{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCEUIUPL2WQJGEAJ6QD74ZQZ3P","short_pith_number":"pith:WCEUIUPL","schema_version":"1.0","canonical_sha256":"b0894451ebd5a0931009f407fe6619dbd5894016a5bc6c1f50f5dda852b7180b","source":{"kind":"arxiv","id":"2401.10744","version":1},"attestation_state":"computed","paper":{"title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingya Zhou, Kaiyuan Wang, Shoutai Zhu, Wenqi Wei, Yanlin Zhu, Ye Yuan, Ziqiang Yuan","submitted_at":"2024-01-19T15:09:39Z","abstract_excerpt":"Large Language models (LLMs) usually rely on extensive training datasets. In the financial domain, creating numerical reasoning datasets that include a mix of tables and long text often involves substantial manual annotation expenses. To address the limited data resources and reduce the annotation cost, we introduce FinLLMs, a method for generating financial question-answering data based on common financial formulas using Large Language Models. First, we compile a list of common financial formulas and construct a graph based on the variables these formulas employ. We then augment the formula s"},"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":"2401.10744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-19T15:09:39Z","cross_cats_sorted":[],"title_canon_sha256":"a86b3ba8cddabefa817e95f5dfc63954d8153e19b231354f751277e96edbf9d7","abstract_canon_sha256":"9dbd150ae406b902ff06abd0183aaa95065ca7e83f2bb113991ebb3cc6ed5bac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:30.865158Z","signature_b64":"A0E2s42aUCgFhEhycXF2foLT39JaHtpPliZHD9UhhoVZzWJhc54MIqyFballxdmGXg0kxsD66lJFJGoMDLRtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0894451ebd5a0931009f407fe6619dbd5894016a5bc6c1f50f5dda852b7180b","last_reissued_at":"2026-07-05T07:35:30.864783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:30.864783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingya Zhou, Kaiyuan Wang, Shoutai Zhu, Wenqi Wei, Yanlin Zhu, Ye Yuan, Ziqiang Yuan","submitted_at":"2024-01-19T15:09:39Z","abstract_excerpt":"Large Language models (LLMs) usually rely on extensive training datasets. In the financial domain, creating numerical reasoning datasets that include a mix of tables and long text often involves substantial manual annotation expenses. To address the limited data resources and reduce the annotation cost, we introduce FinLLMs, a method for generating financial question-answering data based on common financial formulas using Large Language Models. First, we compile a list of common financial formulas and construct a graph based on the variables these formulas employ. We then augment the formula s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10744","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/2401.10744/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":"2401.10744","created_at":"2026-07-05T07:35:30.864837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10744v1","created_at":"2026-07-05T07:35:30.864837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10744","created_at":"2026-07-05T07:35:30.864837+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCEUIUPL2WQJ","created_at":"2026-07-05T07:35:30.864837+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCEUIUPL2WQJGEAJ","created_at":"2026-07-05T07:35:30.864837+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCEUIUPL","created_at":"2026-07-05T07:35:30.864837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19394","citing_title":"EmbGen: Teaching with Reassembled Corpora","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P","json":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P.json","graph_json":"https://pith.science/api/pith-number/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/graph.json","events_json":"https://pith.science/api/pith-number/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/events.json","paper":"https://pith.science/paper/WCEUIUPL"},"agent_actions":{"view_html":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P","download_json":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P.json","view_paper":"https://pith.science/paper/WCEUIUPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10744&json=true","fetch_graph":"https://pith.science/api/pith-number/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/graph.json","fetch_events":"https://pith.science/api/pith-number/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/action/storage_attestation","attest_author":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/action/author_attestation","sign_citation":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/action/citation_signature","submit_replication":"https://pith.science/pith/WCEUIUPL2WQJGEAJ6QD74ZQZ3P/action/replication_record"}},"created_at":"2026-07-05T07:35:30.864837+00:00","updated_at":"2026-07-05T07:35:30.864837+00:00"}