{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FGTRPRPQMGKTPDORZYRVUHN6G3","short_pith_number":"pith:FGTRPRPQ","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"},"canonical_sha256":"29a717c5f06195378dd1ce235a1dbe36cae4129fd78a1ea1ba9c52208a6d3ea9","source":{"kind":"arxiv","id":"2311.11564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11564","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11564v1","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11564","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"FGTRPRPQMGKT","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"FGTRPRPQMGKTPDOR","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"FGTRPRPQ","created_at":"2026-07-05T07:14:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FGTRPRPQMGKTPDORZYRVUHN6G3","target":"record","payload":{"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"},"canonical_sha256":"29a717c5f06195378dd1ce235a1dbe36cae4129fd78a1ea1ba9c52208a6d3ea9","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"},"source_kind":"arxiv","source_id":"2311.11564","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":"2026-07-05T07:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CLS428jU9qu0zVSi4KOijtxv606vSJ58UcPfqWteS/qSquJ8scP5bj4CqEsc7sIAgckTcW1oYd+K7QQhSFVzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:51:03.141671Z"},"content_sha256":"b0994f694c5f6cf06d1c95e7c2bfc445702a1647d73d2df457bcfc97b0a2a625","schema_version":"1.0","event_id":"sha256:b0994f694c5f6cf06d1c95e7c2bfc445702a1647d73d2df457bcfc97b0a2a625"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FGTRPRPQMGKTPDORZYRVUHN6G3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pR3CEgnJJM6SEDZPLRdRuQ9TmzdMk6DmueXFJ+xww/t1ZzcZInJAx5UekDNFS1U4YCiOcCB7dMMMHstTbqw8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:51:03.142048Z"},"content_sha256":"3bd98c5982c7e233ce604d436a98c01687c56ab87dad8f29ccc7d75f7c4a8837","schema_version":"1.0","event_id":"sha256:3bd98c5982c7e233ce604d436a98c01687c56ab87dad8f29ccc7d75f7c4a8837"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/bundle.json","state_url":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/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":"2026-07-07T04:51:03Z","links":{"resolver":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3","bundle":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/bundle.json","state":"https://pith.science/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGTRPRPQMGKTPDORZYRVUHN6G3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FGTRPRPQMGKTPDORZYRVUHN6G3","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":"d0e2d8b2ba564e7da7dc5f48302a0087dc9f9fa644183e19735d44ec5399a8bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T07:02:35Z","title_canon_sha256":"17917b49465aeaf3f79cfbdf61c3b3d65f848eefd59723d77c1ecb5007e684d2"},"schema_version":"1.0","source":{"id":"2311.11564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.11564","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2311.11564v1","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11564","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"FGTRPRPQMGKT","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"FGTRPRPQMGKTPDOR","created_at":"2026-07-05T07:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"FGTRPRPQ","created_at":"2026-07-05T07:14:35Z"}],"graph_snapshots":[{"event_id":"sha256:3bd98c5982c7e233ce604d436a98c01687c56ab87dad8f29ccc7d75f7c4a8837","target":"graph","created_at":"2026-07-05T07:14:35Z","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/2311.11564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Juntao Li, Jun Zhang, Lei Geng, Sujian Li, Wenjie Li, Xinjie Zhou, Xu Yan, Yang Yang, Ziqiang Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T07:02:35Z","title":"KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11564","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:b0994f694c5f6cf06d1c95e7c2bfc445702a1647d73d2df457bcfc97b0a2a625","target":"record","created_at":"2026-07-05T07:14:35Z","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":"d0e2d8b2ba564e7da7dc5f48302a0087dc9f9fa644183e19735d44ec5399a8bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-20T07:02:35Z","title_canon_sha256":"17917b49465aeaf3f79cfbdf61c3b3d65f848eefd59723d77c1ecb5007e684d2"},"schema_version":"1.0","source":{"id":"2311.11564","kind":"arxiv","version":1}},"canonical_sha256":"29a717c5f06195378dd1ce235a1dbe36cae4129fd78a1ea1ba9c52208a6d3ea9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29a717c5f06195378dd1ce235a1dbe36cae4129fd78a1ea1ba9c52208a6d3ea9","first_computed_at":"2026-07-05T07:14:35.546275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:35.546275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ndYhrZc8HwdJpZwIe05p83mPyKn0Cc3PuQ/DX5ietu5nQ/ZCohl2j8t5UmZ9AkGmu5vdrLC9aRurSjXwGn37Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:35.546771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.11564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0994f694c5f6cf06d1c95e7c2bfc445702a1647d73d2df457bcfc97b0a2a625","sha256:3bd98c5982c7e233ce604d436a98c01687c56ab87dad8f29ccc7d75f7c4a8837"],"state_sha256":"beb4a01756298e3c21780e641ce57f832700c2fc52a5e1bbcf74538a538dbdc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p67HPMyHa0xP3T878WxHkHZQJKQ3w2B9ml6eAndzbatvmcIG74SpNevHx0CeT/btHJQLfLeuLM9kGQvUcjNzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:51:03.144161Z","bundle_sha256":"048d18c641aeb3083b7a5864a1af41953dfe9ffbd21446c67dc1f360b6db3f50"}}