{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:STOYC5PUOBINBWDOU75Y2UQ7OX","short_pith_number":"pith:STOYC5PU","schema_version":"1.0","canonical_sha256":"94dd8175f47050d0d86ea7fb8d521f75ccfc5210255f653baa54ef4486e5b842","source":{"kind":"arxiv","id":"2308.09975","version":2},"attestation_state":"computed","paper":{"title":"FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Zhu, Chuqi Wang, Hanyang Cao, Haotian Xia, Jinyi Niu, Liwen Zhang, Sizhe Wang, Weining Shen, Xiaolong Liang, Xiaoming Huang, Xin Guo, Yanhui Wang, Yun Chen, Zhaowei Liu, Zhiqiang Liu, Zhi Yang, Zhongyu Wei","submitted_at":"2023-08-19T10:38:00Z","abstract_excerpt":"Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored, and their performance on complex tasks like financial agent remains unknown. This paper presents FinEval, a benchmark designed to evaluate LLMs' financial domain knowledge and practical abilities. The dataset contains 8,351 questions categorized into four different key areas: Financial Academic Knowledge, Financial Industry Knowledge, Financial Security Knowledge, and Financial Agent. Financial Academic Kno"},"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":"2308.09975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-19T10:38:00Z","cross_cats_sorted":[],"title_canon_sha256":"46c1aeaaf0fc3c79cc294eaae6e34c2eae21e5fdf83661dc5c846e33d703e2e8","abstract_canon_sha256":"69aa5f2eb32f0dadb57feb989632476e99c9373142622caae7c16a0db5fcf2f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:40.927970Z","signature_b64":"lOyAU6P5ae6bJJqZSkr0xmNO9ew5O/KPOH4D+VQou5GIVEfvilwRMhMj2cQkGVMY3H4l7XnPTfqjYaY2Med/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94dd8175f47050d0d86ea7fb8d521f75ccfc5210255f653baa54ef4486e5b842","last_reissued_at":"2026-07-05T09:45:40.927541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:40.927541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Zhu, Chuqi Wang, Hanyang Cao, Haotian Xia, Jinyi Niu, Liwen Zhang, Sizhe Wang, Weining Shen, Xiaolong Liang, Xiaoming Huang, Xin Guo, Yanhui Wang, Yun Chen, Zhaowei Liu, Zhiqiang Liu, Zhi Yang, Zhongyu Wei","submitted_at":"2023-08-19T10:38:00Z","abstract_excerpt":"Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored, and their performance on complex tasks like financial agent remains unknown. This paper presents FinEval, a benchmark designed to evaluate LLMs' financial domain knowledge and practical abilities. The dataset contains 8,351 questions categorized into four different key areas: Financial Academic Knowledge, Financial Industry Knowledge, Financial Security Knowledge, and Financial Agent. Financial Academic Kno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09975","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/2308.09975/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":"2308.09975","created_at":"2026-07-05T09:45:40.927596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09975v2","created_at":"2026-07-05T09:45:40.927596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09975","created_at":"2026-07-05T09:45:40.927596+00:00"},{"alias_kind":"pith_short_12","alias_value":"STOYC5PUOBIN","created_at":"2026-07-05T09:45:40.927596+00:00"},{"alias_kind":"pith_short_16","alias_value":"STOYC5PUOBINBWDO","created_at":"2026-07-05T09:45:40.927596+00:00"},{"alias_kind":"pith_short_8","alias_value":"STOYC5PU","created_at":"2026-07-05T09:45:40.927596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13779","citing_title":"MinT: Managed Infrastructure for Training and Serving Millions of LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24414","citing_title":"JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17962","citing_title":"FinDocMRE: A Benchmark for Document-Level Financial Multimodal Reasoning Evaluation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08136","citing_title":"EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13779","citing_title":"MinT: Managed Infrastructure for Training and Serving Millions of LLMs","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX","json":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX.json","graph_json":"https://pith.science/api/pith-number/STOYC5PUOBINBWDOU75Y2UQ7OX/graph.json","events_json":"https://pith.science/api/pith-number/STOYC5PUOBINBWDOU75Y2UQ7OX/events.json","paper":"https://pith.science/paper/STOYC5PU"},"agent_actions":{"view_html":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX","download_json":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX.json","view_paper":"https://pith.science/paper/STOYC5PU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09975&json=true","fetch_graph":"https://pith.science/api/pith-number/STOYC5PUOBINBWDOU75Y2UQ7OX/graph.json","fetch_events":"https://pith.science/api/pith-number/STOYC5PUOBINBWDOU75Y2UQ7OX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX/action/storage_attestation","attest_author":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX/action/author_attestation","sign_citation":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX/action/citation_signature","submit_replication":"https://pith.science/pith/STOYC5PUOBINBWDOU75Y2UQ7OX/action/replication_record"}},"created_at":"2026-07-05T09:45:40.927596+00:00","updated_at":"2026-07-05T09:45:40.927596+00:00"}