{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NZO2BNT2IDSH6JS24KZ3MKD5OP","short_pith_number":"pith:NZO2BNT2","schema_version":"1.0","canonical_sha256":"6e5da0b67a40e47f265ae2b3b6287d73d7850f6e71d8209570a8dee31d21a955","source":{"kind":"arxiv","id":"2311.06602","version":2},"attestation_state":"computed","paper":{"title":"BizBench: A Quantitative Reasoning Benchmark for Business and Finance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charles Lovering, Chris Tanner, Michael Krumdick, Rik Koncel-Kedziorski, Varshini Reddy, Viet Lai","submitted_at":"2023-11-11T16:16:11Z","abstract_excerpt":"Answering questions within business and finance requires reasoning, precision, and a wide-breadth of technical knowledge. Together, these requirements make this domain difficult for large language models (LLMs). We introduce BizBench, a benchmark for evaluating models' ability to reason about realistic financial problems. BizBench comprises eight quantitative reasoning tasks, focusing on question-answering (QA) over financial data via program synthesis. We include three financially-themed code-generation tasks from newly collected and augmented QA data. Additionally, we isolate the reasoning 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":"2311.06602","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-11T16:16:11Z","cross_cats_sorted":[],"title_canon_sha256":"fae189561a94b659bcbff9be9f01767c36220ef08663f16d6d8dac4c3f526069","abstract_canon_sha256":"519d19621b099075983c6c81b595d1e078d323cdd1a0f8a08ff2eec451312968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:13.682137Z","signature_b64":"XDoW+Kob6921Dv50fRCVrmshKpG4UiZcP0kl8Kn/7HwxbBk8xbZkN8fKyj++L9sgV9jTZWsnMl7P/eAzna/eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5da0b67a40e47f265ae2b3b6287d73d7850f6e71d8209570a8dee31d21a955","last_reissued_at":"2026-07-05T07:55:13.681555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:13.681555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BizBench: A Quantitative Reasoning Benchmark for Business and Finance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charles Lovering, Chris Tanner, Michael Krumdick, Rik Koncel-Kedziorski, Varshini Reddy, Viet Lai","submitted_at":"2023-11-11T16:16:11Z","abstract_excerpt":"Answering questions within business and finance requires reasoning, precision, and a wide-breadth of technical knowledge. Together, these requirements make this domain difficult for large language models (LLMs). We introduce BizBench, a benchmark for evaluating models' ability to reason about realistic financial problems. BizBench comprises eight quantitative reasoning tasks, focusing on question-answering (QA) over financial data via program synthesis. We include three financially-themed code-generation tasks from newly collected and augmented QA data. Additionally, we isolate the reasoning c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06602","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/2311.06602/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":"2311.06602","created_at":"2026-07-05T07:55:13.681615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06602v2","created_at":"2026-07-05T07:55:13.681615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06602","created_at":"2026-07-05T07:55:13.681615+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZO2BNT2IDSH","created_at":"2026-07-05T07:55:13.681615+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZO2BNT2IDSH6JS2","created_at":"2026-07-05T07:55:13.681615+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZO2BNT2","created_at":"2026-07-05T07:55:13.681615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17642","citing_title":"FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.09544","citing_title":"MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP","json":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP.json","graph_json":"https://pith.science/api/pith-number/NZO2BNT2IDSH6JS24KZ3MKD5OP/graph.json","events_json":"https://pith.science/api/pith-number/NZO2BNT2IDSH6JS24KZ3MKD5OP/events.json","paper":"https://pith.science/paper/NZO2BNT2"},"agent_actions":{"view_html":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP","download_json":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP.json","view_paper":"https://pith.science/paper/NZO2BNT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06602&json=true","fetch_graph":"https://pith.science/api/pith-number/NZO2BNT2IDSH6JS24KZ3MKD5OP/graph.json","fetch_events":"https://pith.science/api/pith-number/NZO2BNT2IDSH6JS24KZ3MKD5OP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP/action/storage_attestation","attest_author":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP/action/author_attestation","sign_citation":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP/action/citation_signature","submit_replication":"https://pith.science/pith/NZO2BNT2IDSH6JS24KZ3MKD5OP/action/replication_record"}},"created_at":"2026-07-05T07:55:13.681615+00:00","updated_at":"2026-07-05T07:55:13.681615+00:00"}