{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QFRIRP7ULWP2SQUIKOCMY2BX4T","short_pith_number":"pith:QFRIRP7U","schema_version":"1.0","canonical_sha256":"816288bff45d9fa942885384cc6837e4f64dd624392ae98e5b7a1e1056e26489","source":{"kind":"arxiv","id":"2501.06211","version":1},"attestation_state":"computed","paper":{"title":"FLAME: Financial Large-Language Model Assessment and Metrics Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.CL","authors_text":"Jiayu Guo, Martha Li, Songtao Tan, Yu Guo","submitted_at":"2025-01-03T09:17:23Z","abstract_excerpt":"LLMs have revolutionized NLP and demonstrated potential across diverse domains. More and more financial LLMs have been introduced for finance-specific tasks, yet comprehensively assessing their value is still challenging. In this paper, we introduce FLAME, a comprehensive financial LLMs evaluation system in Chinese, which includes two core evaluation benchmarks: FLAME-Cer and FLAME-Sce. FLAME-Cer covers 14 types of authoritative financial certifications, including CPA, CFA, and FRM, with a total of approximately 16,000 carefully selected questions. All questions have been manually reviewed to "},"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":"2501.06211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T09:17:23Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"57078dcae6249c8ba5c91cc871f80dafd18b29e2258d7e76ab2898dcf3eee7f6","abstract_canon_sha256":"471008502fcfd94e2a60f310ef012711dce885358687615a55aab5d5d3220d4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:34.718797Z","signature_b64":"bAiv9s0dQ6MeU18OXtR7ouvjW+4nf8fRH/HEuO6Xx13RmoNlui5s9zjOf7IQCKdJuKECKeQ05rcs4lfu0pnnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"816288bff45d9fa942885384cc6837e4f64dd624392ae98e5b7a1e1056e26489","last_reissued_at":"2026-07-05T09:59:34.718369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:34.718369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLAME: Financial Large-Language Model Assessment and Metrics Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.CL","authors_text":"Jiayu Guo, Martha Li, Songtao Tan, Yu Guo","submitted_at":"2025-01-03T09:17:23Z","abstract_excerpt":"LLMs have revolutionized NLP and demonstrated potential across diverse domains. More and more financial LLMs have been introduced for finance-specific tasks, yet comprehensively assessing their value is still challenging. In this paper, we introduce FLAME, a comprehensive financial LLMs evaluation system in Chinese, which includes two core evaluation benchmarks: FLAME-Cer and FLAME-Sce. FLAME-Cer covers 14 types of authoritative financial certifications, including CPA, CFA, and FRM, with a total of approximately 16,000 carefully selected questions. All questions have been manually reviewed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06211","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/2501.06211/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":"2501.06211","created_at":"2026-07-05T09:59:34.718426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06211v1","created_at":"2026-07-05T09:59:34.718426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06211","created_at":"2026-07-05T09:59:34.718426+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFRIRP7ULWP2","created_at":"2026-07-05T09:59:34.718426+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFRIRP7ULWP2SQUI","created_at":"2026-07-05T09:59:34.718426+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFRIRP7U","created_at":"2026-07-05T09:59:34.718426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.09544","citing_title":"MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T","json":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T.json","graph_json":"https://pith.science/api/pith-number/QFRIRP7ULWP2SQUIKOCMY2BX4T/graph.json","events_json":"https://pith.science/api/pith-number/QFRIRP7ULWP2SQUIKOCMY2BX4T/events.json","paper":"https://pith.science/paper/QFRIRP7U"},"agent_actions":{"view_html":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T","download_json":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T.json","view_paper":"https://pith.science/paper/QFRIRP7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06211&json=true","fetch_graph":"https://pith.science/api/pith-number/QFRIRP7ULWP2SQUIKOCMY2BX4T/graph.json","fetch_events":"https://pith.science/api/pith-number/QFRIRP7ULWP2SQUIKOCMY2BX4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T/action/storage_attestation","attest_author":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T/action/author_attestation","sign_citation":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T/action/citation_signature","submit_replication":"https://pith.science/pith/QFRIRP7ULWP2SQUIKOCMY2BX4T/action/replication_record"}},"created_at":"2026-07-05T09:59:34.718426+00:00","updated_at":"2026-07-05T09:59:34.718426+00:00"}