{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UBDO5SCJI3GVM3VAPAS5YHXNYV","short_pith_number":"pith:UBDO5SCJ","schema_version":"1.0","canonical_sha256":"a046eec84946cd566ea07825dc1eedc56484d24e536d9ed34ba7e3efc4fd6f2e","source":{"kind":"arxiv","id":"2407.02301","version":1},"attestation_state":"computed","paper":{"title":"CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binfan Zheng, Binwei Yan, Dacheng Tao, Hao Liu, Haoyu Wang, Qiang Li, Tianyu Guo, Weihao Wang, Wei He, Weijian Sun, Ying Nie, Yunhe Wang","submitted_at":"2024-07-02T14:34:36Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assessing the financial knowledge of LLMs under Chinese context. In practice, to better align with the career trajectory of Chinese financial practitioners, we build a systematic evaluation from 4 first-level categories: (1) Financial Subject: whether LLMs can memorize the necessar"},"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":"2407.02301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T14:34:36Z","cross_cats_sorted":[],"title_canon_sha256":"d6e6d9fe878e66e537cfcb373ed5aeea6c3f8a387d79fe117da93a6dcc36eba7","abstract_canon_sha256":"356f48cfe061374b8cdd7cfb6e9864cea89319d5adee582511dcfd2e77bc7045"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:22.310352Z","signature_b64":"V+Wgh5uagzKa8eESfxT9LftlZ19EZJISc+CYB46Jm8OOfKC4t/fprbHSiL9trzD7T7+QsqvAQbKEAfec6aWSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a046eec84946cd566ea07825dc1eedc56484d24e536d9ed34ba7e3efc4fd6f2e","last_reissued_at":"2026-07-05T08:39:22.309892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:22.309892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binfan Zheng, Binwei Yan, Dacheng Tao, Hao Liu, Haoyu Wang, Qiang Li, Tianyu Guo, Weihao Wang, Wei He, Weijian Sun, Ying Nie, Yunhe Wang","submitted_at":"2024-07-02T14:34:36Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assessing the financial knowledge of LLMs under Chinese context. In practice, to better align with the career trajectory of Chinese financial practitioners, we build a systematic evaluation from 4 first-level categories: (1) Financial Subject: whether LLMs can memorize the necessar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02301","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/2407.02301/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":"2407.02301","created_at":"2026-07-05T08:39:22.309961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02301v1","created_at":"2026-07-05T08:39:22.309961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02301","created_at":"2026-07-05T08:39:22.309961+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBDO5SCJI3GV","created_at":"2026-07-05T08:39:22.309961+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBDO5SCJI3GVM3VA","created_at":"2026-07-05T08:39:22.309961+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBDO5SCJ","created_at":"2026-07-05T08:39:22.309961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00706","citing_title":"FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV","json":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV.json","graph_json":"https://pith.science/api/pith-number/UBDO5SCJI3GVM3VAPAS5YHXNYV/graph.json","events_json":"https://pith.science/api/pith-number/UBDO5SCJI3GVM3VAPAS5YHXNYV/events.json","paper":"https://pith.science/paper/UBDO5SCJ"},"agent_actions":{"view_html":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV","download_json":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV.json","view_paper":"https://pith.science/paper/UBDO5SCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02301&json=true","fetch_graph":"https://pith.science/api/pith-number/UBDO5SCJI3GVM3VAPAS5YHXNYV/graph.json","fetch_events":"https://pith.science/api/pith-number/UBDO5SCJI3GVM3VAPAS5YHXNYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV/action/storage_attestation","attest_author":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV/action/author_attestation","sign_citation":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV/action/citation_signature","submit_replication":"https://pith.science/pith/UBDO5SCJI3GVM3VAPAS5YHXNYV/action/replication_record"}},"created_at":"2026-07-05T08:39:22.309961+00:00","updated_at":"2026-07-05T08:39:22.309961+00:00"}