{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YHMLVEKATFI7NIN6WDHCTX5H7I","short_pith_number":"pith:YHMLVEKA","schema_version":"1.0","canonical_sha256":"c1d8ba91409951f6a1beb0ce29dfa7fa39d9f49defc0cf6205ec63931180c5a2","source":{"kind":"arxiv","id":"2412.15907","version":1},"attestation_state":"computed","paper":{"title":"Development of a Large-scale Dataset of Chest Computed Tomography Reports in Japanese and a High-performance Finding Classification Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hiroshi Hirakawa, Osamu Abe, Satoshi Nakamura, Shintaro Kano, Shouhei Hanaoka, Takeharu Yoshikawa, Tomohiro Kikuchi, Yosuke Yamagishi, Yuki Sonoda, Yuta Nakamura","submitted_at":"2024-12-20T13:59:11Z","abstract_excerpt":"Background: Recent advances in large language models highlight the need for high-quality multilingual medical datasets. While Japan leads globally in CT scanner deployment and utilization, the lack of large-scale Japanese radiology datasets has hindered the development of specialized language models for medical imaging analysis. Objective: To develop a comprehensive Japanese CT report dataset through machine translation and establish a specialized language model for structured finding classification. Additionally, to create a rigorously validated evaluation dataset through expert radiologist r"},"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":"2412.15907","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T13:59:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24c12e7077cf4ad6a71ace752d4914a39a00e5b396a5738a8498e4844e81dbe7","abstract_canon_sha256":"2645726b4761940bfc97ca49640f4d49549cfc24c40cbd60ad6e0a0810572256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:56.791529Z","signature_b64":"2WycpwHVW5+ca9/ukAmg7lPs5WwfQ6fhOrV5S1WFBpvqRfW9tevUmTRg9+ndTidroKM6rsHLymeVUlrpWq4kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1d8ba91409951f6a1beb0ce29dfa7fa39d9f49defc0cf6205ec63931180c5a2","last_reissued_at":"2026-07-05T12:01:56.791033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:56.791033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Development of a Large-scale Dataset of Chest Computed Tomography Reports in Japanese and a High-performance Finding Classification Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hiroshi Hirakawa, Osamu Abe, Satoshi Nakamura, Shintaro Kano, Shouhei Hanaoka, Takeharu Yoshikawa, Tomohiro Kikuchi, Yosuke Yamagishi, Yuki Sonoda, Yuta Nakamura","submitted_at":"2024-12-20T13:59:11Z","abstract_excerpt":"Background: Recent advances in large language models highlight the need for high-quality multilingual medical datasets. While Japan leads globally in CT scanner deployment and utilization, the lack of large-scale Japanese radiology datasets has hindered the development of specialized language models for medical imaging analysis. Objective: To develop a comprehensive Japanese CT report dataset through machine translation and establish a specialized language model for structured finding classification. Additionally, to create a rigorously validated evaluation dataset through expert radiologist r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15907","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/2412.15907/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":"2412.15907","created_at":"2026-07-05T12:01:56.791084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15907v1","created_at":"2026-07-05T12:01:56.791084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15907","created_at":"2026-07-05T12:01:56.791084+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHMLVEKATFI7","created_at":"2026-07-05T12:01:56.791084+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHMLVEKATFI7NIN6","created_at":"2026-07-05T12:01:56.791084+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHMLVEKA","created_at":"2026-07-05T12:01:56.791084+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/YHMLVEKATFI7NIN6WDHCTX5H7I","json":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I.json","graph_json":"https://pith.science/api/pith-number/YHMLVEKATFI7NIN6WDHCTX5H7I/graph.json","events_json":"https://pith.science/api/pith-number/YHMLVEKATFI7NIN6WDHCTX5H7I/events.json","paper":"https://pith.science/paper/YHMLVEKA"},"agent_actions":{"view_html":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I","download_json":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I.json","view_paper":"https://pith.science/paper/YHMLVEKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15907&json=true","fetch_graph":"https://pith.science/api/pith-number/YHMLVEKATFI7NIN6WDHCTX5H7I/graph.json","fetch_events":"https://pith.science/api/pith-number/YHMLVEKATFI7NIN6WDHCTX5H7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I/action/storage_attestation","attest_author":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I/action/author_attestation","sign_citation":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I/action/citation_signature","submit_replication":"https://pith.science/pith/YHMLVEKATFI7NIN6WDHCTX5H7I/action/replication_record"}},"created_at":"2026-07-05T12:01:56.791084+00:00","updated_at":"2026-07-05T12:01:56.791084+00:00"}