{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NMBMFDPMVQTOZ4F7GASVEFDYIQ","short_pith_number":"pith:NMBMFDPM","schema_version":"1.0","canonical_sha256":"6b02c28decac26ecf0bf3025521478440dc43b9a00e0e88fe55b83b1fc4610d3","source":{"kind":"arxiv","id":"2403.15062","version":1},"attestation_state":"computed","paper":{"title":"Construction of a Japanese Financial Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"q-fin.CP","authors_text":"Masanori Hirano","submitted_at":"2024-03-22T09:40:27Z","abstract_excerpt":"With the recent development of large language models (LLMs), models that focus on certain domains and languages have been discussed for their necessity. There is also a growing need for benchmarks to evaluate the performance of current LLMs in each domain. Therefore, in this study, we constructed a benchmark comprising multiple tasks specific to the Japanese and financial domains and performed benchmark measurements on some models. Consequently, we confirmed that GPT-4 is currently outstanding, and that the constructed benchmarks function effectively. According to our analysis, our benchmark c"},"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":"2403.15062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2024-03-22T09:40:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"da82adbfc0edf875b990a7f4cdc2c615264f973e37214b8ed02d55cff5aee3a1","abstract_canon_sha256":"d4362ee1b947103fc762187c012ce708d021e731076ec69158871a667c8a0322"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:29.753468Z","signature_b64":"dpubxcl88kmmPnvcuLQv7zO2v78nj7Wk/GCCv75VQiD3ZlHCYPHhbg0rzLKsQ/kinK88Y7nSHShFgkF5XA71Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b02c28decac26ecf0bf3025521478440dc43b9a00e0e88fe55b83b1fc4610d3","last_reissued_at":"2026-07-05T07:59:29.753005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:29.753005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Construction of a Japanese Financial Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"q-fin.CP","authors_text":"Masanori Hirano","submitted_at":"2024-03-22T09:40:27Z","abstract_excerpt":"With the recent development of large language models (LLMs), models that focus on certain domains and languages have been discussed for their necessity. There is also a growing need for benchmarks to evaluate the performance of current LLMs in each domain. Therefore, in this study, we constructed a benchmark comprising multiple tasks specific to the Japanese and financial domains and performed benchmark measurements on some models. Consequently, we confirmed that GPT-4 is currently outstanding, and that the constructed benchmarks function effectively. According to our analysis, our benchmark c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15062","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/2403.15062/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":"2403.15062","created_at":"2026-07-05T07:59:29.753065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15062v1","created_at":"2026-07-05T07:59:29.753065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15062","created_at":"2026-07-05T07:59:29.753065+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMBMFDPMVQTO","created_at":"2026-07-05T07:59:29.753065+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMBMFDPMVQTOZ4F7","created_at":"2026-07-05T07:59:29.753065+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMBMFDPM","created_at":"2026-07-05T07:59:29.753065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02638","citing_title":"QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturing","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ","json":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ.json","graph_json":"https://pith.science/api/pith-number/NMBMFDPMVQTOZ4F7GASVEFDYIQ/graph.json","events_json":"https://pith.science/api/pith-number/NMBMFDPMVQTOZ4F7GASVEFDYIQ/events.json","paper":"https://pith.science/paper/NMBMFDPM"},"agent_actions":{"view_html":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ","download_json":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ.json","view_paper":"https://pith.science/paper/NMBMFDPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15062&json=true","fetch_graph":"https://pith.science/api/pith-number/NMBMFDPMVQTOZ4F7GASVEFDYIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NMBMFDPMVQTOZ4F7GASVEFDYIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ/action/storage_attestation","attest_author":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ/action/author_attestation","sign_citation":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ/action/citation_signature","submit_replication":"https://pith.science/pith/NMBMFDPMVQTOZ4F7GASVEFDYIQ/action/replication_record"}},"created_at":"2026-07-05T07:59:29.753065+00:00","updated_at":"2026-07-05T07:59:29.753065+00:00"}