang, Lei Geng, Sujian Li, Wenjie Li, Xinjie Zhou, Xu Yan, Yang Yang, Ziqiang Cao","submitted_at":"2023-11-20T07:02:35Z","abstract_excerpt":"Most biomedical pretrained language models are monolingual and cannot handle the growing cross-lingual requirements. The scarcity of non-English domain corpora, not to mention parallel data, poses a significant hurdle in training multilingual biomedical models. Since knowledge forms the core of domain-specific corpora and can be translated into various languages accurately, we propose a model called KBioXLM, which transforms the multilingual pretrained model XLM-R into the biomedical domain using a knowledge-anchored approach. We achieve a biomedical multilingual corpus by incorporating three "},"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":"2311.11564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T07:02:35Z","cross_cats_sorted":[],"title_canon_sha256":"17917b49465aeaf3f79cfbdf61c3b3d65f848eefd59723d77c1ecb5007e684d2","abstract_canon_sha256":"d0e2d8b2ba564e7da7dc5f48302a0087dc9f9fa644183e19735d44ec5399a8bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:35.546771Z","signature_b64":"ndYhrZc8HwdJpZwIe05p83mPyKn0Cc3PuQ/DX5ietu5nQ/ZCohl2j8t5UmZ9AkGmu5vdrLC9aRurSjXwGn37Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a717c5f06195378dd1ce235a1dbe36cae4129fd78a1ea1ba9c52208a6d3ea9","last_reissued_at":"2026-07-05T07:14:35.546275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:35.546275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juntao Li, Jun Zhang, Lei Geng, Sujian Li, Wenjie Li, Xinjie Zhou, Xu Yan, Yang Yang, Ziqiang Cao","submitted_at":"2023-11-20T07:02:35Z","abstract_excerpt":"Most biomedical pretrained language models are monolingual and cannot handle the growing cross-lingual requirements. The scarcity of non-English domain corpora, not to mention parallel data, poses a significant hurdle in training multilingual biomedical models. Since knowledge forms the core of domain-specific corpora and can be translated into various languages accurately, we propose a model called KBioXLM, which transforms the multilingual pretrained model XLM-R into the biomedical domain using a knowledge-anchored approach. We achieve a biomedical multilingual corpus by incorporating three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11564","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/2311.11564/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":"2311.11564","created_at":"2026-07-05T07:14:35.546341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11564v1","created_at":"2026-07-05T07:14:35.546341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11564","created_at":"2026-07-05T07:14:35.546341+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGTRPRPQMGKT","created_at":"2026-07-05T07:14:35.546341+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGTRPRPQMGKTPDOR","created_at":"2026-07-05T07:14:35.546341+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGTRPRPQ","created_at":"2026-07-05T07:14:35.546341+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/FGTRPRPQMGKTPDORZYRVUHN6G3","json":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3.json","graph_json":"https://pith.science/api/pith-number/FGTRPRPQMGKTPDORZYRVUHN6G3/graph.json","events_json":"https://pith.science/api/pith-number/FGTRPRPQMGKTPDORZYRVUHN6G3/events.json","paper":"https://pith.science/paper/FGTRPRPQ"},"agent_actions":{"view_html":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3","download_json":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3.json","view_paper":"https://pith.science/paper/FGTRPRPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11564&json=true","fetch_graph":"https://pith.science/api/pith-number/FGTRPRPQMGKTPDORZYRVUHN6G3/graph.json","fetch_events":"https://pith.science/api/pith-number/FGTRPRPQMGKTPDORZYRVUHN6G3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/action/storage_attestation","attest_author":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/action/author_attestation","sign_citation":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/action/citation_signature","submit_replication":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/action/replication_record"}},"created_at":"2026-07-05T07:14:35.546341+00:00","updated_at":"2026-07-05T07:14:35.546341+00:00"}