{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q7JHQDWRFD73X6KR2UEBXWU33S","short_pith_number":"pith:Q7JHQDWR","schema_version":"1.0","canonical_sha256":"87d2780ed128ffbbf951d5081bda9bdcbcec46ad1f2817fd158d0f894289d73a","source":{"kind":"arxiv","id":"2505.19457","version":1},"attestation_state":"computed","paper":{"title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.CL"],"primary_cat":"cs.AI","authors_text":"Guilong Lu, Ji Liu, Rongjunchen Zhang, Wenqiao Zhu, Xuntao Guo","submitted_at":"2025-05-26T03:23:02Z","abstract_excerpt":"Large language models excel in general tasks, yet assessing their reliability in logic-heavy, precision-critical domains like finance, law, and healthcare remains challenging. To address this, we introduce BizFinBench, the first benchmark specifically designed to evaluate LLMs in real-world financial applications. BizFinBench consists of 6,781 well-annotated queries in Chinese, spanning five dimensions: numerical calculation, reasoning, information extraction, prediction recognition, and knowledge-based question answering, grouped into nine fine-grained categories. The benchmark includes both "},"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":"2505.19457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T03:23:02Z","cross_cats_sorted":["cs.CE","cs.CL"],"title_canon_sha256":"9f821e4db2496a26b7b6432bb56075281cfff254ba97f8087a5dda36be78f774","abstract_canon_sha256":"82fe828bd517c5f365d05abe013e9becdbc9d2bcb06ce1b1695d3a1d76ec8ac5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:30.465881Z","signature_b64":"prZf3bJVP+MhtBwrPKpuov/q20o0VBcy5dBAQC7DvERznRzkXYJbLxfO7PJmhW3vOMoCwPMOzPirCqWNQ7INCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87d2780ed128ffbbf951d5081bda9bdcbcec46ad1f2817fd158d0f894289d73a","last_reissued_at":"2026-07-05T11:09:30.465368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:30.465368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.CL"],"primary_cat":"cs.AI","authors_text":"Guilong Lu, Ji Liu, Rongjunchen Zhang, Wenqiao Zhu, Xuntao Guo","submitted_at":"2025-05-26T03:23:02Z","abstract_excerpt":"Large language models excel in general tasks, yet assessing their reliability in logic-heavy, precision-critical domains like finance, law, and healthcare remains challenging. To address this, we introduce BizFinBench, the first benchmark specifically designed to evaluate LLMs in real-world financial applications. BizFinBench consists of 6,781 well-annotated queries in Chinese, spanning five dimensions: numerical calculation, reasoning, information extraction, prediction recognition, and knowledge-based question answering, grouped into nine fine-grained categories. The benchmark includes both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19457","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/2505.19457/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":"2505.19457","created_at":"2026-07-05T11:09:30.465421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19457v1","created_at":"2026-07-05T11:09:30.465421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19457","created_at":"2026-07-05T11:09:30.465421+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7JHQDWRFD73","created_at":"2026-07-05T11:09:30.465421+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7JHQDWRFD73X6KR","created_at":"2026-07-05T11:09:30.465421+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7JHQDWR","created_at":"2026-07-05T11:09:30.465421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01886","citing_title":"Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22664","citing_title":"MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22664","citing_title":"MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09514","citing_title":"EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26235","citing_title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S","json":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S.json","graph_json":"https://pith.science/api/pith-number/Q7JHQDWRFD73X6KR2UEBXWU33S/graph.json","events_json":"https://pith.science/api/pith-number/Q7JHQDWRFD73X6KR2UEBXWU33S/events.json","paper":"https://pith.science/paper/Q7JHQDWR"},"agent_actions":{"view_html":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S","download_json":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S.json","view_paper":"https://pith.science/paper/Q7JHQDWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19457&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7JHQDWRFD73X6KR2UEBXWU33S/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7JHQDWRFD73X6KR2UEBXWU33S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S/action/storage_attestation","attest_author":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S/action/author_attestation","sign_citation":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S/action/citation_signature","submit_replication":"https://pith.science/pith/Q7JHQDWRFD73X6KR2UEBXWU33S/action/replication_record"}},"created_at":"2026-07-05T11:09:30.465421+00:00","updated_at":"2026-07-05T11:09:30.465421+00:00"}