{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HZFKVNYNSJGUWVHXNDHLE4J4NR","short_pith_number":"pith:HZFKVNYN","canonical_record":{"source":{"id":"2303.18027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-31T13:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"a87942947bb34a3fecd280211aed71a1f01ae69180a8fab445b469a0b8b021d1","abstract_canon_sha256":"e9a03649965d9d8e36ca13bf94a4ba2a6b423d10a3ee8ce77a1112682f86291d"},"schema_version":"1.0"},"canonical_sha256":"3e4aaab70d924d4b54f768ceb2713c6c5eaac63ad15981159742dc16bb6ac63b","source":{"kind":"arxiv","id":"2303.18027","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.18027","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.18027v2","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.18027","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"HZFKVNYNSJGU","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"HZFKVNYNSJGUWVHX","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"HZFKVNYN","created_at":"2026-07-05T05:58:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HZFKVNYNSJGUWVHXNDHLE4J4NR","target":"record","payload":{"canonical_record":{"source":{"id":"2303.18027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-31T13:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"a87942947bb34a3fecd280211aed71a1f01ae69180a8fab445b469a0b8b021d1","abstract_canon_sha256":"e9a03649965d9d8e36ca13bf94a4ba2a6b423d10a3ee8ce77a1112682f86291d"},"schema_version":"1.0"},"canonical_sha256":"3e4aaab70d924d4b54f768ceb2713c6c5eaac63ad15981159742dc16bb6ac63b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:20.622699Z","signature_b64":"z3G6OD9E7BogyzLzraj66YCDd3CGztfoMhEVbGmQJTiNxSkd1NZmBAzp6ce1KyMZkNDz+JyVUCBT04VR4/wqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4aaab70d924d4b54f768ceb2713c6c5eaac63ad15981159742dc16bb6ac63b","last_reissued_at":"2026-07-05T05:58:20.622158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:20.622158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.18027","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:58:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3mqVc/U5kF3/HsD8/iKfJd3qT9QYbKczpt5ylhd9QdT5v3DUVilbIBrSmoxI0S5EpSnLUOGQhUxeaPlL0BBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:20:59.044323Z"},"content_sha256":"ddd06d55ac9ce85cda8f4059137c53fb0ab75bc4485bf1174a6770bbae943542","schema_version":"1.0","event_id":"sha256:ddd06d55ac9ce85cda8f4059137c53fb0ab75bc4485bf1174a6770bbae943542"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HZFKVNYNSJGUWVHXNDHLE4J4NR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dragomir Radev, Jungo Kasai, Keisuke Sakaguchi, Yuhei Kasai, Yutaro Yamada","submitted_at":"2023-03-31T13:04:47Z","abstract_excerpt":"As large language models (LLMs) gain popularity among speakers of diverse languages, we believe that it is crucial to benchmark them to better understand model behaviors, failures, and limitations in languages beyond English. In this work, we evaluate LLM APIs (ChatGPT, GPT-3, and GPT-4) on the Japanese national medical licensing examinations from the past five years, including the current year. Our team comprises native Japanese-speaking NLP researchers and a practicing cardiologist based in Japan. Our experiments show that GPT-4 outperforms ChatGPT and GPT-3 and passes all six years of the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.18027","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/2303.18027/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":"2026-07-05T05:58:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jdv9OKpnFQW3j93NU3zymPe62ZhpHdy+mr4+kgT62xOChJhKLBT8o+tPPfcsj4+V74gVAdwjHbDLkUxBwEcOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:20:59.044847Z"},"content_sha256":"3252f1a415908d17151daaaae6cbcc2f31829342aedad660c2e94376f70e3558","schema_version":"1.0","event_id":"sha256:3252f1a415908d17151daaaae6cbcc2f31829342aedad660c2e94376f70e3558"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR/bundle.json","state_url":"https://pith.science/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR/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":"2026-08-21T15:20:59Z","links":{"resolver":"https://pith.science/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR","bundle":"https://pith.science/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR/bundle.json","state":"https://pith.science/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZFKVNYNSJGUWVHXNDHLE4J4NR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HZFKVNYNSJGUWVHXNDHLE4J4NR","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":"e9a03649965d9d8e36ca13bf94a4ba2a6b423d10a3ee8ce77a1112682f86291d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-31T13:04:47Z","title_canon_sha256":"a87942947bb34a3fecd280211aed71a1f01ae69180a8fab445b469a0b8b021d1"},"schema_version":"1.0","source":{"id":"2303.18027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.18027","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.18027v2","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.18027","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"HZFKVNYNSJGU","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"HZFKVNYNSJGUWVHX","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"HZFKVNYN","created_at":"2026-07-05T05:58:20Z"}],"graph_snapshots":[{"event_id":"sha256:3252f1a415908d17151daaaae6cbcc2f31829342aedad660c2e94376f70e3558","target":"graph","created_at":"2026-07-05T05:58:20Z","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/2303.18027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) gain popularity among speakers of diverse languages, we believe that it is crucial to benchmark them to better understand model behaviors, failures, and limitations in languages beyond English. In this work, we evaluate LLM APIs (ChatGPT, GPT-3, and GPT-4) on the Japanese national medical licensing examinations from the past five years, including the current year. Our team comprises native Japanese-speaking NLP researchers and a practicing cardiologist based in Japan. Our experiments show that GPT-4 outperforms ChatGPT and GPT-3 and passes all six years of the e","authors_text":"Dragomir Radev, Jungo Kasai, Keisuke Sakaguchi, Yuhei Kasai, Yutaro Yamada","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-31T13:04:47Z","title":"Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.18027","kind":"arxiv","version":2},"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:ddd06d55ac9ce85cda8f4059137c53fb0ab75bc4485bf1174a6770bbae943542","target":"record","created_at":"2026-07-05T05:58:20Z","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":"e9a03649965d9d8e36ca13bf94a4ba2a6b423d10a3ee8ce77a1112682f86291d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-31T13:04:47Z","title_canon_sha256":"a87942947bb34a3fecd280211aed71a1f01ae69180a8fab445b469a0b8b021d1"},"schema_version":"1.0","source":{"id":"2303.18027","kind":"arxiv","version":2}},"canonical_sha256":"3e4aaab70d924d4b54f768ceb2713c6c5eaac63ad15981159742dc16bb6ac63b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e4aaab70d924d4b54f768ceb2713c6c5eaac63ad15981159742dc16bb6ac63b","first_computed_at":"2026-07-05T05:58:20.622158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:20.622158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z3G6OD9E7BogyzLzraj66YCDd3CGztfoMhEVbGmQJTiNxSkd1NZmBAzp6ce1KyMZkNDz+JyVUCBT04VR4/wqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:20.622699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.18027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddd06d55ac9ce85cda8f4059137c53fb0ab75bc4485bf1174a6770bbae943542","sha256:3252f1a415908d17151daaaae6cbcc2f31829342aedad660c2e94376f70e3558"],"state_sha256":"06c85a0136d6300be66a2b70774c5a6d2dd283ed73ba9c145c16e4045ca98ba1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RtlPI11V2aLAphl8fnVVcOR1YKA/MQXwObF/KAXk6CQSJ/donxUhc6o31/0TIwAwKlztecdXkNxyN6um/ZiVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:20:59.049975Z","bundle_sha256":"dbadce62cc7a6c501586260da58a5e7fa6e722bf4cd31d68864b2cf4fdf12ab0"}}