{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3DYFBORH5SYDCIN2RINV5N2K7L","short_pith_number":"pith:3DYFBORH","schema_version":"1.0","canonical_sha256":"d8f050ba27ecb03121ba8a1b5eb74afafe76afb0cce203959c8a383d31a18c60","source":{"kind":"arxiv","id":"2505.16661","version":2},"attestation_state":"computed","paper":{"title":"A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Issey Sukeda, Kosei Buma, Shinnosuke Ono, Shunsuke Sasaki, Takuro Fujii","submitted_at":"2025-05-22T13:27:37Z","abstract_excerpt":"We present a Japanese domain-specific language model for the pharmaceutical field, developed through continual pretraining on 2 billion Japanese pharmaceutical tokens and 8 billion English biomedical tokens. To enable rigorous evaluation, we introduce three new benchmarks: YakugakuQA, based on national pharmacist licensing exams; NayoseQA, which tests cross-lingual synonym and terminology normalization; and SogoCheck, a novel task designed to assess consistency reasoning between paired statements. We evaluate our model against both open-source medical LLMs and commercial models, including GPT-"},"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":"2505.16661","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T13:27:37Z","cross_cats_sorted":[],"title_canon_sha256":"ab7e343004bbb6bfab0dec5c98915c5f293ff792e47cf11eb6c2f2292e767b9f","abstract_canon_sha256":"a7c5ded1e1c7754f89fd44de832b244cbab46c0bf23ea7de72204a60625daa0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:07.532063Z","signature_b64":"kmXyRoU2tCBeOC4aGm6qJEdCNsgIKYJ/e+8SzoF6YmcNVu0aMrQ2VYiQKFCKRDggRqZdVWzu4C6Xjoh1/e2IAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8f050ba27ecb03121ba8a1b5eb74afafe76afb0cce203959c8a383d31a18c60","last_reissued_at":"2026-07-05T12:07:07.531514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:07.531514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Issey Sukeda, Kosei Buma, Shinnosuke Ono, Shunsuke Sasaki, Takuro Fujii","submitted_at":"2025-05-22T13:27:37Z","abstract_excerpt":"We present a Japanese domain-specific language model for the pharmaceutical field, developed through continual pretraining on 2 billion Japanese pharmaceutical tokens and 8 billion English biomedical tokens. To enable rigorous evaluation, we introduce three new benchmarks: YakugakuQA, based on national pharmacist licensing exams; NayoseQA, which tests cross-lingual synonym and terminology normalization; and SogoCheck, a novel task designed to assess consistency reasoning between paired statements. We evaluate our model against both open-source medical LLMs and commercial models, including GPT-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16661","kind":"arxiv","version":2},"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/2505.16661/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":"2505.16661","created_at":"2026-07-05T12:07:07.531576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16661v2","created_at":"2026-07-05T12:07:07.531576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16661","created_at":"2026-07-05T12:07:07.531576+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DYFBORH5SYD","created_at":"2026-07-05T12:07:07.531576+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DYFBORH5SYDCIN2","created_at":"2026-07-05T12:07:07.531576+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DYFBORH","created_at":"2026-07-05T12:07:07.531576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11114","citing_title":"KokushiMD-10: Benchmark for Evaluating Large Language Models on Ten Japanese National Healthcare Licensing Examinations","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L","json":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L.json","graph_json":"https://pith.science/api/pith-number/3DYFBORH5SYDCIN2RINV5N2K7L/graph.json","events_json":"https://pith.science/api/pith-number/3DYFBORH5SYDCIN2RINV5N2K7L/events.json","paper":"https://pith.science/paper/3DYFBORH"},"agent_actions":{"view_html":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L","download_json":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L.json","view_paper":"https://pith.science/paper/3DYFBORH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16661&json=true","fetch_graph":"https://pith.science/api/pith-number/3DYFBORH5SYDCIN2RINV5N2K7L/graph.json","fetch_events":"https://pith.science/api/pith-number/3DYFBORH5SYDCIN2RINV5N2K7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L/action/storage_attestation","attest_author":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L/action/author_attestation","sign_citation":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L/action/citation_signature","submit_replication":"https://pith.science/pith/3DYFBORH5SYDCIN2RINV5N2K7L/action/replication_record"}},"created_at":"2026-07-05T12:07:07.531576+00:00","updated_at":"2026-07-05T12:07:07.531576+00:00"}